import os
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import zipfile
import cv2
from skimage import io
import tensorflow as tf
from tensorflow.python.keras import Sequential
from tensorflow.keras import layers, optimizers
from tensorflow.keras.layers import *
from tensorflow.keras.models import Model
from tensorflow.keras.initializers import glorot_uniform
from tensorflow.keras.utils import plot_model
from tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping, ModelCheckpoint, LearningRateScheduler
import tensorflow.keras.backend as K
import random
import glob
from sklearn.preprocessing import StandardScaler, normalize
from IPython.display import display
data = pd.read_csv('brain_dataset/lgg-mri-segmentation/kaggle_3m/data.csv')
data.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 110 entries, 0 to 109 Data columns (total 18 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Patient 110 non-null object 1 RNASeqCluster 92 non-null float64 2 MethylationCluster 109 non-null float64 3 miRNACluster 110 non-null int64 4 CNCluster 108 non-null float64 5 RPPACluster 98 non-null float64 6 OncosignCluster 105 non-null float64 7 COCCluster 110 non-null int64 8 histological_type 109 non-null float64 9 neoplasm_histologic_grade 109 non-null float64 10 tumor_tissue_site 109 non-null float64 11 laterality 109 non-null float64 12 tumor_location 109 non-null float64 13 gender 109 non-null float64 14 age_at_initial_pathologic 109 non-null float64 15 race 108 non-null float64 16 ethnicity 102 non-null float64 17 death01 109 non-null float64 dtypes: float64(15), int64(2), object(1) memory usage: 15.6+ KB
data.head(10)
| Patient | RNASeqCluster | MethylationCluster | miRNACluster | CNCluster | RPPACluster | OncosignCluster | COCCluster | histological_type | neoplasm_histologic_grade | tumor_tissue_site | laterality | tumor_location | gender | age_at_initial_pathologic | race | ethnicity | death01 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | TCGA_CS_4941 | 2.0 | 4.0 | 2 | 2.0 | NaN | 3.0 | 2 | 1.0 | 2.0 | 1.0 | 3.0 | 2.0 | 2.0 | 67.0 | 3.0 | 2.0 | 1.0 |
| 1 | TCGA_CS_4942 | 1.0 | 5.0 | 2 | 1.0 | 1.0 | 2.0 | 1 | 1.0 | 2.0 | 1.0 | 3.0 | 2.0 | 1.0 | 44.0 | 2.0 | NaN | 1.0 |
| 2 | TCGA_CS_4943 | 1.0 | 5.0 | 2 | 1.0 | 2.0 | 2.0 | 1 | 1.0 | 2.0 | 1.0 | 1.0 | 2.0 | 2.0 | 37.0 | 3.0 | NaN | 0.0 |
| 3 | TCGA_CS_4944 | NaN | 5.0 | 2 | 1.0 | 2.0 | 1.0 | 1 | 1.0 | 1.0 | 1.0 | 3.0 | 6.0 | 2.0 | 50.0 | 3.0 | NaN | 0.0 |
| 4 | TCGA_CS_5393 | 4.0 | 5.0 | 2 | 1.0 | 2.0 | 3.0 | 1 | 1.0 | 2.0 | 1.0 | 1.0 | 6.0 | 2.0 | 39.0 | 3.0 | NaN | 0.0 |
| 5 | TCGA_CS_5395 | 2.0 | 4.0 | 2 | 2.0 | NaN | 3.0 | 2 | 3.0 | 1.0 | 1.0 | 3.0 | 5.0 | 2.0 | 43.0 | 2.0 | NaN | 1.0 |
| 6 | TCGA_CS_5396 | 3.0 | 3.0 | 2 | 3.0 | 2.0 | 2.0 | 3 | 3.0 | 2.0 | 1.0 | 3.0 | 2.0 | 1.0 | 53.0 | 3.0 | 2.0 | 0.0 |
| 7 | TCGA_CS_5397 | NaN | 4.0 | 1 | 2.0 | 3.0 | 3.0 | 2 | 1.0 | 2.0 | 1.0 | 1.0 | 6.0 | 1.0 | 54.0 | 3.0 | 2.0 | 1.0 |
| 8 | TCGA_CS_6186 | 2.0 | 4.0 | 1 | 2.0 | 1.0 | 3.0 | 2 | 2.0 | 2.0 | 1.0 | 3.0 | 2.0 | 2.0 | 58.0 | 3.0 | 2.0 | 1.0 |
| 9 | TCGA_CS_6188 | 2.0 | 4.0 | 3 | 2.0 | 3.0 | 3.0 | 2 | 1.0 | 2.0 | 1.0 | 3.0 | 6.0 | 2.0 | 48.0 | 3.0 | 2.0 | 0.0 |
data_map = []
for sub_dir_path in glob.glob("brain_dataset/lgg-mri-segmentation/kaggle_3m/"+"*"):
#if os.path.isdir(sub_path_dir):
try:
dir_name = sub_dir_path.split('/')[-1]
for filename in os.listdir(sub_dir_path):
image_path = sub_dir_path + '/' + filename
data_map.extend([dir_name, image_path])
except Exception as e:
print(e)
[Errno 20] Not a directory: 'brain_dataset/lgg-mri-segmentation/kaggle_3m/data.csv' [Errno 20] Not a directory: 'brain_dataset/lgg-mri-segmentation/kaggle_3m/README.md'
df = pd.DataFrame({"patient_id" : data_map[::2],
"path" : data_map[1::2]})
df.head()
| patient_id | path | |
|---|---|---|
| 0 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... |
| 1 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... |
| 2 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... |
| 3 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... |
| 4 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... |
df_imgs = df[~df['path'].str.contains("mask")]
df_masks = df[df['path'].str.contains("mask")]
# File path line length images for later sorting
BASE_LEN = 89
END_IMG_LEN = 4
END_MASK_LEN = 9
# Data sorting
imgs = sorted(df_imgs["path"].values, key=lambda x : int(x[BASE_LEN:-END_IMG_LEN]))
masks = sorted(df_masks["path"].values, key=lambda x : int(x[BASE_LEN:-END_MASK_LEN]))
# Sorting check
idx = random.randint(0, len(imgs)-1)
print("Path to the Image:", imgs[idx], "\nPath to the Mask:", masks[idx])
Path to the Image: brain_dataset/lgg-mri-segmentation/kaggle_3m/TCGA_DU_A5TY_19970709/TCGA_DU_A5TY_19970709_36.tif Path to the Mask: brain_dataset/lgg-mri-segmentation/kaggle_3m/TCGA_DU_A5TY_19970709/TCGA_DU_A5TY_19970709_36_mask.tif
# Final dataframe
brain_df = pd.DataFrame({"patient_id": df_imgs.patient_id.values,
"image_path": imgs,
"mask_path": masks
})
def pos_neg_diagnosis(mask_path):
value = np.max(cv2.imread(mask_path))
if value > 0 :
return 1
else:
return 0
brain_df['mask'] = brain_df['mask_path'].apply(lambda x: pos_neg_diagnosis(x))
brain_df
| patient_id | image_path | mask_path | mask | |
|---|---|---|---|---|
| 0 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 1 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 2 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 3 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 4 | TCGA_CS_6667_20011105 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| ... | ... | ... | ... | ... |
| 3924 | TCGA_FG_A60K_20040224 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 3925 | TCGA_FG_A60K_20040224 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 3926 | TCGA_FG_A60K_20040224 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 3927 | TCGA_FG_A60K_20040224 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
| 3928 | TCGA_FG_A60K_20040224 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 |
3929 rows × 4 columns
brain_df['mask'].value_counts()
0 2556 1 1373 Name: mask, dtype: int64
import plotly.graph_objects as go # using plotly to create interactive plots
fig = go.Figure([go.Bar(x=brain_df['mask'].value_counts().index,
y=brain_df['mask'].value_counts(),
width=[.4, .4]
)
])
fig.update_traces(marker_color='rgb(158,202,225)', marker_line_color='rgb(8,48,107)',
marker_line_width=4, opacity=0.4
)
fig.update_layout(title_text="Mask Count Plot",
width=700,
height=550,
yaxis=dict(
title_text="Count",
tickmode="array",
titlefont=dict(size=20)
)
)
fig.update_yaxes(automargin=True)
fig.show()
for i in range(len(brain_df)):
if cv2.imread(brain_df.mask_path[i]).max() > 0:
break
plt.figure(figsize=(8,8))
plt.subplot(1,2,1)
plt.imshow(cv2.imread(brain_df.mask_path[i]));
plt.title('Tumor Location')
plt.subplot(1,2,2)
plt.imshow(cv2.imread(brain_df.image_path[i]));
cv2.imread(brain_df.mask_path[i]).max(), cv2.imread(brain_df.mask_path[i]).min()
(255, 0)
# Basic visualizations: Visualize the images (MRI and Mask) in the dataset separately
fig, axs = plt.subplots(6,2, figsize=(16,26))
count = 0
for x in range(6):
i = random.randint(0, len(brain_df)) # select a random index
axs[count][0].title.set_text("Brain MRI") # set title
axs[count][0].imshow(cv2.imread(brain_df.image_path[i])) # show MRI
axs[count][1].title.set_text("Mask - " + str(brain_df['mask'][i])) # plot title on the mask (0 or 1)
axs[count][1].imshow(cv2.imread(brain_df.mask_path[i])) # Show corresponding mask
count += 1
fig.tight_layout()
count = 0
i = 0
fig,axs = plt.subplots(12,3, figsize=(20,50))
for mask in brain_df['mask']:
if (mask==1):
img = io.imread(brain_df.image_path[i])
axs[count][0].title.set_text("Brain MRI")
axs[count][0].imshow(img)
mask = io.imread(brain_df.mask_path[i])
axs[count][1].title.set_text("Mask")
axs[count][1].imshow(mask, cmap='gray')
img[mask==255] = (0,255,150) # change pixel color at the position of mask
axs[count][2].title.set_text("MRI with Mask")
axs[count][2].imshow(img)
count +=1
i += 1
if (count==12):
break
fig.tight_layout()
brain_df_train = brain_df.drop(columns=['patient_id'])
# Convert the data in mask column to string format, to use categorical mode in flow_from_dataframe
brain_df_train['mask'] = brain_df_train['mask'].apply(lambda x: str(x))
brain_df_train.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 3929 entries, 0 to 3928 Data columns (total 3 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 image_path 3929 non-null object 1 mask_path 3929 non-null object 2 mask 3929 non-null object dtypes: object(3) memory usage: 92.2+ KB
from sklearn.model_selection import train_test_split
train, test = train_test_split(brain_df_train, test_size=0.15)
from keras_preprocessing.image import ImageDataGenerator
datagen = ImageDataGenerator(rescale=1./255., validation_split=0.1)
train_generator = datagen.flow_from_dataframe(train,
directory='./',
x_col='image_path',
y_col='mask',
subset='training',
class_mode='categorical',
batch_size=16,
shuffle=True,
target_size=(256,256)
)
valid_generator = datagen.flow_from_dataframe(train,
directory='./',
x_col='image_path',
y_col='mask',
subset='validation',
class_mode='categorical',
batch_size=16,
shuffle=True,
target_size=(256,256)
)
test_datagen = ImageDataGenerator(rescale=1./255.)
test_generator = test_datagen.flow_from_dataframe(test,
directory='./',
x_col='image_path',
y_col='mask',
class_mode='categorical',
batch_size=16,
shuffle=False,
target_size=(256,256)
)
Found 3006 validated image filenames belonging to 2 classes. Found 333 validated image filenames belonging to 2 classes. Found 590 validated image filenames belonging to 2 classes.
from tensorflow.keras.applications.resnet50 import ResNet50
clf_model = ResNet50(weights='imagenet', include_top=False, input_tensor=Input(shape=(256,256,3)))
clf_model.summary()
Model: "resnet50"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 256, 256, 3 0 []
)]
conv1_pad (ZeroPadding2D) (None, 262, 262, 3) 0 ['input_1[0][0]']
conv1_conv (Conv2D) (None, 128, 128, 64 9472 ['conv1_pad[0][0]']
)
conv1_bn (BatchNormalization) (None, 128, 128, 64 256 ['conv1_conv[0][0]']
)
conv1_relu (Activation) (None, 128, 128, 64 0 ['conv1_bn[0][0]']
)
pool1_pad (ZeroPadding2D) (None, 130, 130, 64 0 ['conv1_relu[0][0]']
)
pool1_pool (MaxPooling2D) (None, 64, 64, 64) 0 ['pool1_pad[0][0]']
conv2_block1_1_conv (Conv2D) (None, 64, 64, 64) 4160 ['pool1_pool[0][0]']
conv2_block1_1_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block1_1_conv[0][0]']
ization)
conv2_block1_1_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block1_1_bn[0][0]']
n)
conv2_block1_2_conv (Conv2D) (None, 64, 64, 64) 36928 ['conv2_block1_1_relu[0][0]']
conv2_block1_2_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block1_2_conv[0][0]']
ization)
conv2_block1_2_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block1_2_bn[0][0]']
n)
conv2_block1_0_conv (Conv2D) (None, 64, 64, 256) 16640 ['pool1_pool[0][0]']
conv2_block1_3_conv (Conv2D) (None, 64, 64, 256) 16640 ['conv2_block1_2_relu[0][0]']
conv2_block1_0_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block1_0_conv[0][0]']
ization)
conv2_block1_3_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block1_3_conv[0][0]']
ization)
conv2_block1_add (Add) (None, 64, 64, 256) 0 ['conv2_block1_0_bn[0][0]',
'conv2_block1_3_bn[0][0]']
conv2_block1_out (Activation) (None, 64, 64, 256) 0 ['conv2_block1_add[0][0]']
conv2_block2_1_conv (Conv2D) (None, 64, 64, 64) 16448 ['conv2_block1_out[0][0]']
conv2_block2_1_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block2_1_conv[0][0]']
ization)
conv2_block2_1_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block2_1_bn[0][0]']
n)
conv2_block2_2_conv (Conv2D) (None, 64, 64, 64) 36928 ['conv2_block2_1_relu[0][0]']
conv2_block2_2_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block2_2_conv[0][0]']
ization)
conv2_block2_2_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block2_2_bn[0][0]']
n)
conv2_block2_3_conv (Conv2D) (None, 64, 64, 256) 16640 ['conv2_block2_2_relu[0][0]']
conv2_block2_3_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block2_3_conv[0][0]']
ization)
conv2_block2_add (Add) (None, 64, 64, 256) 0 ['conv2_block1_out[0][0]',
'conv2_block2_3_bn[0][0]']
conv2_block2_out (Activation) (None, 64, 64, 256) 0 ['conv2_block2_add[0][0]']
conv2_block3_1_conv (Conv2D) (None, 64, 64, 64) 16448 ['conv2_block2_out[0][0]']
conv2_block3_1_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block3_1_conv[0][0]']
ization)
conv2_block3_1_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block3_1_bn[0][0]']
n)
conv2_block3_2_conv (Conv2D) (None, 64, 64, 64) 36928 ['conv2_block3_1_relu[0][0]']
conv2_block3_2_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block3_2_conv[0][0]']
ization)
conv2_block3_2_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block3_2_bn[0][0]']
n)
conv2_block3_3_conv (Conv2D) (None, 64, 64, 256) 16640 ['conv2_block3_2_relu[0][0]']
conv2_block3_3_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block3_3_conv[0][0]']
ization)
conv2_block3_add (Add) (None, 64, 64, 256) 0 ['conv2_block2_out[0][0]',
'conv2_block3_3_bn[0][0]']
conv2_block3_out (Activation) (None, 64, 64, 256) 0 ['conv2_block3_add[0][0]']
conv3_block1_1_conv (Conv2D) (None, 32, 32, 128) 32896 ['conv2_block3_out[0][0]']
conv3_block1_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block1_1_conv[0][0]']
ization)
conv3_block1_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block1_1_bn[0][0]']
n)
conv3_block1_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block1_1_relu[0][0]']
conv3_block1_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block1_2_conv[0][0]']
ization)
conv3_block1_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block1_2_bn[0][0]']
n)
conv3_block1_0_conv (Conv2D) (None, 32, 32, 512) 131584 ['conv2_block3_out[0][0]']
conv3_block1_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block1_2_relu[0][0]']
conv3_block1_0_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block1_0_conv[0][0]']
ization)
conv3_block1_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block1_3_conv[0][0]']
ization)
conv3_block1_add (Add) (None, 32, 32, 512) 0 ['conv3_block1_0_bn[0][0]',
'conv3_block1_3_bn[0][0]']
conv3_block1_out (Activation) (None, 32, 32, 512) 0 ['conv3_block1_add[0][0]']
conv3_block2_1_conv (Conv2D) (None, 32, 32, 128) 65664 ['conv3_block1_out[0][0]']
conv3_block2_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block2_1_conv[0][0]']
ization)
conv3_block2_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block2_1_bn[0][0]']
n)
conv3_block2_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block2_1_relu[0][0]']
conv3_block2_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block2_2_conv[0][0]']
ization)
conv3_block2_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block2_2_bn[0][0]']
n)
conv3_block2_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block2_2_relu[0][0]']
conv3_block2_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block2_3_conv[0][0]']
ization)
conv3_block2_add (Add) (None, 32, 32, 512) 0 ['conv3_block1_out[0][0]',
'conv3_block2_3_bn[0][0]']
conv3_block2_out (Activation) (None, 32, 32, 512) 0 ['conv3_block2_add[0][0]']
conv3_block3_1_conv (Conv2D) (None, 32, 32, 128) 65664 ['conv3_block2_out[0][0]']
conv3_block3_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block3_1_conv[0][0]']
ization)
conv3_block3_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block3_1_bn[0][0]']
n)
conv3_block3_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block3_1_relu[0][0]']
conv3_block3_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block3_2_conv[0][0]']
ization)
conv3_block3_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block3_2_bn[0][0]']
n)
conv3_block3_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block3_2_relu[0][0]']
conv3_block3_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block3_3_conv[0][0]']
ization)
conv3_block3_add (Add) (None, 32, 32, 512) 0 ['conv3_block2_out[0][0]',
'conv3_block3_3_bn[0][0]']
conv3_block3_out (Activation) (None, 32, 32, 512) 0 ['conv3_block3_add[0][0]']
conv3_block4_1_conv (Conv2D) (None, 32, 32, 128) 65664 ['conv3_block3_out[0][0]']
conv3_block4_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block4_1_conv[0][0]']
ization)
conv3_block4_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block4_1_bn[0][0]']
n)
conv3_block4_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block4_1_relu[0][0]']
conv3_block4_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block4_2_conv[0][0]']
ization)
conv3_block4_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block4_2_bn[0][0]']
n)
conv3_block4_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block4_2_relu[0][0]']
conv3_block4_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block4_3_conv[0][0]']
ization)
conv3_block4_add (Add) (None, 32, 32, 512) 0 ['conv3_block3_out[0][0]',
'conv3_block4_3_bn[0][0]']
conv3_block4_out (Activation) (None, 32, 32, 512) 0 ['conv3_block4_add[0][0]']
conv4_block1_1_conv (Conv2D) (None, 16, 16, 256) 131328 ['conv3_block4_out[0][0]']
conv4_block1_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block1_1_conv[0][0]']
ization)
conv4_block1_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block1_1_bn[0][0]']
n)
conv4_block1_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block1_1_relu[0][0]']
conv4_block1_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block1_2_conv[0][0]']
ization)
conv4_block1_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block1_2_bn[0][0]']
n)
conv4_block1_0_conv (Conv2D) (None, 16, 16, 1024 525312 ['conv3_block4_out[0][0]']
)
conv4_block1_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block1_2_relu[0][0]']
)
conv4_block1_0_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block1_0_conv[0][0]']
ization) )
conv4_block1_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block1_3_conv[0][0]']
ization) )
conv4_block1_add (Add) (None, 16, 16, 1024 0 ['conv4_block1_0_bn[0][0]',
) 'conv4_block1_3_bn[0][0]']
conv4_block1_out (Activation) (None, 16, 16, 1024 0 ['conv4_block1_add[0][0]']
)
conv4_block2_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block1_out[0][0]']
conv4_block2_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block2_1_conv[0][0]']
ization)
conv4_block2_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block2_1_bn[0][0]']
n)
conv4_block2_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block2_1_relu[0][0]']
conv4_block2_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block2_2_conv[0][0]']
ization)
conv4_block2_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block2_2_bn[0][0]']
n)
conv4_block2_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block2_2_relu[0][0]']
)
conv4_block2_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block2_3_conv[0][0]']
ization) )
conv4_block2_add (Add) (None, 16, 16, 1024 0 ['conv4_block1_out[0][0]',
) 'conv4_block2_3_bn[0][0]']
conv4_block2_out (Activation) (None, 16, 16, 1024 0 ['conv4_block2_add[0][0]']
)
conv4_block3_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block2_out[0][0]']
conv4_block3_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block3_1_conv[0][0]']
ization)
conv4_block3_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block3_1_bn[0][0]']
n)
conv4_block3_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block3_1_relu[0][0]']
conv4_block3_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block3_2_conv[0][0]']
ization)
conv4_block3_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block3_2_bn[0][0]']
n)
conv4_block3_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block3_2_relu[0][0]']
)
conv4_block3_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block3_3_conv[0][0]']
ization) )
conv4_block3_add (Add) (None, 16, 16, 1024 0 ['conv4_block2_out[0][0]',
) 'conv4_block3_3_bn[0][0]']
conv4_block3_out (Activation) (None, 16, 16, 1024 0 ['conv4_block3_add[0][0]']
)
conv4_block4_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block3_out[0][0]']
conv4_block4_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block4_1_conv[0][0]']
ization)
conv4_block4_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block4_1_bn[0][0]']
n)
conv4_block4_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block4_1_relu[0][0]']
conv4_block4_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block4_2_conv[0][0]']
ization)
conv4_block4_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block4_2_bn[0][0]']
n)
conv4_block4_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block4_2_relu[0][0]']
)
conv4_block4_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block4_3_conv[0][0]']
ization) )
conv4_block4_add (Add) (None, 16, 16, 1024 0 ['conv4_block3_out[0][0]',
) 'conv4_block4_3_bn[0][0]']
conv4_block4_out (Activation) (None, 16, 16, 1024 0 ['conv4_block4_add[0][0]']
)
conv4_block5_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block4_out[0][0]']
conv4_block5_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block5_1_conv[0][0]']
ization)
conv4_block5_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block5_1_bn[0][0]']
n)
conv4_block5_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block5_1_relu[0][0]']
conv4_block5_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block5_2_conv[0][0]']
ization)
conv4_block5_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block5_2_bn[0][0]']
n)
conv4_block5_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block5_2_relu[0][0]']
)
conv4_block5_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block5_3_conv[0][0]']
ization) )
conv4_block5_add (Add) (None, 16, 16, 1024 0 ['conv4_block4_out[0][0]',
) 'conv4_block5_3_bn[0][0]']
conv4_block5_out (Activation) (None, 16, 16, 1024 0 ['conv4_block5_add[0][0]']
)
conv4_block6_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block5_out[0][0]']
conv4_block6_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block6_1_conv[0][0]']
ization)
conv4_block6_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block6_1_bn[0][0]']
n)
conv4_block6_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block6_1_relu[0][0]']
conv4_block6_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block6_2_conv[0][0]']
ization)
conv4_block6_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block6_2_bn[0][0]']
n)
conv4_block6_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block6_2_relu[0][0]']
)
conv4_block6_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block6_3_conv[0][0]']
ization) )
conv4_block6_add (Add) (None, 16, 16, 1024 0 ['conv4_block5_out[0][0]',
) 'conv4_block6_3_bn[0][0]']
conv4_block6_out (Activation) (None, 16, 16, 1024 0 ['conv4_block6_add[0][0]']
)
conv5_block1_1_conv (Conv2D) (None, 8, 8, 512) 524800 ['conv4_block6_out[0][0]']
conv5_block1_1_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block1_1_conv[0][0]']
ization)
conv5_block1_1_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block1_1_bn[0][0]']
n)
conv5_block1_2_conv (Conv2D) (None, 8, 8, 512) 2359808 ['conv5_block1_1_relu[0][0]']
conv5_block1_2_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block1_2_conv[0][0]']
ization)
conv5_block1_2_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block1_2_bn[0][0]']
n)
conv5_block1_0_conv (Conv2D) (None, 8, 8, 2048) 2099200 ['conv4_block6_out[0][0]']
conv5_block1_3_conv (Conv2D) (None, 8, 8, 2048) 1050624 ['conv5_block1_2_relu[0][0]']
conv5_block1_0_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block1_0_conv[0][0]']
ization)
conv5_block1_3_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block1_3_conv[0][0]']
ization)
conv5_block1_add (Add) (None, 8, 8, 2048) 0 ['conv5_block1_0_bn[0][0]',
'conv5_block1_3_bn[0][0]']
conv5_block1_out (Activation) (None, 8, 8, 2048) 0 ['conv5_block1_add[0][0]']
conv5_block2_1_conv (Conv2D) (None, 8, 8, 512) 1049088 ['conv5_block1_out[0][0]']
conv5_block2_1_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block2_1_conv[0][0]']
ization)
conv5_block2_1_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block2_1_bn[0][0]']
n)
conv5_block2_2_conv (Conv2D) (None, 8, 8, 512) 2359808 ['conv5_block2_1_relu[0][0]']
conv5_block2_2_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block2_2_conv[0][0]']
ization)
conv5_block2_2_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block2_2_bn[0][0]']
n)
conv5_block2_3_conv (Conv2D) (None, 8, 8, 2048) 1050624 ['conv5_block2_2_relu[0][0]']
conv5_block2_3_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block2_3_conv[0][0]']
ization)
conv5_block2_add (Add) (None, 8, 8, 2048) 0 ['conv5_block1_out[0][0]',
'conv5_block2_3_bn[0][0]']
conv5_block2_out (Activation) (None, 8, 8, 2048) 0 ['conv5_block2_add[0][0]']
conv5_block3_1_conv (Conv2D) (None, 8, 8, 512) 1049088 ['conv5_block2_out[0][0]']
conv5_block3_1_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block3_1_conv[0][0]']
ization)
conv5_block3_1_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block3_1_bn[0][0]']
n)
conv5_block3_2_conv (Conv2D) (None, 8, 8, 512) 2359808 ['conv5_block3_1_relu[0][0]']
conv5_block3_2_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block3_2_conv[0][0]']
ization)
conv5_block3_2_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block3_2_bn[0][0]']
n)
conv5_block3_3_conv (Conv2D) (None, 8, 8, 2048) 1050624 ['conv5_block3_2_relu[0][0]']
conv5_block3_3_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block3_3_conv[0][0]']
ization)
conv5_block3_add (Add) (None, 8, 8, 2048) 0 ['conv5_block2_out[0][0]',
'conv5_block3_3_bn[0][0]']
conv5_block3_out (Activation) (None, 8, 8, 2048) 0 ['conv5_block3_add[0][0]']
==================================================================================================
Total params: 23,587,712
Trainable params: 23,534,592
Non-trainable params: 53,120
__________________________________________________________________________________________________
# before this i tried with trainable layer but the accuracy was less as compared
for layer in clf_model.layers:
layers.trainable = False
head = clf_model.output
head = AveragePooling2D(pool_size=(4,4))(head)
head = Flatten(name='Flatten')(head)
head = Dense(256, activation='relu')(head)
head = Dropout(0.3)(head)
head = Dense(256, activation='relu')(head)
head = Dropout(0.3)(head)
head = Dense(2, activation='softmax')(head)
model = Model(clf_model.input, head)
model.compile(loss = 'categorical_crossentropy',
optimizer='adam',
metrics= ["accuracy"]
)
model.summary()
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 256, 256, 3 0 []
)]
conv1_pad (ZeroPadding2D) (None, 262, 262, 3) 0 ['input_1[0][0]']
conv1_conv (Conv2D) (None, 128, 128, 64 9472 ['conv1_pad[0][0]']
)
conv1_bn (BatchNormalization) (None, 128, 128, 64 256 ['conv1_conv[0][0]']
)
conv1_relu (Activation) (None, 128, 128, 64 0 ['conv1_bn[0][0]']
)
pool1_pad (ZeroPadding2D) (None, 130, 130, 64 0 ['conv1_relu[0][0]']
)
pool1_pool (MaxPooling2D) (None, 64, 64, 64) 0 ['pool1_pad[0][0]']
conv2_block1_1_conv (Conv2D) (None, 64, 64, 64) 4160 ['pool1_pool[0][0]']
conv2_block1_1_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block1_1_conv[0][0]']
ization)
conv2_block1_1_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block1_1_bn[0][0]']
n)
conv2_block1_2_conv (Conv2D) (None, 64, 64, 64) 36928 ['conv2_block1_1_relu[0][0]']
conv2_block1_2_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block1_2_conv[0][0]']
ization)
conv2_block1_2_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block1_2_bn[0][0]']
n)
conv2_block1_0_conv (Conv2D) (None, 64, 64, 256) 16640 ['pool1_pool[0][0]']
conv2_block1_3_conv (Conv2D) (None, 64, 64, 256) 16640 ['conv2_block1_2_relu[0][0]']
conv2_block1_0_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block1_0_conv[0][0]']
ization)
conv2_block1_3_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block1_3_conv[0][0]']
ization)
conv2_block1_add (Add) (None, 64, 64, 256) 0 ['conv2_block1_0_bn[0][0]',
'conv2_block1_3_bn[0][0]']
conv2_block1_out (Activation) (None, 64, 64, 256) 0 ['conv2_block1_add[0][0]']
conv2_block2_1_conv (Conv2D) (None, 64, 64, 64) 16448 ['conv2_block1_out[0][0]']
conv2_block2_1_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block2_1_conv[0][0]']
ization)
conv2_block2_1_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block2_1_bn[0][0]']
n)
conv2_block2_2_conv (Conv2D) (None, 64, 64, 64) 36928 ['conv2_block2_1_relu[0][0]']
conv2_block2_2_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block2_2_conv[0][0]']
ization)
conv2_block2_2_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block2_2_bn[0][0]']
n)
conv2_block2_3_conv (Conv2D) (None, 64, 64, 256) 16640 ['conv2_block2_2_relu[0][0]']
conv2_block2_3_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block2_3_conv[0][0]']
ization)
conv2_block2_add (Add) (None, 64, 64, 256) 0 ['conv2_block1_out[0][0]',
'conv2_block2_3_bn[0][0]']
conv2_block2_out (Activation) (None, 64, 64, 256) 0 ['conv2_block2_add[0][0]']
conv2_block3_1_conv (Conv2D) (None, 64, 64, 64) 16448 ['conv2_block2_out[0][0]']
conv2_block3_1_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block3_1_conv[0][0]']
ization)
conv2_block3_1_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block3_1_bn[0][0]']
n)
conv2_block3_2_conv (Conv2D) (None, 64, 64, 64) 36928 ['conv2_block3_1_relu[0][0]']
conv2_block3_2_bn (BatchNormal (None, 64, 64, 64) 256 ['conv2_block3_2_conv[0][0]']
ization)
conv2_block3_2_relu (Activatio (None, 64, 64, 64) 0 ['conv2_block3_2_bn[0][0]']
n)
conv2_block3_3_conv (Conv2D) (None, 64, 64, 256) 16640 ['conv2_block3_2_relu[0][0]']
conv2_block3_3_bn (BatchNormal (None, 64, 64, 256) 1024 ['conv2_block3_3_conv[0][0]']
ization)
conv2_block3_add (Add) (None, 64, 64, 256) 0 ['conv2_block2_out[0][0]',
'conv2_block3_3_bn[0][0]']
conv2_block3_out (Activation) (None, 64, 64, 256) 0 ['conv2_block3_add[0][0]']
conv3_block1_1_conv (Conv2D) (None, 32, 32, 128) 32896 ['conv2_block3_out[0][0]']
conv3_block1_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block1_1_conv[0][0]']
ization)
conv3_block1_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block1_1_bn[0][0]']
n)
conv3_block1_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block1_1_relu[0][0]']
conv3_block1_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block1_2_conv[0][0]']
ization)
conv3_block1_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block1_2_bn[0][0]']
n)
conv3_block1_0_conv (Conv2D) (None, 32, 32, 512) 131584 ['conv2_block3_out[0][0]']
conv3_block1_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block1_2_relu[0][0]']
conv3_block1_0_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block1_0_conv[0][0]']
ization)
conv3_block1_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block1_3_conv[0][0]']
ization)
conv3_block1_add (Add) (None, 32, 32, 512) 0 ['conv3_block1_0_bn[0][0]',
'conv3_block1_3_bn[0][0]']
conv3_block1_out (Activation) (None, 32, 32, 512) 0 ['conv3_block1_add[0][0]']
conv3_block2_1_conv (Conv2D) (None, 32, 32, 128) 65664 ['conv3_block1_out[0][0]']
conv3_block2_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block2_1_conv[0][0]']
ization)
conv3_block2_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block2_1_bn[0][0]']
n)
conv3_block2_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block2_1_relu[0][0]']
conv3_block2_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block2_2_conv[0][0]']
ization)
conv3_block2_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block2_2_bn[0][0]']
n)
conv3_block2_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block2_2_relu[0][0]']
conv3_block2_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block2_3_conv[0][0]']
ization)
conv3_block2_add (Add) (None, 32, 32, 512) 0 ['conv3_block1_out[0][0]',
'conv3_block2_3_bn[0][0]']
conv3_block2_out (Activation) (None, 32, 32, 512) 0 ['conv3_block2_add[0][0]']
conv3_block3_1_conv (Conv2D) (None, 32, 32, 128) 65664 ['conv3_block2_out[0][0]']
conv3_block3_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block3_1_conv[0][0]']
ization)
conv3_block3_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block3_1_bn[0][0]']
n)
conv3_block3_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block3_1_relu[0][0]']
conv3_block3_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block3_2_conv[0][0]']
ization)
conv3_block3_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block3_2_bn[0][0]']
n)
conv3_block3_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block3_2_relu[0][0]']
conv3_block3_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block3_3_conv[0][0]']
ization)
conv3_block3_add (Add) (None, 32, 32, 512) 0 ['conv3_block2_out[0][0]',
'conv3_block3_3_bn[0][0]']
conv3_block3_out (Activation) (None, 32, 32, 512) 0 ['conv3_block3_add[0][0]']
conv3_block4_1_conv (Conv2D) (None, 32, 32, 128) 65664 ['conv3_block3_out[0][0]']
conv3_block4_1_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block4_1_conv[0][0]']
ization)
conv3_block4_1_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block4_1_bn[0][0]']
n)
conv3_block4_2_conv (Conv2D) (None, 32, 32, 128) 147584 ['conv3_block4_1_relu[0][0]']
conv3_block4_2_bn (BatchNormal (None, 32, 32, 128) 512 ['conv3_block4_2_conv[0][0]']
ization)
conv3_block4_2_relu (Activatio (None, 32, 32, 128) 0 ['conv3_block4_2_bn[0][0]']
n)
conv3_block4_3_conv (Conv2D) (None, 32, 32, 512) 66048 ['conv3_block4_2_relu[0][0]']
conv3_block4_3_bn (BatchNormal (None, 32, 32, 512) 2048 ['conv3_block4_3_conv[0][0]']
ization)
conv3_block4_add (Add) (None, 32, 32, 512) 0 ['conv3_block3_out[0][0]',
'conv3_block4_3_bn[0][0]']
conv3_block4_out (Activation) (None, 32, 32, 512) 0 ['conv3_block4_add[0][0]']
conv4_block1_1_conv (Conv2D) (None, 16, 16, 256) 131328 ['conv3_block4_out[0][0]']
conv4_block1_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block1_1_conv[0][0]']
ization)
conv4_block1_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block1_1_bn[0][0]']
n)
conv4_block1_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block1_1_relu[0][0]']
conv4_block1_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block1_2_conv[0][0]']
ization)
conv4_block1_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block1_2_bn[0][0]']
n)
conv4_block1_0_conv (Conv2D) (None, 16, 16, 1024 525312 ['conv3_block4_out[0][0]']
)
conv4_block1_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block1_2_relu[0][0]']
)
conv4_block1_0_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block1_0_conv[0][0]']
ization) )
conv4_block1_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block1_3_conv[0][0]']
ization) )
conv4_block1_add (Add) (None, 16, 16, 1024 0 ['conv4_block1_0_bn[0][0]',
) 'conv4_block1_3_bn[0][0]']
conv4_block1_out (Activation) (None, 16, 16, 1024 0 ['conv4_block1_add[0][0]']
)
conv4_block2_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block1_out[0][0]']
conv4_block2_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block2_1_conv[0][0]']
ization)
conv4_block2_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block2_1_bn[0][0]']
n)
conv4_block2_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block2_1_relu[0][0]']
conv4_block2_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block2_2_conv[0][0]']
ization)
conv4_block2_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block2_2_bn[0][0]']
n)
conv4_block2_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block2_2_relu[0][0]']
)
conv4_block2_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block2_3_conv[0][0]']
ization) )
conv4_block2_add (Add) (None, 16, 16, 1024 0 ['conv4_block1_out[0][0]',
) 'conv4_block2_3_bn[0][0]']
conv4_block2_out (Activation) (None, 16, 16, 1024 0 ['conv4_block2_add[0][0]']
)
conv4_block3_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block2_out[0][0]']
conv4_block3_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block3_1_conv[0][0]']
ization)
conv4_block3_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block3_1_bn[0][0]']
n)
conv4_block3_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block3_1_relu[0][0]']
conv4_block3_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block3_2_conv[0][0]']
ization)
conv4_block3_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block3_2_bn[0][0]']
n)
conv4_block3_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block3_2_relu[0][0]']
)
conv4_block3_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block3_3_conv[0][0]']
ization) )
conv4_block3_add (Add) (None, 16, 16, 1024 0 ['conv4_block2_out[0][0]',
) 'conv4_block3_3_bn[0][0]']
conv4_block3_out (Activation) (None, 16, 16, 1024 0 ['conv4_block3_add[0][0]']
)
conv4_block4_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block3_out[0][0]']
conv4_block4_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block4_1_conv[0][0]']
ization)
conv4_block4_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block4_1_bn[0][0]']
n)
conv4_block4_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block4_1_relu[0][0]']
conv4_block4_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block4_2_conv[0][0]']
ization)
conv4_block4_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block4_2_bn[0][0]']
n)
conv4_block4_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block4_2_relu[0][0]']
)
conv4_block4_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block4_3_conv[0][0]']
ization) )
conv4_block4_add (Add) (None, 16, 16, 1024 0 ['conv4_block3_out[0][0]',
) 'conv4_block4_3_bn[0][0]']
conv4_block4_out (Activation) (None, 16, 16, 1024 0 ['conv4_block4_add[0][0]']
)
conv4_block5_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block4_out[0][0]']
conv4_block5_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block5_1_conv[0][0]']
ization)
conv4_block5_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block5_1_bn[0][0]']
n)
conv4_block5_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block5_1_relu[0][0]']
conv4_block5_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block5_2_conv[0][0]']
ization)
conv4_block5_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block5_2_bn[0][0]']
n)
conv4_block5_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block5_2_relu[0][0]']
)
conv4_block5_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block5_3_conv[0][0]']
ization) )
conv4_block5_add (Add) (None, 16, 16, 1024 0 ['conv4_block4_out[0][0]',
) 'conv4_block5_3_bn[0][0]']
conv4_block5_out (Activation) (None, 16, 16, 1024 0 ['conv4_block5_add[0][0]']
)
conv4_block6_1_conv (Conv2D) (None, 16, 16, 256) 262400 ['conv4_block5_out[0][0]']
conv4_block6_1_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block6_1_conv[0][0]']
ization)
conv4_block6_1_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block6_1_bn[0][0]']
n)
conv4_block6_2_conv (Conv2D) (None, 16, 16, 256) 590080 ['conv4_block6_1_relu[0][0]']
conv4_block6_2_bn (BatchNormal (None, 16, 16, 256) 1024 ['conv4_block6_2_conv[0][0]']
ization)
conv4_block6_2_relu (Activatio (None, 16, 16, 256) 0 ['conv4_block6_2_bn[0][0]']
n)
conv4_block6_3_conv (Conv2D) (None, 16, 16, 1024 263168 ['conv4_block6_2_relu[0][0]']
)
conv4_block6_3_bn (BatchNormal (None, 16, 16, 1024 4096 ['conv4_block6_3_conv[0][0]']
ization) )
conv4_block6_add (Add) (None, 16, 16, 1024 0 ['conv4_block5_out[0][0]',
) 'conv4_block6_3_bn[0][0]']
conv4_block6_out (Activation) (None, 16, 16, 1024 0 ['conv4_block6_add[0][0]']
)
conv5_block1_1_conv (Conv2D) (None, 8, 8, 512) 524800 ['conv4_block6_out[0][0]']
conv5_block1_1_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block1_1_conv[0][0]']
ization)
conv5_block1_1_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block1_1_bn[0][0]']
n)
conv5_block1_2_conv (Conv2D) (None, 8, 8, 512) 2359808 ['conv5_block1_1_relu[0][0]']
conv5_block1_2_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block1_2_conv[0][0]']
ization)
conv5_block1_2_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block1_2_bn[0][0]']
n)
conv5_block1_0_conv (Conv2D) (None, 8, 8, 2048) 2099200 ['conv4_block6_out[0][0]']
conv5_block1_3_conv (Conv2D) (None, 8, 8, 2048) 1050624 ['conv5_block1_2_relu[0][0]']
conv5_block1_0_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block1_0_conv[0][0]']
ization)
conv5_block1_3_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block1_3_conv[0][0]']
ization)
conv5_block1_add (Add) (None, 8, 8, 2048) 0 ['conv5_block1_0_bn[0][0]',
'conv5_block1_3_bn[0][0]']
conv5_block1_out (Activation) (None, 8, 8, 2048) 0 ['conv5_block1_add[0][0]']
conv5_block2_1_conv (Conv2D) (None, 8, 8, 512) 1049088 ['conv5_block1_out[0][0]']
conv5_block2_1_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block2_1_conv[0][0]']
ization)
conv5_block2_1_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block2_1_bn[0][0]']
n)
conv5_block2_2_conv (Conv2D) (None, 8, 8, 512) 2359808 ['conv5_block2_1_relu[0][0]']
conv5_block2_2_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block2_2_conv[0][0]']
ization)
conv5_block2_2_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block2_2_bn[0][0]']
n)
conv5_block2_3_conv (Conv2D) (None, 8, 8, 2048) 1050624 ['conv5_block2_2_relu[0][0]']
conv5_block2_3_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block2_3_conv[0][0]']
ization)
conv5_block2_add (Add) (None, 8, 8, 2048) 0 ['conv5_block1_out[0][0]',
'conv5_block2_3_bn[0][0]']
conv5_block2_out (Activation) (None, 8, 8, 2048) 0 ['conv5_block2_add[0][0]']
conv5_block3_1_conv (Conv2D) (None, 8, 8, 512) 1049088 ['conv5_block2_out[0][0]']
conv5_block3_1_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block3_1_conv[0][0]']
ization)
conv5_block3_1_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block3_1_bn[0][0]']
n)
conv5_block3_2_conv (Conv2D) (None, 8, 8, 512) 2359808 ['conv5_block3_1_relu[0][0]']
conv5_block3_2_bn (BatchNormal (None, 8, 8, 512) 2048 ['conv5_block3_2_conv[0][0]']
ization)
conv5_block3_2_relu (Activatio (None, 8, 8, 512) 0 ['conv5_block3_2_bn[0][0]']
n)
conv5_block3_3_conv (Conv2D) (None, 8, 8, 2048) 1050624 ['conv5_block3_2_relu[0][0]']
conv5_block3_3_bn (BatchNormal (None, 8, 8, 2048) 8192 ['conv5_block3_3_conv[0][0]']
ization)
conv5_block3_add (Add) (None, 8, 8, 2048) 0 ['conv5_block2_out[0][0]',
'conv5_block3_3_bn[0][0]']
conv5_block3_out (Activation) (None, 8, 8, 2048) 0 ['conv5_block3_add[0][0]']
average_pooling2d (AveragePool (None, 2, 2, 2048) 0 ['conv5_block3_out[0][0]']
ing2D)
Flatten (Flatten) (None, 8192) 0 ['average_pooling2d[0][0]']
dense (Dense) (None, 256) 2097408 ['Flatten[0][0]']
dropout (Dropout) (None, 256) 0 ['dense[0][0]']
dense_1 (Dense) (None, 256) 65792 ['dropout[0][0]']
dropout_1 (Dropout) (None, 256) 0 ['dense_1[0][0]']
dense_2 (Dense) (None, 2) 514 ['dropout_1[0][0]']
==================================================================================================
Total params: 25,751,426
Trainable params: 25,698,306
Non-trainable params: 53,120
__________________________________________________________________________________________________
earlystopping = EarlyStopping(monitor='val_loss',
mode='min',
verbose=1,
patience=15
)
checkpointer = ModelCheckpoint(filepath="clf-resnet-weights.hdf5",
verbose=1,
save_best_only=True
)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
mode='min',
verbose=1,
patience=10,
min_delta=0.0001,
factor=0.2
)
callbacks = [checkpointer, earlystopping, reduce_lr]
h = model.fit(train_generator,
steps_per_epoch= train_generator.n // train_generator.batch_size,
epochs = 50,
validation_data= valid_generator,
validation_steps= valid_generator.n // valid_generator.batch_size,
callbacks=[checkpointer, earlystopping])
Epoch 1/50
2023-01-13 07:40:11.581318: W tensorflow/tsl/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz
187/187 [==============================] - ETA: 0s - loss: 0.7085 - accuracy: 0.7278 Epoch 1: val_loss improved from inf to 1.07708, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 522s 3s/step - loss: 0.7085 - accuracy: 0.7278 - val_loss: 1.0771 - val_accuracy: 0.6281 Epoch 2/50 187/187 [==============================] - ETA: 0s - loss: 0.4584 - accuracy: 0.7977 Epoch 2: val_loss improved from 1.07708 to 0.82635, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 523s 3s/step - loss: 0.4584 - accuracy: 0.7977 - val_loss: 0.8264 - val_accuracy: 0.6250 Epoch 3/50 187/187 [==============================] - ETA: 0s - loss: 0.3876 - accuracy: 0.8355 Epoch 3: val_loss improved from 0.82635 to 0.69625, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 526s 3s/step - loss: 0.3876 - accuracy: 0.8355 - val_loss: 0.6962 - val_accuracy: 0.6219 Epoch 4/50 187/187 [==============================] - ETA: 0s - loss: 0.3591 - accuracy: 0.8619 Epoch 4: val_loss did not improve from 0.69625 187/187 [==============================] - 543s 3s/step - loss: 0.3591 - accuracy: 0.8619 - val_loss: 1.0981 - val_accuracy: 0.6375 Epoch 5/50 187/187 [==============================] - ETA: 0s - loss: 0.3425 - accuracy: 0.8726 Epoch 5: val_loss improved from 0.69625 to 0.59643, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 535s 3s/step - loss: 0.3425 - accuracy: 0.8726 - val_loss: 0.5964 - val_accuracy: 0.6719 Epoch 6/50 187/187 [==============================] - ETA: 0s - loss: 0.3549 - accuracy: 0.8595 Epoch 6: val_loss did not improve from 0.59643 187/187 [==============================] - 528s 3s/step - loss: 0.3549 - accuracy: 0.8595 - val_loss: 1.0486 - val_accuracy: 0.7750 Epoch 7/50 187/187 [==============================] - ETA: 0s - loss: 0.2745 - accuracy: 0.8963 Epoch 7: val_loss improved from 0.59643 to 0.23840, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 530s 3s/step - loss: 0.2745 - accuracy: 0.8963 - val_loss: 0.2384 - val_accuracy: 0.9187 Epoch 8/50 187/187 [==============================] - ETA: 0s - loss: 0.2036 - accuracy: 0.9284 Epoch 8: val_loss did not improve from 0.23840 187/187 [==============================] - 533s 3s/step - loss: 0.2036 - accuracy: 0.9284 - val_loss: 0.2434 - val_accuracy: 0.9187 Epoch 9/50 187/187 [==============================] - ETA: 0s - loss: 0.1963 - accuracy: 0.9251 Epoch 9: val_loss improved from 0.23840 to 0.17171, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 521s 3s/step - loss: 0.1963 - accuracy: 0.9251 - val_loss: 0.1717 - val_accuracy: 0.9375 Epoch 10/50 187/187 [==============================] - ETA: 0s - loss: 0.2147 - accuracy: 0.9164 Epoch 10: val_loss did not improve from 0.17171 187/187 [==============================] - 506s 3s/step - loss: 0.2147 - accuracy: 0.9164 - val_loss: 0.4331 - val_accuracy: 0.8594 Epoch 11/50 187/187 [==============================] - ETA: 0s - loss: 0.1850 - accuracy: 0.9368 Epoch 11: val_loss did not improve from 0.17171 187/187 [==============================] - 512s 3s/step - loss: 0.1850 - accuracy: 0.9368 - val_loss: 0.6973 - val_accuracy: 0.8750 Epoch 12/50 187/187 [==============================] - ETA: 0s - loss: 0.1636 - accuracy: 0.9344 Epoch 12: val_loss did not improve from 0.17171 187/187 [==============================] - 508s 3s/step - loss: 0.1636 - accuracy: 0.9344 - val_loss: 0.2608 - val_accuracy: 0.8813 Epoch 13/50 187/187 [==============================] - ETA: 0s - loss: 0.1713 - accuracy: 0.9411 Epoch 13: val_loss did not improve from 0.17171 187/187 [==============================] - 512s 3s/step - loss: 0.1713 - accuracy: 0.9411 - val_loss: 0.5337 - val_accuracy: 0.9094 Epoch 14/50 187/187 [==============================] - ETA: 0s - loss: 0.1335 - accuracy: 0.9599 Epoch 14: val_loss improved from 0.17171 to 0.10353, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 511s 3s/step - loss: 0.1335 - accuracy: 0.9599 - val_loss: 0.1035 - val_accuracy: 0.9781 Epoch 15/50 187/187 [==============================] - ETA: 0s - loss: 0.1293 - accuracy: 0.9482 Epoch 15: val_loss did not improve from 0.10353 187/187 [==============================] - 508s 3s/step - loss: 0.1293 - accuracy: 0.9482 - val_loss: 0.1207 - val_accuracy: 0.9594 Epoch 16/50 187/187 [==============================] - ETA: 0s - loss: 0.1008 - accuracy: 0.9659 Epoch 16: val_loss did not improve from 0.10353 187/187 [==============================] - 506s 3s/step - loss: 0.1008 - accuracy: 0.9659 - val_loss: 0.2903 - val_accuracy: 0.9281 Epoch 17/50 187/187 [==============================] - ETA: 0s - loss: 0.1004 - accuracy: 0.9629 Epoch 17: val_loss did not improve from 0.10353 187/187 [==============================] - 506s 3s/step - loss: 0.1004 - accuracy: 0.9629 - val_loss: 0.1218 - val_accuracy: 0.9563 Epoch 18/50 187/187 [==============================] - ETA: 0s - loss: 0.0914 - accuracy: 0.9679 Epoch 18: val_loss did not improve from 0.10353 187/187 [==============================] - 508s 3s/step - loss: 0.0914 - accuracy: 0.9679 - val_loss: 0.1768 - val_accuracy: 0.9406 Epoch 19/50 187/187 [==============================] - ETA: 0s - loss: 0.0961 - accuracy: 0.9672 Epoch 19: val_loss did not improve from 0.10353 187/187 [==============================] - 507s 3s/step - loss: 0.0961 - accuracy: 0.9672 - val_loss: 0.2162 - val_accuracy: 0.9031 Epoch 20/50 187/187 [==============================] - ETA: 0s - loss: 0.1060 - accuracy: 0.9629 Epoch 20: val_loss did not improve from 0.10353 187/187 [==============================] - 506s 3s/step - loss: 0.1060 - accuracy: 0.9629 - val_loss: 0.1717 - val_accuracy: 0.9375 Epoch 21/50 187/187 [==============================] - ETA: 0s - loss: 0.0834 - accuracy: 0.9753 Epoch 21: val_loss did not improve from 0.10353 187/187 [==============================] - 508s 3s/step - loss: 0.0834 - accuracy: 0.9753 - val_loss: 0.1652 - val_accuracy: 0.9656 Epoch 22/50 187/187 [==============================] - ETA: 0s - loss: 0.0828 - accuracy: 0.9742 Epoch 22: val_loss did not improve from 0.10353 187/187 [==============================] - 512s 3s/step - loss: 0.0828 - accuracy: 0.9742 - val_loss: 0.2636 - val_accuracy: 0.9312 Epoch 23/50 187/187 [==============================] - ETA: 0s - loss: 0.0769 - accuracy: 0.9796 Epoch 23: val_loss improved from 0.10353 to 0.08339, saving model to clf-resnet-weights.hdf5 187/187 [==============================] - 510s 3s/step - loss: 0.0769 - accuracy: 0.9796 - val_loss: 0.0834 - val_accuracy: 0.9750 Epoch 24/50 187/187 [==============================] - ETA: 0s - loss: 0.0577 - accuracy: 0.9816 Epoch 24: val_loss did not improve from 0.08339 187/187 [==============================] - 509s 3s/step - loss: 0.0577 - accuracy: 0.9816 - val_loss: 0.2484 - val_accuracy: 0.9375 Epoch 25/50 187/187 [==============================] - ETA: 0s - loss: 0.0802 - accuracy: 0.9719 Epoch 25: val_loss did not improve from 0.08339 187/187 [==============================] - 508s 3s/step - loss: 0.0802 - accuracy: 0.9719 - val_loss: 0.1346 - val_accuracy: 0.9594 Epoch 26/50 187/187 [==============================] - ETA: 0s - loss: 0.0269 - accuracy: 0.9913 Epoch 26: val_loss did not improve from 0.08339 187/187 [==============================] - 508s 3s/step - loss: 0.0269 - accuracy: 0.9913 - val_loss: 0.1674 - val_accuracy: 0.9656 Epoch 27/50 187/187 [==============================] - ETA: 0s - loss: 0.0628 - accuracy: 0.9783 Epoch 27: val_loss did not improve from 0.08339 187/187 [==============================] - 506s 3s/step - loss: 0.0628 - accuracy: 0.9783 - val_loss: 0.2157 - val_accuracy: 0.9406 Epoch 28/50 187/187 [==============================] - ETA: 0s - loss: 0.0791 - accuracy: 0.9742 Epoch 28: val_loss did not improve from 0.08339 187/187 [==============================] - 508s 3s/step - loss: 0.0791 - accuracy: 0.9742 - val_loss: 0.1559 - val_accuracy: 0.9563 Epoch 29/50 187/187 [==============================] - ETA: 0s - loss: 0.0532 - accuracy: 0.9846 Epoch 29: val_loss did not improve from 0.08339 187/187 [==============================] - 508s 3s/step - loss: 0.0532 - accuracy: 0.9846 - val_loss: 0.1498 - val_accuracy: 0.9469 Epoch 30/50 187/187 [==============================] - ETA: 0s - loss: 0.0643 - accuracy: 0.9829 Epoch 30: val_loss did not improve from 0.08339 187/187 [==============================] - 508s 3s/step - loss: 0.0643 - accuracy: 0.9829 - val_loss: 0.1310 - val_accuracy: 0.9594 Epoch 31/50 187/187 [==============================] - ETA: 0s - loss: 0.0594 - accuracy: 0.9823 Epoch 31: val_loss did not improve from 0.08339 187/187 [==============================] - 507s 3s/step - loss: 0.0594 - accuracy: 0.9823 - val_loss: 0.1268 - val_accuracy: 0.9563 Epoch 32/50 187/187 [==============================] - ETA: 0s - loss: 0.0771 - accuracy: 0.9739 Epoch 32: val_loss did not improve from 0.08339 187/187 [==============================] - 509s 3s/step - loss: 0.0771 - accuracy: 0.9739 - val_loss: 0.3002 - val_accuracy: 0.9531 Epoch 33/50 187/187 [==============================] - ETA: 0s - loss: 0.0742 - accuracy: 0.9783 Epoch 33: val_loss did not improve from 0.08339 187/187 [==============================] - 510s 3s/step - loss: 0.0742 - accuracy: 0.9783 - val_loss: 0.6265 - val_accuracy: 0.8875 Epoch 34/50 187/187 [==============================] - ETA: 0s - loss: 0.0647 - accuracy: 0.9773 Epoch 34: val_loss did not improve from 0.08339 187/187 [==============================] - 509s 3s/step - loss: 0.0647 - accuracy: 0.9773 - val_loss: 0.1176 - val_accuracy: 0.9594 Epoch 35/50 187/187 [==============================] - ETA: 0s - loss: 0.0489 - accuracy: 0.9856 Epoch 35: val_loss did not improve from 0.08339 187/187 [==============================] - 508s 3s/step - loss: 0.0489 - accuracy: 0.9856 - val_loss: 0.2906 - val_accuracy: 0.8969 Epoch 36/50 187/187 [==============================] - ETA: 0s - loss: 0.0451 - accuracy: 0.9866 Epoch 36: val_loss did not improve from 0.08339 187/187 [==============================] - 514s 3s/step - loss: 0.0451 - accuracy: 0.9866 - val_loss: 0.1928 - val_accuracy: 0.9438 Epoch 37/50 187/187 [==============================] - ETA: 0s - loss: 0.0451 - accuracy: 0.9846 Epoch 37: val_loss did not improve from 0.08339 187/187 [==============================] - 514s 3s/step - loss: 0.0451 - accuracy: 0.9846 - val_loss: 0.1868 - val_accuracy: 0.9594 Epoch 38/50 187/187 [==============================] - ETA: 0s - loss: 0.0179 - accuracy: 0.9953 Epoch 38: val_loss did not improve from 0.08339 187/187 [==============================] - 516s 3s/step - loss: 0.0179 - accuracy: 0.9953 - val_loss: 0.1485 - val_accuracy: 0.9656 Epoch 38: early stopping
# saving model achitecture in json file
model_json = model.to_json()
with open("clf-resnet-model.json", "w") as json_file:
json_file.write(model_json)
h.history.keys()
dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])
plt.figure(figsize=(12,5))
plt.subplot(1,2,1)
plt.plot(h.history['loss']);
plt.plot(h.history['val_loss']);
plt.title("Classification Model LOSS");
plt.ylabel("loss");
plt.xlabel("Epochs");
plt.legend(['train', 'val']);
plt.subplot(1,2,2)
plt.plot(h.history['accuracy']);
plt.plot(h.history['val_accuracy']);
plt.title("Classification Model Acc");
plt.ylabel("Accuracy");
plt.xlabel("Epochs");
plt.legend(['train', 'val']);
_, acc = model.evaluate(test_generator)
print("Test accuracy : {} %".format(acc*100))
37/37 [==============================] - 25s 674ms/step - loss: 0.2195 - accuracy: 0.9424 Test accuracy : 94.23728585243225 %
prediction = model.predict(test_generator)
pred = np.argmax(prediction, axis=1)
#pred = np.asarray(pred).astype('str')
original = np.asarray(test['mask']).astype('int')
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
accuracy = accuracy_score(original, pred)
print(accuracy)
cm = confusion_matrix(original, pred)
report = classification_report(original, pred, labels = [0,1])
print(report)
plt.figure(figsize = (5,5))
sns.heatmap(cm, annot=True);
37/37 [==============================] - 25s 663ms/step
0.9423728813559322
precision recall f1-score support
0 0.96 0.95 0.95 378
1 0.91 0.93 0.92 212
accuracy 0.94 590
macro avg 0.94 0.94 0.94 590
weighted avg 0.94 0.94 0.94 590
brain_df_mask = brain_df[brain_df['mask'] == 1]
brain_df_mask.shape
(1373, 4)
# creating test, train and val sets
X_train, X_val = train_test_split(brain_df_mask, test_size=0.15)
X_test, X_val = train_test_split(X_val, test_size=0.5)
print("Train size is {}, valid size is {} & test size is {}".format(len(X_train), len(X_val), len(X_test)))
train_ids = list(X_train.image_path)
train_mask = list(X_train.mask_path)
val_ids = list(X_val.image_path)
val_mask= list(X_val.mask_path)
Train size is 1167, valid size is 103 & test size is 103
class DataGenerator(tf.keras.utils.Sequence):
def __init__(self, ids , mask, image_dir = './', batch_size = 16, img_h = 256, img_w = 256, shuffle = True):
self.ids = ids
self.mask = mask
self.image_dir = image_dir
self.batch_size = batch_size
self.img_h = img_h
self.img_w = img_w
self.shuffle = shuffle
self.on_epoch_end()
def __len__(self):
'Get the number of batches per epoch'
return int(np.floor(len(self.ids)) / self.batch_size)
def __getitem__(self, index):
'Generate a batch of data'
#generate index of batch_size length
indexes = self.indexes[index* self.batch_size : (index+1) * self.batch_size]
#get the ImageId corresponding to the indexes created above based on batch size
list_ids = [self.ids[i] for i in indexes]
#get the MaskId corresponding to the indexes created above based on batch size
list_mask = [self.mask[i] for i in indexes]
#generate data for the X(features) and y(label)
X, y = self.__data_generation(list_ids, list_mask)
#returning the data
return X, y
def on_epoch_end(self):
'Used for updating the indices after each epoch, once at the beginning as well as at the end of each epoch'
#getting the array of indices based on the input dataframe
self.indexes = np.arange(len(self.ids))
#if shuffle is true, shuffle the indices
if self.shuffle:
np.random.shuffle(self.indexes)
def __data_generation(self, list_ids, list_mask):
'generate the data corresponding the indexes in a given batch of images'
# create empty arrays of shape (batch_size,height,width,depth)
#Depth is 3 for input and depth is taken as 1 for output becasue mask consist only of 1 channel.
X = np.empty((self.batch_size, self.img_h, self.img_w, 3))
y = np.empty((self.batch_size, self.img_h, self.img_w, 1))
#iterate through the dataframe rows, whose size is equal to the batch_size
for i in range(len(list_ids)):
#path of the image
img_path = str(list_ids[i])
#mask path
mask_path = str(list_mask[i])
#reading the original image and the corresponding mask image
img = io.imread(img_path)
mask = io.imread(mask_path)
#resizing and coverting them to array of type float64
img = cv2.resize(img,(self.img_h,self.img_w))
img = np.array(img, dtype = np.float64)
mask = cv2.resize(mask,(self.img_h,self.img_w))
mask = np.array(mask, dtype = np.float64)
#standardising
img -= img.mean()
img /= img.std()
mask -= mask.mean()
mask /= mask.std()
#Adding image to the empty array
X[i,] = img
#expanding the dimnesion of the image from (256,256) to (256,256,1)
y[i,] = np.expand_dims(mask, axis = 2)
#normalizing y
y = (y > 0).astype(int)
return X, y
train_data = DataGenerator(train_ids, train_mask)
val_data = DataGenerator(val_ids, val_mask)
It's been a while since the inception of U-Net, the network was initially designed to do medical image segmentation but since then it’s been used for all sorts of segmentation tasks. In my limited experience, I’ve always found that segmentation works better than object detection (given that you have the labeled data). The probable reason for segmentation being better than detection is that it is learning to identify each pixel as part of the object or not whereas detection tries to learn the four sets of coordinates surrounding the object (a much tougher and error-prone task to optimize).
To understand the architecture of U-Net let’s understand the given task first. Given an input image the network should try to generate a segmentation output mask which means each pixel should be classified as the desired object or not (look at the figure below). So, the idea behind U-net was that, if we feed the image to an encoder that keeps decreasing the spatial size of the feature block; after sufficient training, the network will generalize to store only the important features and discard away less useful data. Finally, the output of the encoder followed by a decoder will generate the desired output mask. The problem was that the decoder layers were not getting enough context in order to generate the segmentation mask from the encoder output.
The great idea introduced in the U-Net paper to solve the context issue was to add skip connections from the encoder to the decoder before each size-reduction step. Given below is the architecture of the U-Net, we can see that after applying two Conv blocks image is reduced by half, and from each Conv block (2 Conv blocks), there is a skip connection that takes the features from the encoder and concatenates them to the decoder thus giving the decoder enough context to generate proper segmentation mask. If we replace the operation of concatenation with addition we get the network called LinkNet. LinkNet performs similar to the U-Net (in some cases even beating the U-Net).
ResUnet is a very interesting idea that takes the performance gain of Residual networks and uses it with the U-Net. Given below is the architecture of ResUnet. In my testing, I’ve found that it is a very capable network but with a slightly large number of parameters.
# lets create model now
def resblock(X, f):
'''
function for creating res block
'''
X_copy = X #copy of input
# main path
X = Conv2D(f, kernel_size=(1,1), kernel_initializer='he_normal')(X)
X = BatchNormalization()(X)
X = Activation('relu')(X)
X = Conv2D(f, kernel_size=(3,3), padding='same', kernel_initializer='he_normal')(X)
X = BatchNormalization()(X)
# shortcut path
X_copy = Conv2D(f, kernel_size=(1,1), kernel_initializer='he_normal')(X_copy)
X_copy = BatchNormalization()(X_copy)
# Adding the output from main path and short path together
X = Add()([X, X_copy])
X = Activation('relu')(X)
return X
def upsample_concat(x, skip):
'''
funtion for upsampling image
'''
X = UpSampling2D((2,2))(x)
merge = Concatenate()([X, skip])
return merge
input_shape = (256,256,3)
X_input = Input(input_shape) #iniating tensor of input shape
# Stage 1
conv_1 = Conv2D(16, 3, activation='relu', padding='same', kernel_initializer='he_normal')(X_input)
conv_1 = BatchNormalization()(conv_1)
conv_1 = Conv2D(16, 3, activation='relu', padding='same', kernel_initializer='he_normal')(conv_1)
conv_1 = BatchNormalization()(conv_1)
pool_1 = MaxPool2D((2,2))(conv_1)
# stage 2
conv_2 = resblock(pool_1, 32)
pool_2 = MaxPool2D((2,2))(conv_2)
# Stage 3
conv_3 = resblock(pool_2, 64)
pool_3 = MaxPool2D((2,2))(conv_3)
# Stage 4
conv_4 = resblock(pool_3, 128)
pool_4 = MaxPool2D((2,2))(conv_4)
# Stage 5 (bottle neck)
conv_5 = resblock(pool_4, 256)
# Upsample Stage 1
up_1 = upsample_concat(conv_5, conv_4)
up_1 = resblock(up_1, 128)
# Upsample Stage 2
up_2 = upsample_concat(up_1, conv_3)
up_2 = resblock(up_2, 64)
# Upsample Stage 3
up_3 = upsample_concat(up_2, conv_2)
up_3 = resblock(up_3, 32)
# Upsample Stage 4
up_4 = upsample_concat(up_3, conv_1)
up_4 = resblock(up_4, 16)
# final output
out = Conv2D(1, (1,1), kernel_initializer='he_normal', padding='same', activation='sigmoid')(up_4)
seg_model = Model(X_input, out)
seg_model.summary()
Model: "model_1"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_2 (InputLayer) [(None, 256, 256, 3 0 []
)]
conv2d (Conv2D) (None, 256, 256, 16 448 ['input_2[0][0]']
)
batch_normalization (BatchNorm (None, 256, 256, 16 64 ['conv2d[0][0]']
alization) )
conv2d_1 (Conv2D) (None, 256, 256, 16 2320 ['batch_normalization[0][0]']
)
batch_normalization_1 (BatchNo (None, 256, 256, 16 64 ['conv2d_1[0][0]']
rmalization) )
max_pooling2d (MaxPooling2D) (None, 128, 128, 16 0 ['batch_normalization_1[0][0]']
)
conv2d_2 (Conv2D) (None, 128, 128, 32 544 ['max_pooling2d[0][0]']
)
batch_normalization_2 (BatchNo (None, 128, 128, 32 128 ['conv2d_2[0][0]']
rmalization) )
activation (Activation) (None, 128, 128, 32 0 ['batch_normalization_2[0][0]']
)
conv2d_3 (Conv2D) (None, 128, 128, 32 9248 ['activation[0][0]']
)
conv2d_4 (Conv2D) (None, 128, 128, 32 544 ['max_pooling2d[0][0]']
)
batch_normalization_3 (BatchNo (None, 128, 128, 32 128 ['conv2d_3[0][0]']
rmalization) )
batch_normalization_4 (BatchNo (None, 128, 128, 32 128 ['conv2d_4[0][0]']
rmalization) )
add (Add) (None, 128, 128, 32 0 ['batch_normalization_3[0][0]',
) 'batch_normalization_4[0][0]']
activation_1 (Activation) (None, 128, 128, 32 0 ['add[0][0]']
)
max_pooling2d_1 (MaxPooling2D) (None, 64, 64, 32) 0 ['activation_1[0][0]']
conv2d_5 (Conv2D) (None, 64, 64, 64) 2112 ['max_pooling2d_1[0][0]']
batch_normalization_5 (BatchNo (None, 64, 64, 64) 256 ['conv2d_5[0][0]']
rmalization)
activation_2 (Activation) (None, 64, 64, 64) 0 ['batch_normalization_5[0][0]']
conv2d_6 (Conv2D) (None, 64, 64, 64) 36928 ['activation_2[0][0]']
conv2d_7 (Conv2D) (None, 64, 64, 64) 2112 ['max_pooling2d_1[0][0]']
batch_normalization_6 (BatchNo (None, 64, 64, 64) 256 ['conv2d_6[0][0]']
rmalization)
batch_normalization_7 (BatchNo (None, 64, 64, 64) 256 ['conv2d_7[0][0]']
rmalization)
add_1 (Add) (None, 64, 64, 64) 0 ['batch_normalization_6[0][0]',
'batch_normalization_7[0][0]']
activation_3 (Activation) (None, 64, 64, 64) 0 ['add_1[0][0]']
max_pooling2d_2 (MaxPooling2D) (None, 32, 32, 64) 0 ['activation_3[0][0]']
conv2d_8 (Conv2D) (None, 32, 32, 128) 8320 ['max_pooling2d_2[0][0]']
batch_normalization_8 (BatchNo (None, 32, 32, 128) 512 ['conv2d_8[0][0]']
rmalization)
activation_4 (Activation) (None, 32, 32, 128) 0 ['batch_normalization_8[0][0]']
conv2d_9 (Conv2D) (None, 32, 32, 128) 147584 ['activation_4[0][0]']
conv2d_10 (Conv2D) (None, 32, 32, 128) 8320 ['max_pooling2d_2[0][0]']
batch_normalization_9 (BatchNo (None, 32, 32, 128) 512 ['conv2d_9[0][0]']
rmalization)
batch_normalization_10 (BatchN (None, 32, 32, 128) 512 ['conv2d_10[0][0]']
ormalization)
add_2 (Add) (None, 32, 32, 128) 0 ['batch_normalization_9[0][0]',
'batch_normalization_10[0][0]']
activation_5 (Activation) (None, 32, 32, 128) 0 ['add_2[0][0]']
max_pooling2d_3 (MaxPooling2D) (None, 16, 16, 128) 0 ['activation_5[0][0]']
conv2d_11 (Conv2D) (None, 16, 16, 256) 33024 ['max_pooling2d_3[0][0]']
batch_normalization_11 (BatchN (None, 16, 16, 256) 1024 ['conv2d_11[0][0]']
ormalization)
activation_6 (Activation) (None, 16, 16, 256) 0 ['batch_normalization_11[0][0]']
conv2d_12 (Conv2D) (None, 16, 16, 256) 590080 ['activation_6[0][0]']
conv2d_13 (Conv2D) (None, 16, 16, 256) 33024 ['max_pooling2d_3[0][0]']
batch_normalization_12 (BatchN (None, 16, 16, 256) 1024 ['conv2d_12[0][0]']
ormalization)
batch_normalization_13 (BatchN (None, 16, 16, 256) 1024 ['conv2d_13[0][0]']
ormalization)
add_3 (Add) (None, 16, 16, 256) 0 ['batch_normalization_12[0][0]',
'batch_normalization_13[0][0]']
activation_7 (Activation) (None, 16, 16, 256) 0 ['add_3[0][0]']
up_sampling2d (UpSampling2D) (None, 32, 32, 256) 0 ['activation_7[0][0]']
concatenate (Concatenate) (None, 32, 32, 384) 0 ['up_sampling2d[0][0]',
'activation_5[0][0]']
conv2d_14 (Conv2D) (None, 32, 32, 128) 49280 ['concatenate[0][0]']
batch_normalization_14 (BatchN (None, 32, 32, 128) 512 ['conv2d_14[0][0]']
ormalization)
activation_8 (Activation) (None, 32, 32, 128) 0 ['batch_normalization_14[0][0]']
conv2d_15 (Conv2D) (None, 32, 32, 128) 147584 ['activation_8[0][0]']
conv2d_16 (Conv2D) (None, 32, 32, 128) 49280 ['concatenate[0][0]']
batch_normalization_15 (BatchN (None, 32, 32, 128) 512 ['conv2d_15[0][0]']
ormalization)
batch_normalization_16 (BatchN (None, 32, 32, 128) 512 ['conv2d_16[0][0]']
ormalization)
add_4 (Add) (None, 32, 32, 128) 0 ['batch_normalization_15[0][0]',
'batch_normalization_16[0][0]']
activation_9 (Activation) (None, 32, 32, 128) 0 ['add_4[0][0]']
up_sampling2d_1 (UpSampling2D) (None, 64, 64, 128) 0 ['activation_9[0][0]']
concatenate_1 (Concatenate) (None, 64, 64, 192) 0 ['up_sampling2d_1[0][0]',
'activation_3[0][0]']
conv2d_17 (Conv2D) (None, 64, 64, 64) 12352 ['concatenate_1[0][0]']
batch_normalization_17 (BatchN (None, 64, 64, 64) 256 ['conv2d_17[0][0]']
ormalization)
activation_10 (Activation) (None, 64, 64, 64) 0 ['batch_normalization_17[0][0]']
conv2d_18 (Conv2D) (None, 64, 64, 64) 36928 ['activation_10[0][0]']
conv2d_19 (Conv2D) (None, 64, 64, 64) 12352 ['concatenate_1[0][0]']
batch_normalization_18 (BatchN (None, 64, 64, 64) 256 ['conv2d_18[0][0]']
ormalization)
batch_normalization_19 (BatchN (None, 64, 64, 64) 256 ['conv2d_19[0][0]']
ormalization)
add_5 (Add) (None, 64, 64, 64) 0 ['batch_normalization_18[0][0]',
'batch_normalization_19[0][0]']
activation_11 (Activation) (None, 64, 64, 64) 0 ['add_5[0][0]']
up_sampling2d_2 (UpSampling2D) (None, 128, 128, 64 0 ['activation_11[0][0]']
)
concatenate_2 (Concatenate) (None, 128, 128, 96 0 ['up_sampling2d_2[0][0]',
) 'activation_1[0][0]']
conv2d_20 (Conv2D) (None, 128, 128, 32 3104 ['concatenate_2[0][0]']
)
batch_normalization_20 (BatchN (None, 128, 128, 32 128 ['conv2d_20[0][0]']
ormalization) )
activation_12 (Activation) (None, 128, 128, 32 0 ['batch_normalization_20[0][0]']
)
conv2d_21 (Conv2D) (None, 128, 128, 32 9248 ['activation_12[0][0]']
)
conv2d_22 (Conv2D) (None, 128, 128, 32 3104 ['concatenate_2[0][0]']
)
batch_normalization_21 (BatchN (None, 128, 128, 32 128 ['conv2d_21[0][0]']
ormalization) )
batch_normalization_22 (BatchN (None, 128, 128, 32 128 ['conv2d_22[0][0]']
ormalization) )
add_6 (Add) (None, 128, 128, 32 0 ['batch_normalization_21[0][0]',
) 'batch_normalization_22[0][0]']
activation_13 (Activation) (None, 128, 128, 32 0 ['add_6[0][0]']
)
up_sampling2d_3 (UpSampling2D) (None, 256, 256, 32 0 ['activation_13[0][0]']
)
concatenate_3 (Concatenate) (None, 256, 256, 48 0 ['up_sampling2d_3[0][0]',
) 'batch_normalization_1[0][0]']
conv2d_23 (Conv2D) (None, 256, 256, 16 784 ['concatenate_3[0][0]']
)
batch_normalization_23 (BatchN (None, 256, 256, 16 64 ['conv2d_23[0][0]']
ormalization) )
activation_14 (Activation) (None, 256, 256, 16 0 ['batch_normalization_23[0][0]']
)
conv2d_24 (Conv2D) (None, 256, 256, 16 2320 ['activation_14[0][0]']
)
conv2d_25 (Conv2D) (None, 256, 256, 16 784 ['concatenate_3[0][0]']
)
batch_normalization_24 (BatchN (None, 256, 256, 16 64 ['conv2d_24[0][0]']
ormalization) )
batch_normalization_25 (BatchN (None, 256, 256, 16 64 ['conv2d_25[0][0]']
ormalization) )
add_7 (Add) (None, 256, 256, 16 0 ['batch_normalization_24[0][0]',
) 'batch_normalization_25[0][0]']
activation_15 (Activation) (None, 256, 256, 16 0 ['add_7[0][0]']
)
conv2d_26 (Conv2D) (None, 256, 256, 1) 17 ['activation_15[0][0]']
==================================================================================================
Total params: 1,210,513
Trainable params: 1,206,129
Non-trainable params: 4,384
__________________________________________________________________________________________________
from keras.losses import binary_crossentropy
epsilon = 1e-5
smooth = 1
def tversky(y_true, y_pred):
y_true_pos = K.flatten(y_true)
y_pred_pos = K.flatten(y_pred)
true_pos = K.sum(y_true_pos * y_pred_pos)
false_neg = K.sum(y_true_pos * (1-y_pred_pos))
false_pos = K.sum((1-y_true_pos)*y_pred_pos)
alpha = 0.7
return (true_pos + smooth)/(true_pos + alpha*false_neg + (1-alpha)*false_pos + smooth)
def focal_tversky(y_true,y_pred):
y_true = tf.cast(y_true, tf.float32)
y_pred = tf.cast(y_pred, tf.float32)
pt_1 = tversky(y_true, y_pred)
gamma = 0.75
return K.pow((1-pt_1), gamma)
def tversky_loss(y_true, y_pred):
return 1 - tversky(y_true,y_pred)
# compling model and callbacks functions
adam = tf.keras.optimizers.Adam(lr = 0.05, epsilon = 0.1)
seg_model.compile(optimizer = adam,
loss = focal_tversky,
metrics = [tversky]
)
#callbacks
earlystopping = EarlyStopping(monitor='val_loss',
mode='min',
verbose=1,
patience=20
)
# save the best model with lower validation loss
checkpointer = ModelCheckpoint(filepath="ResUNet-segModel-weights.hdf5",
verbose=1,
save_best_only=True
)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
mode='min',
verbose=1,
patience=10,
min_delta=0.0001,
factor=0.2
)
WARNING:absl:`lr` is deprecated, please use `learning_rate` instead, or use the legacy optimizer, e.g.,tf.keras.optimizers.legacy.Adam.
h = seg_model.fit(train_data,
epochs = 60,
validation_data = val_data,
callbacks = [checkpointer, earlystopping, reduce_lr]
)
Epoch 1/60 72/72 [==============================] - ETA: 0s - loss: 0.9108 - tversky: 0.1171 Epoch 1: val_loss improved from inf to 0.90497, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 129s 2s/step - loss: 0.9108 - tversky: 0.1171 - val_loss: 0.9050 - val_tversky: 0.1246 - lr: 0.0010 Epoch 2/60 72/72 [==============================] - ETA: 0s - loss: 0.8959 - tversky: 0.1362 Epoch 2: val_loss improved from 0.90497 to 0.89721, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 127s 2s/step - loss: 0.8959 - tversky: 0.1362 - val_loss: 0.8972 - val_tversky: 0.1346 - lr: 0.0010 Epoch 3/60 72/72 [==============================] - ETA: 0s - loss: 0.8848 - tversky: 0.1505 Epoch 3: val_loss improved from 0.89721 to 0.88756, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 128s 2s/step - loss: 0.8848 - tversky: 0.1505 - val_loss: 0.8876 - val_tversky: 0.1470 - lr: 0.0010 Epoch 4/60 72/72 [==============================] - ETA: 0s - loss: 0.8758 - tversky: 0.1619 Epoch 4: val_loss improved from 0.88756 to 0.87454, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 121s 2s/step - loss: 0.8758 - tversky: 0.1619 - val_loss: 0.8745 - val_tversky: 0.1636 - lr: 0.0010 Epoch 5/60 72/72 [==============================] - ETA: 0s - loss: 0.8681 - tversky: 0.1718 Epoch 5: val_loss improved from 0.87454 to 0.86393, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 136s 2s/step - loss: 0.8681 - tversky: 0.1718 - val_loss: 0.8639 - val_tversky: 0.1771 - lr: 0.0010 Epoch 6/60 72/72 [==============================] - ETA: 0s - loss: 0.8603 - tversky: 0.1816 Epoch 6: val_loss improved from 0.86393 to 0.85728, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 131s 2s/step - loss: 0.8603 - tversky: 0.1816 - val_loss: 0.8573 - val_tversky: 0.1855 - lr: 0.0010 Epoch 7/60 72/72 [==============================] - ETA: 0s - loss: 0.8525 - tversky: 0.1915 Epoch 7: val_loss improved from 0.85728 to 0.85344, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 137s 2s/step - loss: 0.8525 - tversky: 0.1915 - val_loss: 0.8534 - val_tversky: 0.1903 - lr: 0.0010 Epoch 8/60 72/72 [==============================] - ETA: 0s - loss: 0.8438 - tversky: 0.2024 Epoch 8: val_loss improved from 0.85344 to 0.84383, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 134s 2s/step - loss: 0.8438 - tversky: 0.2024 - val_loss: 0.8438 - val_tversky: 0.2025 - lr: 0.0010 Epoch 9/60 72/72 [==============================] - ETA: 0s - loss: 0.8354 - tversky: 0.2130 Epoch 9: val_loss improved from 0.84383 to 0.83372, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 135s 2s/step - loss: 0.8354 - tversky: 0.2130 - val_loss: 0.8337 - val_tversky: 0.2152 - lr: 0.0010 Epoch 10/60 72/72 [==============================] - ETA: 0s - loss: 0.8258 - tversky: 0.2250 Epoch 10: val_loss improved from 0.83372 to 0.81608, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 135s 2s/step - loss: 0.8258 - tversky: 0.2250 - val_loss: 0.8161 - val_tversky: 0.2373 - lr: 0.0010 Epoch 11/60 72/72 [==============================] - ETA: 0s - loss: 0.8125 - tversky: 0.2416 Epoch 11: val_loss improved from 0.81608 to 0.80185, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 131s 2s/step - loss: 0.8125 - tversky: 0.2416 - val_loss: 0.8018 - val_tversky: 0.2547 - lr: 0.0010 Epoch 12/60 72/72 [==============================] - ETA: 0s - loss: 0.7941 - tversky: 0.2643 Epoch 12: val_loss improved from 0.80185 to 0.78781, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 133s 2s/step - loss: 0.7941 - tversky: 0.2643 - val_loss: 0.7878 - val_tversky: 0.2721 - lr: 0.0010 Epoch 13/60 72/72 [==============================] - ETA: 0s - loss: 0.7711 - tversky: 0.2925 Epoch 13: val_loss improved from 0.78781 to 0.75006, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 129s 2s/step - loss: 0.7711 - tversky: 0.2925 - val_loss: 0.7501 - val_tversky: 0.3184 - lr: 0.0010 Epoch 14/60 72/72 [==============================] - ETA: 0s - loss: 0.7396 - tversky: 0.3308 Epoch 14: val_loss improved from 0.75006 to 0.71277, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 127s 2s/step - loss: 0.7396 - tversky: 0.3308 - val_loss: 0.7128 - val_tversky: 0.3629 - lr: 0.0010 Epoch 15/60 72/72 [==============================] - ETA: 0s - loss: 0.7021 - tversky: 0.3753 Epoch 15: val_loss improved from 0.71277 to 0.67982, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 120s 2s/step - loss: 0.7021 - tversky: 0.3753 - val_loss: 0.6798 - val_tversky: 0.4011 - lr: 0.0010 Epoch 16/60 72/72 [==============================] - ETA: 0s - loss: 0.6574 - tversky: 0.4276 Epoch 16: val_loss improved from 0.67982 to 0.64098, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 122s 2s/step - loss: 0.6574 - tversky: 0.4276 - val_loss: 0.6410 - val_tversky: 0.4470 - lr: 0.0010 Epoch 17/60 72/72 [==============================] - ETA: 0s - loss: 0.6182 - tversky: 0.4721 Epoch 17: val_loss improved from 0.64098 to 0.58106, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 124s 2s/step - loss: 0.6182 - tversky: 0.4721 - val_loss: 0.5811 - val_tversky: 0.5146 - lr: 0.0010 Epoch 18/60 72/72 [==============================] - ETA: 0s - loss: 0.5748 - tversky: 0.5211 Epoch 18: val_loss improved from 0.58106 to 0.54863, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 122s 2s/step - loss: 0.5748 - tversky: 0.5211 - val_loss: 0.5486 - val_tversky: 0.5497 - lr: 0.0010 Epoch 19/60 72/72 [==============================] - ETA: 0s - loss: 0.5401 - tversky: 0.5587 Epoch 19: val_loss improved from 0.54863 to 0.51370, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 126s 2s/step - loss: 0.5401 - tversky: 0.5587 - val_loss: 0.5137 - val_tversky: 0.5873 - lr: 0.0010 Epoch 20/60 72/72 [==============================] - ETA: 0s - loss: 0.5144 - tversky: 0.5859 Epoch 20: val_loss improved from 0.51370 to 0.48971, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 119s 2s/step - loss: 0.5144 - tversky: 0.5859 - val_loss: 0.4897 - val_tversky: 0.6105 - lr: 0.0010 Epoch 21/60 72/72 [==============================] - ETA: 0s - loss: 0.4952 - tversky: 0.6066 Epoch 21: val_loss improved from 0.48971 to 0.48735, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 123s 2s/step - loss: 0.4952 - tversky: 0.6066 - val_loss: 0.4873 - val_tversky: 0.6153 - lr: 0.0010 Epoch 22/60 72/72 [==============================] - ETA: 0s - loss: 0.4764 - tversky: 0.6263 Epoch 22: val_loss improved from 0.48735 to 0.47520, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 127s 2s/step - loss: 0.4764 - tversky: 0.6263 - val_loss: 0.4752 - val_tversky: 0.6275 - lr: 0.0010 Epoch 23/60 72/72 [==============================] - ETA: 0s - loss: 0.4607 - tversky: 0.6426 Epoch 23: val_loss improved from 0.47520 to 0.45390, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 124s 2s/step - loss: 0.4607 - tversky: 0.6426 - val_loss: 0.4539 - val_tversky: 0.6505 - lr: 0.0010 Epoch 24/60 72/72 [==============================] - ETA: 0s - loss: 0.4442 - tversky: 0.6590 Epoch 24: val_loss improved from 0.45390 to 0.44585, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 119s 2s/step - loss: 0.4442 - tversky: 0.6590 - val_loss: 0.4458 - val_tversky: 0.6586 - lr: 0.0010 Epoch 25/60 72/72 [==============================] - ETA: 0s - loss: 0.4249 - tversky: 0.6790 Epoch 25: val_loss did not improve from 0.44585 72/72 [==============================] - 121s 2s/step - loss: 0.4249 - tversky: 0.6790 - val_loss: 0.4510 - val_tversky: 0.6516 - lr: 0.0010 Epoch 26/60 72/72 [==============================] - ETA: 0s - loss: 0.4112 - tversky: 0.6926 Epoch 26: val_loss improved from 0.44585 to 0.41146, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 116s 2s/step - loss: 0.4112 - tversky: 0.6926 - val_loss: 0.4115 - val_tversky: 0.6923 - lr: 0.0010 Epoch 27/60 72/72 [==============================] - ETA: 0s - loss: 0.4021 - tversky: 0.7008 Epoch 27: val_loss improved from 0.41146 to 0.40334, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 118s 2s/step - loss: 0.4021 - tversky: 0.7008 - val_loss: 0.4033 - val_tversky: 0.7011 - lr: 0.0010 Epoch 28/60 72/72 [==============================] - ETA: 0s - loss: 0.3935 - tversky: 0.7099 Epoch 28: val_loss improved from 0.40334 to 0.38929, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 120s 2s/step - loss: 0.3935 - tversky: 0.7099 - val_loss: 0.3893 - val_tversky: 0.7152 - lr: 0.0010 Epoch 29/60 72/72 [==============================] - ETA: 0s - loss: 0.3785 - tversky: 0.7240 Epoch 29: val_loss did not improve from 0.38929 72/72 [==============================] - 121s 2s/step - loss: 0.3785 - tversky: 0.7240 - val_loss: 0.3896 - val_tversky: 0.7143 - lr: 0.0010 Epoch 30/60 72/72 [==============================] - ETA: 0s - loss: 0.3718 - tversky: 0.7309 Epoch 30: val_loss improved from 0.38929 to 0.37345, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 116s 2s/step - loss: 0.3718 - tversky: 0.7309 - val_loss: 0.3735 - val_tversky: 0.7302 - lr: 0.0010 Epoch 31/60 72/72 [==============================] - ETA: 0s - loss: 0.3632 - tversky: 0.7392 Epoch 31: val_loss did not improve from 0.37345 72/72 [==============================] - 120s 2s/step - loss: 0.3632 - tversky: 0.7392 - val_loss: 0.3815 - val_tversky: 0.7213 - lr: 0.0010 Epoch 32/60 72/72 [==============================] - ETA: 0s - loss: 0.3505 - tversky: 0.7511 Epoch 32: val_loss improved from 0.37345 to 0.35426, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 116s 2s/step - loss: 0.3505 - tversky: 0.7511 - val_loss: 0.3543 - val_tversky: 0.7485 - lr: 0.0010 Epoch 33/60 72/72 [==============================] - ETA: 0s - loss: 0.3475 - tversky: 0.7537 Epoch 33: val_loss improved from 0.35426 to 0.35403, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 117s 2s/step - loss: 0.3475 - tversky: 0.7537 - val_loss: 0.3540 - val_tversky: 0.7482 - lr: 0.0010 Epoch 34/60 72/72 [==============================] - ETA: 0s - loss: 0.3326 - tversky: 0.7683 Epoch 34: val_loss improved from 0.35403 to 0.35246, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 120s 2s/step - loss: 0.3326 - tversky: 0.7683 - val_loss: 0.3525 - val_tversky: 0.7501 - lr: 0.0010 Epoch 35/60 72/72 [==============================] - ETA: 0s - loss: 0.3302 - tversky: 0.7699 Epoch 35: val_loss improved from 0.35246 to 0.33997, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 123s 2s/step - loss: 0.3302 - tversky: 0.7699 - val_loss: 0.3400 - val_tversky: 0.7609 - lr: 0.0010 Epoch 36/60 72/72 [==============================] - ETA: 0s - loss: 0.3185 - tversky: 0.7814 Epoch 36: val_loss did not improve from 0.33997 72/72 [==============================] - 120s 2s/step - loss: 0.3185 - tversky: 0.7814 - val_loss: 0.3501 - val_tversky: 0.7523 - lr: 0.0010 Epoch 37/60 72/72 [==============================] - ETA: 0s - loss: 0.3156 - tversky: 0.7838 Epoch 37: val_loss did not improve from 0.33997 72/72 [==============================] - 127s 2s/step - loss: 0.3156 - tversky: 0.7838 - val_loss: 0.3525 - val_tversky: 0.7488 - lr: 0.0010 Epoch 38/60 72/72 [==============================] - ETA: 0s - loss: 0.3091 - tversky: 0.7899 Epoch 38: val_loss improved from 0.33997 to 0.32281, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 129s 2s/step - loss: 0.3091 - tversky: 0.7899 - val_loss: 0.3228 - val_tversky: 0.7771 - lr: 0.0010 Epoch 39/60 72/72 [==============================] - ETA: 0s - loss: 0.2996 - tversky: 0.7978 Epoch 39: val_loss did not improve from 0.32281 72/72 [==============================] - 128s 2s/step - loss: 0.2996 - tversky: 0.7978 - val_loss: 0.3375 - val_tversky: 0.7633 - lr: 0.0010 Epoch 40/60 72/72 [==============================] - ETA: 0s - loss: 0.2943 - tversky: 0.8029 Epoch 40: val_loss did not improve from 0.32281 72/72 [==============================] - 125s 2s/step - loss: 0.2943 - tversky: 0.8029 - val_loss: 0.3303 - val_tversky: 0.7698 - lr: 0.0010 Epoch 41/60 72/72 [==============================] - ETA: 0s - loss: 0.2852 - tversky: 0.8112 Epoch 41: val_loss improved from 0.32281 to 0.30088, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 127s 2s/step - loss: 0.2852 - tversky: 0.8112 - val_loss: 0.3009 - val_tversky: 0.7981 - lr: 0.0010 Epoch 42/60 72/72 [==============================] - ETA: 0s - loss: 0.2811 - tversky: 0.8148 Epoch 42: val_loss did not improve from 0.30088 72/72 [==============================] - 126s 2s/step - loss: 0.2811 - tversky: 0.8148 - val_loss: 0.3035 - val_tversky: 0.7949 - lr: 0.0010 Epoch 43/60 72/72 [==============================] - ETA: 0s - loss: 0.2722 - tversky: 0.8227 Epoch 43: val_loss did not improve from 0.30088 72/72 [==============================] - 128s 2s/step - loss: 0.2722 - tversky: 0.8227 - val_loss: 0.3057 - val_tversky: 0.7939 - lr: 0.0010 Epoch 44/60 72/72 [==============================] - ETA: 0s - loss: 0.2717 - tversky: 0.8227 Epoch 44: val_loss improved from 0.30088 to 0.29223, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 121s 2s/step - loss: 0.2717 - tversky: 0.8227 - val_loss: 0.2922 - val_tversky: 0.8050 - lr: 0.0010 Epoch 45/60 72/72 [==============================] - ETA: 0s - loss: 0.2557 - tversky: 0.8370 Epoch 45: val_loss improved from 0.29223 to 0.28744, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 126s 2s/step - loss: 0.2557 - tversky: 0.8370 - val_loss: 0.2874 - val_tversky: 0.8097 - lr: 0.0010 Epoch 46/60 72/72 [==============================] - ETA: 0s - loss: 0.2557 - tversky: 0.8367 Epoch 46: val_loss did not improve from 0.28744 72/72 [==============================] - 130s 2s/step - loss: 0.2557 - tversky: 0.8367 - val_loss: 0.2888 - val_tversky: 0.8082 - lr: 0.0010 Epoch 47/60 72/72 [==============================] - ETA: 0s - loss: 0.2544 - tversky: 0.8383 Epoch 47: val_loss improved from 0.28744 to 0.27332, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 127s 2s/step - loss: 0.2544 - tversky: 0.8383 - val_loss: 0.2733 - val_tversky: 0.8214 - lr: 0.0010 Epoch 48/60 72/72 [==============================] - ETA: 0s - loss: 0.2467 - tversky: 0.8443 Epoch 48: val_loss did not improve from 0.27332 72/72 [==============================] - 128s 2s/step - loss: 0.2467 - tversky: 0.8443 - val_loss: 0.2810 - val_tversky: 0.8136 - lr: 0.0010 Epoch 49/60 72/72 [==============================] - ETA: 0s - loss: 0.2521 - tversky: 0.8395 Epoch 49: val_loss did not improve from 0.27332 72/72 [==============================] - 122s 2s/step - loss: 0.2521 - tversky: 0.8395 - val_loss: 0.2860 - val_tversky: 0.8108 - lr: 0.0010 Epoch 50/60 72/72 [==============================] - ETA: 0s - loss: 0.2421 - tversky: 0.8481 Epoch 50: val_loss improved from 0.27332 to 0.26800, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 118s 2s/step - loss: 0.2421 - tversky: 0.8481 - val_loss: 0.2680 - val_tversky: 0.8271 - lr: 0.0010 Epoch 51/60 72/72 [==============================] - ETA: 0s - loss: 0.2391 - tversky: 0.8510 Epoch 51: val_loss did not improve from 0.26800 72/72 [==============================] - 117s 2s/step - loss: 0.2391 - tversky: 0.8510 - val_loss: 0.2798 - val_tversky: 0.8158 - lr: 0.0010 Epoch 52/60 72/72 [==============================] - ETA: 0s - loss: 0.2370 - tversky: 0.8527 Epoch 52: val_loss improved from 0.26800 to 0.26463, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 123s 2s/step - loss: 0.2370 - tversky: 0.8527 - val_loss: 0.2646 - val_tversky: 0.8296 - lr: 0.0010 Epoch 53/60 72/72 [==============================] - ETA: 0s - loss: 0.2355 - tversky: 0.8537 Epoch 53: val_loss improved from 0.26463 to 0.24669, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 129s 2s/step - loss: 0.2355 - tversky: 0.8537 - val_loss: 0.2467 - val_tversky: 0.8449 - lr: 0.0010 Epoch 54/60 72/72 [==============================] - ETA: 0s - loss: 0.2283 - tversky: 0.8598 Epoch 54: val_loss did not improve from 0.24669 72/72 [==============================] - 142s 2s/step - loss: 0.2283 - tversky: 0.8598 - val_loss: 0.2695 - val_tversky: 0.8252 - lr: 0.0010 Epoch 55/60 72/72 [==============================] - ETA: 0s - loss: 0.2282 - tversky: 0.8597 Epoch 55: val_loss did not improve from 0.24669 72/72 [==============================] - 184s 3s/step - loss: 0.2282 - tversky: 0.8597 - val_loss: 0.2771 - val_tversky: 0.8187 - lr: 0.0010 Epoch 56/60 72/72 [==============================] - ETA: 0s - loss: 0.2211 - tversky: 0.8655 Epoch 56: val_loss did not improve from 0.24669 72/72 [==============================] - 183s 3s/step - loss: 0.2211 - tversky: 0.8655 - val_loss: 0.2653 - val_tversky: 0.8293 - lr: 0.0010 Epoch 57/60 72/72 [==============================] - ETA: 0s - loss: 0.2212 - tversky: 0.8655 Epoch 57: val_loss improved from 0.24669 to 0.24410, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 190s 3s/step - loss: 0.2212 - tversky: 0.8655 - val_loss: 0.2441 - val_tversky: 0.8466 - lr: 0.0010 Epoch 58/60 72/72 [==============================] - ETA: 0s - loss: 0.2186 - tversky: 0.8677 Epoch 58: val_loss did not improve from 0.24410 72/72 [==============================] - 176s 2s/step - loss: 0.2186 - tversky: 0.8677 - val_loss: 0.2607 - val_tversky: 0.8332 - lr: 0.0010 Epoch 59/60 72/72 [==============================] - ETA: 0s - loss: 0.2124 - tversky: 0.8725 Epoch 59: val_loss did not improve from 0.24410 72/72 [==============================] - 167s 2s/step - loss: 0.2124 - tversky: 0.8725 - val_loss: 0.2543 - val_tversky: 0.8386 - lr: 0.0010 Epoch 60/60 72/72 [==============================] - ETA: 0s - loss: 0.2145 - tversky: 0.8710 Epoch 60: val_loss improved from 0.24410 to 0.23691, saving model to ResUNet-segModel-weights.hdf5 72/72 [==============================] - 170s 2s/step - loss: 0.2145 - tversky: 0.8710 - val_loss: 0.2369 - val_tversky: 0.8520 - lr: 0.0010
# saving model achitecture in json file
seg_model_json = seg_model.to_json()
with open("ResUNet-seg-model.json", "w") as json_file:
json_file.write(seg_model_json)
h.history.keys()
dict_keys(['loss', 'tversky', 'val_loss', 'val_tversky', 'lr'])
plt.figure(figsize=(12,5))
plt.subplot(1,2,1)
plt.plot(h.history['loss']);
plt.plot(h.history['val_loss']);
plt.title("SEG Model focal tversky Loss");
plt.ylabel("focal tversky loss");
plt.xlabel("Epochs");
plt.legend(['train', 'val']);
plt.subplot(1,2,2)
plt.plot(h.history['tversky']);
plt.plot(h.history['val_tversky']);
plt.title("SEG Model tversky score");
plt.ylabel("tversky Accuracy");
plt.xlabel("Epochs");
plt.legend(['train', 'val']);
test_ids = list(X_test.image_path)
test_mask = list(X_test.mask_path)
test_data = DataGenerator(test_ids, test_mask)
_, tv = seg_model.evaluate(test_data)
print("Segmentation tversky is {:.2f}%".format(tv*100))
6/6 [==============================] - 3s 570ms/step - loss: 0.2409 - tversky: 0.8498 Segmentation tversky is 84.98%
def prediction(test, model, model_seg):
'''
Predcition function which takes dataframe containing ImageID as Input and perform 2 type of prediction on the image
Initially, image is passed through the classification network which predicts whether the image has defect or not, if the model
is 99% sure that the image has no defect, then the image is labeled as no-defect, if the model is not sure, it passes the image to the
segmentation network, it again checks if the image has defect or not, if it has defect, then the type and location of defect is found
'''
# empty list to store results
mask, image_id, has_mask = [], [], []
#itetrating through each image in test data
for i in test.image_path:
img = io.imread(i)
#normalizing
img = img *1./255.
#reshaping
img = cv2.resize(img, (256,256))
# converting img into array
img = np.array(img, dtype=np.float64)
#reshaping the image from 256,256,3 to 1,256,256,3
img = np.reshape(img, (1,256,256,3))
#making prediction for tumor in image
is_defect = model.predict(img)
#if tumour is not present we append the details of the image to the list
if np.argmax(is_defect)==0:
image_id.append(i)
has_mask.append(0)
mask.append('No mask :)')
continue
#Creating a empty array of shape 1,256,256,1
X = np.empty((1,256,256,3))
# read the image
img = io.imread(i)
#resizing the image and coverting them to array of type float64
img = cv2.resize(img, (256,256))
img = np.array(img, dtype=np.float64)
# standardising the image
img -= img.mean()
img /= img.std()
#converting the shape of image from 256,256,3 to 1,256,256,3
X[0,] = img
#make prediction of mask
predict = model_seg.predict(X)
# if sum of predicted mask is 0 then there is not tumour
if predict.round().astype(int).sum()==0:
image_id.append(i)
has_mask.append(0)
mask.append('No mask :)')
else:
#if the sum of pixel values are more than 0, then there is tumour
image_id.append(i)
has_mask.append(1)
mask.append(predict)
return pd.DataFrame({'image_path': image_id,'predicted_mask': mask,'has_mask': has_mask})
# making prediction
df_pred = prediction(test, model, seg_model)
df_pred
1/1 [==============================] - 1s 637ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 353ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 137ms/step 1/1 [==============================] - 0s 210ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 102ms/step 1/1 [==============================] - 0s 63ms/step 1/1 [==============================] - 0s 209ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 73ms/step 1/1 [==============================] - 0s 142ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 100ms/step 1/1 [==============================] - 0s 171ms/step 1/1 [==============================] - 0s 158ms/step 1/1 [==============================] - 0s 68ms/step 1/1 [==============================] - 0s 101ms/step 1/1 [==============================] - 0s 151ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 248ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 178ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 144ms/step 1/1 [==============================] - 0s 114ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 57ms/step 1/1 [==============================] - 0s 198ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 64ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 55ms/step 1/1 [==============================] - 0s 240ms/step 1/1 [==============================] - 0s 78ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 115ms/step 1/1 [==============================] - 0s 224ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 156ms/step 1/1 [==============================] - 0s 142ms/step 1/1 [==============================] - 0s 83ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 95ms/step 1/1 [==============================] - 0s 155ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 74ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 177ms/step 1/1 [==============================] - 0s 156ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 98ms/step 1/1 [==============================] - 0s 259ms/step 1/1 [==============================] - 0s 72ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 179ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 97ms/step 1/1 [==============================] - 0s 110ms/step 1/1 [==============================] - 0s 150ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 65ms/step 1/1 [==============================] - 0s 95ms/step 1/1 [==============================] - 0s 87ms/step 1/1 [==============================] - 0s 161ms/step 1/1 [==============================] - 0s 72ms/step 1/1 [==============================] - 0s 110ms/step 1/1 [==============================] - 0s 62ms/step 1/1 [==============================] - 0s 147ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 116ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 206ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 103ms/step 1/1 [==============================] - 0s 52ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 65ms/step 1/1 [==============================] - 0s 85ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 106ms/step 1/1 [==============================] - 0s 61ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 47ms/step 1/1 [==============================] - 0s 208ms/step 1/1 [==============================] - 0s 109ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 55ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 173ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 137ms/step 1/1 [==============================] - 0s 79ms/step 1/1 [==============================] - 0s 138ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 57ms/step 1/1 [==============================] - 0s 144ms/step 1/1 [==============================] - 0s 99ms/step 1/1 [==============================] - 0s 173ms/step 1/1 [==============================] - 0s 74ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 57ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 138ms/step 1/1 [==============================] - 0s 209ms/step 1/1 [==============================] - 0s 159ms/step 1/1 [==============================] - 0s 56ms/step 1/1 [==============================] - 0s 165ms/step 1/1 [==============================] - 0s 64ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 182ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 54ms/step 1/1 [==============================] - 0s 150ms/step 1/1 [==============================] - 0s 160ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 64ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 191ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 107ms/step 1/1 [==============================] - 0s 191ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 116ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 175ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 97ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 73ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 103ms/step 1/1 [==============================] - 0s 158ms/step 1/1 [==============================] - 0s 74ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 159ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 63ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 64ms/step 1/1 [==============================] - 0s 102ms/step 1/1 [==============================] - 0s 180ms/step 1/1 [==============================] - 0s 161ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 187ms/step 1/1 [==============================] - 0s 142ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 110ms/step 1/1 [==============================] - 0s 74ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 231ms/step 1/1 [==============================] - 0s 150ms/step 1/1 [==============================] - 0s 61ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 78ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 142ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 150ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 108ms/step 1/1 [==============================] - 0s 226ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 112ms/step 1/1 [==============================] - 0s 64ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 59ms/step 1/1 [==============================] - 0s 97ms/step 1/1 [==============================] - 0s 178ms/step 1/1 [==============================] - 0s 78ms/step 1/1 [==============================] - 0s 162ms/step 1/1 [==============================] - 0s 79ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 169ms/step 1/1 [==============================] - 0s 168ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 107ms/step 1/1 [==============================] - 0s 55ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 193ms/step 1/1 [==============================] - 0s 93ms/step 1/1 [==============================] - 0s 146ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 199ms/step 1/1 [==============================] - 0s 115ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 73ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 171ms/step 1/1 [==============================] - 0s 164ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 151ms/step 1/1 [==============================] - 0s 51ms/step 1/1 [==============================] - 0s 183ms/step 1/1 [==============================] - 0s 72ms/step 1/1 [==============================] - 0s 99ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 112ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 106ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 116ms/step 1/1 [==============================] - 0s 176ms/step 1/1 [==============================] - 0s 155ms/step 1/1 [==============================] - 0s 53ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 94ms/step 1/1 [==============================] - 0s 163ms/step 1/1 [==============================] - 0s 147ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 84ms/step 1/1 [==============================] - 0s 162ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 58ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 183ms/step 1/1 [==============================] - 0s 114ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 87ms/step 1/1 [==============================] - 0s 157ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 184ms/step 1/1 [==============================] - 0s 176ms/step 1/1 [==============================] - 0s 192ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 221ms/step 1/1 [==============================] - 0s 91ms/step 1/1 [==============================] - 0s 143ms/step 1/1 [==============================] - 0s 151ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 186ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 63ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 108ms/step 1/1 [==============================] - 0s 203ms/step 1/1 [==============================] - 0s 72ms/step 1/1 [==============================] - 0s 114ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 202ms/step 1/1 [==============================] - 0s 73ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 175ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 72ms/step 1/1 [==============================] - 0s 151ms/step 1/1 [==============================] - 0s 65ms/step 1/1 [==============================] - 0s 215ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 109ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 51ms/step 1/1 [==============================] - 0s 235ms/step 1/1 [==============================] - 0s 157ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 146ms/step 1/1 [==============================] - 0s 84ms/step 1/1 [==============================] - 0s 163ms/step 1/1 [==============================] - 0s 151ms/step 1/1 [==============================] - 0s 114ms/step 1/1 [==============================] - 0s 143ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 177ms/step 1/1 [==============================] - 0s 150ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 96ms/step 1/1 [==============================] - 0s 227ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 115ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 103ms/step 1/1 [==============================] - 0s 162ms/step 1/1 [==============================] - 0s 85ms/step 1/1 [==============================] - 0s 151ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 53ms/step 1/1 [==============================] - 0s 184ms/step 1/1 [==============================] - 0s 75ms/step 1/1 [==============================] - 0s 144ms/step 1/1 [==============================] - 0s 63ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 208ms/step 1/1 [==============================] - 0s 75ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 61ms/step 1/1 [==============================] - 0s 137ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 236ms/step 1/1 [==============================] - 0s 143ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 162ms/step 1/1 [==============================] - 0s 52ms/step 1/1 [==============================] - 0s 253ms/step 1/1 [==============================] - 0s 68ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 75ms/step 1/1 [==============================] - 0s 116ms/step 1/1 [==============================] - 0s 173ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 81ms/step 1/1 [==============================] - 0s 182ms/step 1/1 [==============================] - 0s 143ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 85ms/step 1/1 [==============================] - 0s 208ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 63ms/step 1/1 [==============================] - 0s 178ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 164ms/step 1/1 [==============================] - 0s 146ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 157ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 87ms/step 1/1 [==============================] - 0s 143ms/step 1/1 [==============================] - 0s 59ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 138ms/step 1/1 [==============================] - 0s 89ms/step 1/1 [==============================] - 0s 147ms/step 1/1 [==============================] - 0s 65ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 155ms/step 1/1 [==============================] - 0s 174ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 189ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 114ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 64ms/step 1/1 [==============================] - 0s 162ms/step 1/1 [==============================] - 0s 211ms/step 1/1 [==============================] - 0s 72ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 101ms/step 1/1 [==============================] - 0s 163ms/step 1/1 [==============================] - 0s 81ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 156ms/step 1/1 [==============================] - 0s 50ms/step 1/1 [==============================] - 0s 184ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 65ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 161ms/step 1/1 [==============================] - 0s 189ms/step 1/1 [==============================] - 0s 152ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 47ms/step 1/1 [==============================] - 0s 179ms/step 1/1 [==============================] - 0s 150ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 163ms/step 1/1 [==============================] - 0s 97ms/step 1/1 [==============================] - 0s 179ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 53ms/step 1/1 [==============================] - 0s 174ms/step 1/1 [==============================] - 0s 144ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 61ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 138ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 168ms/step 1/1 [==============================] - 0s 163ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 109ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 96ms/step 1/1 [==============================] - 0s 150ms/step 1/1 [==============================] - 0s 63ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 78ms/step 1/1 [==============================] - 0s 109ms/step 1/1 [==============================] - 0s 96ms/step 1/1 [==============================] - 0s 158ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 95ms/step 1/1 [==============================] - 0s 170ms/step 1/1 [==============================] - 0s 142ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 91ms/step 1/1 [==============================] - 0s 160ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 92ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 155ms/step 1/1 [==============================] - 0s 65ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 68ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 99ms/step 1/1 [==============================] - 0s 149ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 108ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 57ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 158ms/step 1/1 [==============================] - 0s 146ms/step 1/1 [==============================] - 0s 107ms/step 1/1 [==============================] - 0s 73ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 170ms/step 1/1 [==============================] - 0s 79ms/step 1/1 [==============================] - 0s 146ms/step 1/1 [==============================] - 0s 58ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 53ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 101ms/step 1/1 [==============================] - 0s 165ms/step 1/1 [==============================] - 0s 75ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 57ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 62ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 138ms/step 1/1 [==============================] - 0s 50ms/step 1/1 [==============================] - 0s 172ms/step 1/1 [==============================] - 0s 79ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 51ms/step 1/1 [==============================] - 0s 156ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 59ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 75ms/step 1/1 [==============================] - 0s 161ms/step 1/1 [==============================] - 0s 143ms/step 1/1 [==============================] - 0s 113ms/step 1/1 [==============================] - 0s 171ms/step 1/1 [==============================] - 0s 55ms/step 1/1 [==============================] - 0s 88ms/step 1/1 [==============================] - 0s 200ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 82ms/step 1/1 [==============================] - 0s 245ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 115ms/step 1/1 [==============================] - 0s 161ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 65ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 77ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 58ms/step 1/1 [==============================] - 0s 143ms/step 1/1 [==============================] - 0s 162ms/step 1/1 [==============================] - 0s 138ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 50ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 109ms/step 1/1 [==============================] - 0s 102ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 68ms/step 1/1 [==============================] - 0s 102ms/step 1/1 [==============================] - 0s 116ms/step 1/1 [==============================] - 0s 78ms/step 1/1 [==============================] - 0s 103ms/step 1/1 [==============================] - 0s 80ms/step 1/1 [==============================] - 0s 155ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 45ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 144ms/step 1/1 [==============================] - 0s 58ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 61ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 52ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 94ms/step 1/1 [==============================] - 0s 91ms/step 1/1 [==============================] - 0s 188ms/step 1/1 [==============================] - 0s 120ms/step 1/1 [==============================] - 0s 54ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 61ms/step 1/1 [==============================] - 0s 94ms/step 1/1 [==============================] - 0s 156ms/step 1/1 [==============================] - 0s 82ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 109ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 86ms/step 1/1 [==============================] - 0s 170ms/step 1/1 [==============================] - 0s 131ms/step 1/1 [==============================] - 0s 58ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 144ms/step 1/1 [==============================] - 0s 48ms/step 1/1 [==============================] - 0s 175ms/step 1/1 [==============================] - 0s 73ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 165ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 49ms/step 1/1 [==============================] - 0s 141ms/step 1/1 [==============================] - 0s 151ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 70ms/step 1/1 [==============================] - 0s 123ms/step 1/1 [==============================] - 0s 176ms/step 1/1 [==============================] - 0s 198ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 164ms/step 1/1 [==============================] - 0s 83ms/step 1/1 [==============================] - 0s 104ms/step 1/1 [==============================] - 0s 119ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 168ms/step 1/1 [==============================] - 0s 80ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 105ms/step 1/1 [==============================] - 0s 166ms/step 1/1 [==============================] - 0s 154ms/step 1/1 [==============================] - 0s 72ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 147ms/step 1/1 [==============================] - 0s 60ms/step 1/1 [==============================] - 0s 169ms/step 1/1 [==============================] - 0s 195ms/step 1/1 [==============================] - 0s 114ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 84ms/step 1/1 [==============================] - 0s 167ms/step 1/1 [==============================] - 0s 136ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 107ms/step 1/1 [==============================] - 0s 133ms/step 1/1 [==============================] - 0s 214ms/step 1/1 [==============================] - 0s 115ms/step 1/1 [==============================] - 0s 102ms/step 1/1 [==============================] - 0s 71ms/step 1/1 [==============================] - 0s 128ms/step 1/1 [==============================] - 0s 229ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 140ms/step 1/1 [==============================] - 0s 146ms/step 1/1 [==============================] - 0s 82ms/step 1/1 [==============================] - 0s 139ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 64ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 156ms/step 1/1 [==============================] - 0s 160ms/step 1/1 [==============================] - 0s 115ms/step 1/1 [==============================] - 0s 125ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 110ms/step 1/1 [==============================] - 0s 239ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 132ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 153ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 124ms/step 1/1 [==============================] - 0s 130ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 96ms/step 1/1 [==============================] - 0s 173ms/step 1/1 [==============================] - 0s 144ms/step 1/1 [==============================] - 0s 56ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 112ms/step 1/1 [==============================] - 0s 247ms/step 1/1 [==============================] - 0s 145ms/step 1/1 [==============================] - 0s 127ms/step 1/1 [==============================] - 0s 135ms/step 1/1 [==============================] - 0s 102ms/step 1/1 [==============================] - 0s 89ms/step 1/1 [==============================] - 0s 174ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 228ms/step 1/1 [==============================] - 0s 68ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 118ms/step 1/1 [==============================] - 0s 138ms/step 1/1 [==============================] - 0s 115ms/step 1/1 [==============================] - 0s 170ms/step 1/1 [==============================] - 0s 69ms/step 1/1 [==============================] - 0s 129ms/step 1/1 [==============================] - 0s 62ms/step 1/1 [==============================] - 0s 121ms/step 1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 88ms/step 1/1 [==============================] - 0s 93ms/step 1/1 [==============================] - 0s 209ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 126ms/step 1/1 [==============================] - 0s 67ms/step 1/1 [==============================] - 0s 112ms/step 1/1 [==============================] - 0s 89ms/step 1/1 [==============================] - 0s 156ms/step 1/1 [==============================] - 0s 61ms/step 1/1 [==============================] - 0s 137ms/step 1/1 [==============================] - 0s 59ms/step 1/1 [==============================] - 0s 109ms/step 1/1 [==============================] - 0s 169ms/step 1/1 [==============================] - 0s 76ms/step 1/1 [==============================] - 0s 148ms/step 1/1 [==============================] - 0s 117ms/step 1/1 [==============================] - 0s 62ms/step 1/1 [==============================] - 0s 134ms/step 1/1 [==============================] - 0s 116ms/step 1/1 [==============================] - 0s 174ms/step 1/1 [==============================] - 0s 152ms/step 1/1 [==============================] - 0s 111ms/step 1/1 [==============================] - 0s 116ms/step 1/1 [==============================] - 0s 112ms/step 1/1 [==============================] - 0s 199ms/step 1/1 [==============================] - 0s 75ms/step 1/1 [==============================] - 0s 122ms/step 1/1 [==============================] - 0s 60ms/step
| image_path | predicted_mask | has_mask | |
|---|---|---|---|
| 0 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | No mask :) | 0 |
| 1 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | [[[[0.00024032], [9.582487e-05], [0.00015765],... | 1 |
| 2 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | No mask :) | 0 |
| 3 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | [[[[0.00018928], [7.79208e-05], [0.00012878], ... | 1 |
| 4 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | No mask :) | 0 |
| ... | ... | ... | ... |
| 585 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | No mask :) | 0 |
| 586 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | No mask :) | 0 |
| 587 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | No mask :) | 0 |
| 588 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | [[[[0.00018134], [7.214157e-05], [0.00012422],... | 1 |
| 589 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | [[[[0.00019356], [7.524462e-05], [0.00012682],... | 1 |
590 rows × 3 columns
# merging original and prediction df
df_pred = test.merge(df_pred, on='image_path')
df_pred.head(10)
| image_path | mask_path | mask | predicted_mask | has_mask | |
|---|---|---|---|---|---|
| 0 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 | No mask :) | 0 |
| 1 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 1 | [[[[0.00024032], [9.582487e-05], [0.00015765],... | 1 |
| 2 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 | No mask :) | 0 |
| 3 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 1 | [[[[0.00018928], [7.79208e-05], [0.00012878], ... | 1 |
| 4 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 | No mask :) | 0 |
| 5 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 | No mask :) | 0 |
| 6 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 1 | [[[[0.00015732], [7.119028e-05], [0.00012219],... | 1 |
| 7 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 1 | [[[[0.0001833], [7.1754126e-05], [0.00011429],... | 1 |
| 8 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 | [[[[0.00032904], [0.00014852], [0.00015443], [... | 1 |
| 9 | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | brain_dataset/lgg-mri-segmentation/kaggle_3m/T... | 0 | No mask :) | 0 |
#visualizing prediction
count = 0
fig, axs = plt.subplots(15,5, figsize=(30,70))
for i in range(len(df_pred)):
if df_pred.has_mask[i]==1 and count<15:
#read mri images
img = io.imread(df_pred.image_path[i])
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
axs[count][0].imshow(img)
axs[count][0].title.set_text('Brain MRI')
#read original mask
mask = io.imread(df_pred.mask_path[i])
axs[count][1].imshow(mask)
axs[count][1].title.set_text('Original Mask')
#read predicted mask
pred = np.array(df_pred.predicted_mask[i]).squeeze().round()
axs[count][2].imshow(pred)
axs[count][2].title.set_text('AI predicted mask')
#overlay original mask with MRI
img[mask==255] = (255,0,0)
axs[count][3].imshow(img)
axs[count][3].title.set_text('Brain MRI with original mask (Ground Truth)')
#overlay predicted mask and MRI
img_ = io.imread(df_pred.image_path[i])
img_ = cv2.cvtColor(img_, cv2.COLOR_BGR2RGB)
img_[pred==1] = (0,255,150)
axs[count][4].imshow(img_)
axs[count][4].title.set_text('MRI with AI PREDICTED MASK')
count +=1
if (count==15):
break
fig.tight_layout()
the predictions made by AI are almost correct :)