Resnet50.py

import tensorflow as tf
from tensorflow.keras.applications.resnet50 import preprocess_input
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.preprocessing import image
import pathlib
import matplotlib.pyplot as plt
import tensorflow_addons as tfa
from tensorflow.keras.applications import ResNet50
from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.layers import Dense, Flatten, GlobalAveragePooling2D, Dropout
from tensorflow.keras import metrics

IMG_WIDTH=224
IMG_HEIGHT=224
IMG_DIM = (IMG_WIDTH, IMG_HEIGHT)
BATCH_SIZE = 3
IMG_DIR = pathlib.Path('/content/thesis_data')
TRAIN_DIR = '/content/thesis_data/train_set'
VAL_DIR = '/content/thesis_data/test_set'

# Specify the values for all arguments to data_generator_with_aug.
data_generator_with_aug = ImageDataGenerator(rescale = 1./255, rotation_range=15,shear_range=0.15,zoom_range=0.05,horizontal_flip=True,vertical_flip=True)
            
data_generator_no_aug = ImageDataGenerator(rescale = 1./255,horizontal_flip=True,vertical_flip=True)

train_generator = data_generator_with_aug.flow_from_directory(
                                        directory=TRAIN_DIR,
                                        target_size=IMG_DIM,
                                        batch_size=32,
                                        class_mode='categorical')

validation_generator = data_generator_no_aug.flow_from_directory(
                                        directory=VAL_DIR,
                                        target_size=IMG_DIM,batch_size=32,
                                        class_mode='categorical')
num_classes = 6

resnet = ResNet50(include_top=False, weights='imagenet', input_shape=(IMG_HEIGHT,IMG_WIDTH,3),pooling='max')

resnet.summary()

output = resnet.layers[-1].output
output = tf.keras.layers.Flatten()(output)
resnet = Model(resnet.input, output)
model = Sequential()
model.add(resnet)
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics=['accuracy',metrics.mean_squared_error])

model.fit(train_generator,
          steps_per_epoch=590//32,
          epochs = 20,
          validation_steps=117//32,
          validation_data = validation_generator)



accuracy = model.history.history['accuracy']
val_accuracy = model.history.history['val_accuracy']
loss = model.history.history['loss']
val_loss = model.history.history['val_loss']
mse = model.history.history['mean_squared_error']
val_mse = model.history.history['mean_squared_error']
epochs = range(len(accuracy))

plt.plot(epochs,accuracy,'bo',label='Training accuracy')
plt.plot(epochs,val_accuracy,'b',label='Validation accuracy')
plt.title('Training and validation accuracy')
plt.legend()
plt.show()
plt.figure()


plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()
plt.show()
plt.figure()

plt.plot(epochs, mse, 'bo', label='Training Mean Squared Error')
plt.plot(epochs, val_mse, 'b', label='Validation Mean Squared Errror')
plt.legend()
plt.show()
save_path = '/content/thesis_data/resnet_output/'
tf.keras.models.save_model(model,save_path)

visualizatio.py

img_path = '/content/sample_data/Capture14.JPG'
from keras.preprocessing import image
import numpy as np
from keras.models import load_model
img = image.load_img(img_path, target_size=(150, 150))
img_tensor = image.img_to_array(img)
img_tensor = np.expand_dims(img_tensor, axis=0)
img_tensor /= 255.
print(img_tensor.shape)

import matplotlib.pyplot as plt
plt.imshow(img_tensor[0])
plt.show()

model = load_model("/content/thesis_data/resnet_output")
from keras import models

layer_outputs = [layer.output for layer in model.layers[:4]]
activation_model = models.Model(inputs=model.input, outputs=layer_outputs)
#activation_model = models.Model(inputs=classifier.input, outputs=layer_outputs)
activations = activation_model.predict(img_tensor)

first_layer_activation = activations[0]
print(first_layer_activation.shape)