model.py

model_input = Input(shape=(X_train.shape[1], X_train.shape[2], X_train.shape[3]), name='inputs')

conv1 = conv2d(16, name='convoluton_1')(model_input)
act1 = ReLU(name='activation_1')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2), name='pooling_1')(act1)

conv2 = conv2d(16, name='convolution_2')(pool1)
act2 = ReLU(name='activation_2')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2), name='pooling_2')(act2)

conv3 = conv2d(32, name='convolution_3')(pool2)
act3 = ReLU(name='activation_3')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2), name='pooling_3')(act3)

conv4 = conv2d(32, name='convolution_4')(pool3)
act4 = ReLU(name='activation_4')(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2), name='pooling_4')(act4)

conv5 = conv2d(64, name='convolition_5')(pool4)
act5 = ReLU(name='activation_5')(conv5)
pool5 = MaxPooling2D(pool_size=(2, 2), name='pooling_5')(act5)

conv6 = conv2d(64, name='convolution_6')(pool5)
act6 = ReLU(name='activation_6')(conv6)
pool6 = MaxPooling2D(pool_size=(2, 2), name='pooling_6')(act6)

flat = Flatten(name='flatten')(pool6)
dense1 = Dense(32, name='dense1')(flat)
output = Dense(1, activation='sigmoid', name='output')(dense1)

model = Model(inputs=[model_input], outputs=[output])
model.summary()