elif option == 3:
image_input = tf.keras.Input(shape=x_train.shape[1:], name='image_input')
x = MobileNet(weights='imagenet', include_top=False)(image_input)
x = tf.keras.layers.Flatten(name='flatten')(x)
x = tf.keras.layers.Dense(4096, activation='relu', name='fc1')(x)
x = tf.keras.layers.Dense(4096, activation='relu', name='fc2')(x)
x = tf.keras.layers.Dense(num_classes, activation='softmax', name='predictions')(x)
model = tf.keras.Model(inputs=image_input, outputs=x)
model.summary()
# Select loss, optimizer, metric
model.compile(loss='categorical_crossentropy',
optimizer=tf.train.AdamOptimizer(0.001),
metrics=['accuracy'])
# Train
start = timer()
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
# callbacks=[TensorBoardColabCallback(tbc)]
# Evaluate
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
timer()-start
#evaluation_datagen = ImageDataGenerator(rescale=1. / 255)
evaluation_datagen = ImageDataGenerator(
preprocessing_function=preprocess_input)
evaluation_generator = evaluation_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
class_mode='categorical',
shuffle=False)
print('dataset ready')
t = time.time()
print('evaluating...')
test_result = model.evaluate(evaluation_generator, verbose=1)
t = time.time() - t
print('evaluate done')
print('\nruntime: %f s' % t)
print('\nTest loss:', test_result[0])
print('Test top1 accuracy:', test_result[1])
print('Test top5 accuracy:', test_result[2])
#%%
prediction = model.predict(evaluation_generator, verbose=1)
prediction = np.argmax(prediction, axis=1)
show_confusion_matrix(evaluation_generator.classes,
prediction,
