def __init__(self, folder_image, folder_label):
self.folder_image = folder_image
self.folder_label = folder_label
self.batch_size = BATCH_SIZE
self.max_txt_length = max_txt_length
self.examples = []
self.cur_index = 0
self.load_data()
self.image_util = ImageUtil(image_height=image_height, image_width=image_width)
self.vocab = Vocabulary()
def main():
sess = tf.Session()
image_util = ImageUtil()
dataloader = ImageDataLoader(IMAGES_DIR, image_util)
train_dataset = dataloader.get_dataset('train', NUM_TRAIN_IMAGES)
val_dataset = dataloader.get_dataset('val', NUM_VAL_IMAGES)
test_dataset = dataloader.get_dataset('test', NUM_TEST_IMAGES)
model = ImageColorization().model
model.compile(optimizer=tf.train.AdamOptimizer(),
loss={'colorization_output': 'mean_squared_error', 'classification_output': 'categorical_crossentropy'},
loss_weights={'colorization_output': 1., 'classification_output': 1./300})
print 'Starting training'
for i in range(NUM_EPOCHS):
model.fit(train_dataset['greyscale'], {'colorization_output': train_dataset['color'], 'classification_output': train_dataset['class']}, epochs=1)
ab_unscaled = model.predict(val_dataset['greyscale'])[0]
lab = np.concatenate([val_dataset['greyscale']*100, ab_unscaled*200-100], axis=3)
show_predicted_values(ab_unscaled, lab)
print 'Finished training'
results = model.predict(test_dataset['greyscale'])
cv2.imshow('origin', img)
def visual_attention(result, attention_plot):
len_result = len(result)
for i in range(len_result):
show_origin_image()
temp_att = np.reshape(attention_plot[i], (height, width))
cv2.imshow(f'predict word: {result[i]}', temp_att)
cv2.waitKey()
cv2.destroyAllWindows()
if __name__ == '__main__':
image_util = ImageUtil(image_height=image_height, image_width=image_width)
img_tensor = image_util.load(args.image)
img_tensor = np.expand_dims(img_tensor, 0)
result = ''
hidden = tf.zeros((1, decode_units))
word_one_hot = np.zeros((1, vocab_size))
word_one_hot[0][1] = 1.
attention_plot = np.zeros((max_txt_length, height * width))
for i in range(max_txt_length):
predict, hidden, attention_weights = model(word_one_hot, hidden,
img_tensor)
predict_id = tf.argmax(predict, axis=-1)
