def main():
seed = 42
np.random.seed(seed)
current_dir = os.path.dirname(__file__)
sys.path.append(os.path.join(current_dir, '..'))
current_dir = current_dir if current_dir is not '' else '.'
img_dir_path = 'jpg'
txt_dir_path = 'flowers/text_c10'
model_dir_path = current_dir + '/models'
img_width = 32
img_height = 32
from dcgan import DCGan
from image_utils import img_from_normalized_img
from img_cap_loader import load_normalized_img_and_its_text
image_label_pairs = load_normalized_img_and_its_text(img_dir_path,
txt_dir_path,
img_width=img_width,
img_height=img_height)
shuffle(image_label_pairs)
gan = DCGan()
gan.load_model(model_dir_path)
for i in range(10):
image_label_pair = image_label_pairs[i]
normalized_image = image_label_pair[0]
text = image_label_pair[1]
print(text)
image = img_from_normalized_img(normalized_image)
image.save(current_dir + '/data/outputs/' + DCGan.model_name +
'-generated-' + str(i) + '-0.png')
for j in range(3):
generated_image = gan.generate_image_from_text(text)
generated_image.save(current_dir + '/data/outputs/' +
DCGan.model_name + '-generated-' + str(i) +
'-' + str(j) + '.png')
if mode == 'train':
#training
start_time = time.time()
logs = gan.fit(model_dir_path=model_dir_path,
image_label_pairs=image_label_pairs,
snapshot_dir_path=current_dir + snapshots_dir_path,
snapshot_interval=10,
batch_size=batch_size,
epochs=epochs)
from training_plot import on_epoch_end
on_epoch_end(logs)
end_time = time.time()
print(end_time - start_time)
elif mode == 'test':
#testing
from dcgan import DCGan
gan = DCGan()
gan.load_model(model_dir_path)
text = 'person holding black guitar'
generated_image = gan.generate_image_from_text(text)
generated_image.save(current_dir + output_dir_path + DCGan.model_name +
'-generated-' + str(0) + '-' + str(0) + '.png')
else:
print('Wrong mode string')