encoder, decoder = get_models(model_path)
word_map, rev_word_map = get_word_map(run_local=args.run_local)
transform = transforms.Compose([
transforms.Resize((336, 336)),
transforms.ToTensor(), data_normalization
])
desktop_path = os.path.join(os.path.join(os.path.expanduser('~')),
'Desktop')
lm_model = load_lm_model()
corpus = Corpus('../../../language_model/word_language_model/data_dir')
# image_name = 'Fork.png'
############
dataloader = load('custom', args.run_local, 1, 1)
for i, data in tqdm(enumerate(dataloader)):
image = data[0].to(device)
if image.shape[1] != 3:
continue
run(encoder, decoder, word_map, rev_word_map, save_dir, image,
data[1][0])
#########
#
# for image_name in os.listdir(os.path.join(desktop_path, 'custom_images')):
# image_path = 'custom_images/{}'.format(image_name)
# img = Image.open(os.path.join(desktop_path, image_path))
#
# try:
# image = transform(img).unsqueeze(0)
image = image.unsqueeze(0) # (1, 3, 256, 256)
# subsec: move to device
image = image.to(device)
# subsec: run beam search
seq_, top_seq_total_scors_, seq_sum_, words = caption_image_beam_search(encoder, decoder, image, word_map,
rev_word_map, args, representations)
if not None == words:
hp_metric_dic['annotations'].append({u'image_id': None, u'caption': words})
if not None == seq_sum_:
generated_sentences_likelihood.append((None, seq_sum_))
if args.data == 'cartoon':
dataloader = load('cartoon', args.run_local, 1, 1)
for bi, data in tqdm(enumerate(dataloader)):
image = data[0].to(device)
if image.shape[1] != 3:
continue
# subsec: move to device
image = image.to(device)
# subsec: run top_k/p
# subsec: run beam search
seq_, top_seq_total_scors_, seq_sum_, words = caption_image_beam_search(encoder, decoder, image, word_map,
rev_word_map, args, representations)
if not None == words:
hp_metric_dic['annotations'].append({u'image_id': bi, u'caption': words})
if not None == seq_sum_:
generated_sentences_likelihood.append((bi, seq_sum_))
seq, alphas, top_seq_total_scors, seq_sum, logits_list = beam_search_decode(encoder, image, args.beam_size,
word_map, decoder)
alphas = torch.FloatTensor(alphas)
visualize_att(image, seq, alphas, rev_word_map, top_seq_total_scors, save_dir, image_id, args.smooth)
f = open(os.path.join(save_dir, 'seq_sum.txt'), 'a+')
f.write('seq_sum: {} for image id: {} with caption: {}\n'.format(seq_sum, image_id, image_title))
print('seq_sum: {}'.format(seq_sum))
if __name__ == '__main__':
save_dir_name = '{}_{}'.format(args.beam_size, args.save_dir_name)
model_path, save_dir = get_model_path_and_save_path(args, save_dir_name)
# Load model
encoder, decoder = get_models(model_path)
# Create rev word map
word_map, rev_word_map = get_word_map()
dataloader = load('flicker', args.run_local, 1, 1)
for ind, image_data in enumerate(dataloader):
image = image_data[0].unsqueeze(0)
image_title = image_data[1]
image_title = min(image_title, key=len)
image_id = dataloader.ids[ind]
run(encoder, decoder, word_map, rev_word_map, save_dir, image, image_title, image_id)
alphas = torch.FloatTensor(alphas)
visualize_att(image, seq, alphas, rev_word_map, top_seq_total_scors, save_dir, image_title, args.smooth)
f = open(os.path.join(save_dir, 'seq_sum.txt'), 'a+')
f.write('seq_sum: {} for image id: {} with caption: {}\n'.format(seq_sum, image_id, image_title))
print('seq_sum: {}'.format(seq_sum))
if __name__ == '__main__':
save_dir_name = '{}_{}'.format(args.beam_size, args.save_dir_name)
model_path, save_dir = get_model_path_and_save_path(args, save_dir_name)
# Load model
encoder, decoder = get_models(model_path)
# Create rev word map
word_map, rev_word_map = get_word_map()
dataloader = load('sbu', args.run_local, 1, 1)
for ind, image_data in enumerate(dataloader):
image = image_data[0]
translator = str.maketrans('', '', string.punctuation)
image_title = image_data[1][0].translate(translator)
image_id = dataloader.dataset.photos[ind]
# image_title = image_data[1][0].strip(string.punctuation)
run(encoder, decoder, word_map, rev_word_map, save_dir, image, image_title, image_id)
decoder,
image,
word_map,
top_k, top_p)
alphas = torch.FloatTensor(alphas)
visualize_att(image, seq, alphas, rev_word_map, top_seq_total_scors, save_dir, image_title, args.smooth)
if __name__ == '__main__':
top_k = 5 # NOTICE: inr
top_p = 0 # NOTICE: double
model_path, save_dir = get_model_path_and_save_path(args, 'top_k_{}'.format(top_k)
if top_k > 0 else 'top_p_{}'.format(top_p))
# Load model
encoder, decoder = get_models(model_path)
# Create rev word map
word_map, rev_word_map = get_word_map()
dataloader = load('custom', True, 1, 1)
for ind, image_data in enumerate(dataloader):
image = image_data[0]
image_title = image_data[1][0]
run(encoder, decoder, word_map, rev_word_map, save_dir, top_k, top_p, image, image_title)
