def train_cnocr(args):
head = '%(asctime)-15s %(message)s'
logging.basicConfig(level=logging.DEBUG, format=head)
args.model_name = args.emb_model_type + '-' + args.seq_model_type
out_dir = os.path.join(args.out_model_dir, args.model_name)
logger.info('save models to dir: %s' % out_dir)
if not os.path.exists(out_dir):
os.makedirs(out_dir)
args.prefix = os.path.join(
out_dir, 'cnocr-v{}-{}'.format(__version__, args.model_name))
hp = CnHyperparams()
hp = _update_hp(hp, args)
network, hp = gen_network(args.model_name, hp)
metrics = CtcMetrics(hp.seq_length)
data_train, data_val = _gen_iters(hp, args.train_file, args.test_file,
args.use_train_image_aug, args.dataset,
args.charset, args.debug)
data_names = ['data']
fit(
network=network,
data_train=data_train,
data_val=data_val,
metrics=metrics,
args=args,
hp=hp,
data_names=data_names,
)
def run_captcha(args):
hp = Hyperparams2()
network = crnn_lstm(hp)
# arg_shape, out_shape, aux_shape = network.infer_shape(data=(128, 1, 32, 100), label=(128, 10),
# l0_init_h=(128, 100), l1_init_h=(128, 100), l2_init_h=(128, 100), l3_init_h=(128, 100))
# print(dict(zip(network.list_arguments(), arg_shape)))
# import pdb; pdb.set_trace()
# Start a multiprocessor captcha image generator
mp_captcha = MPDigitCaptcha(font_paths=get_fonts(args.font_path),
h=hp.img_width,
w=hp.img_height,
num_digit_min=3,
num_digit_max=4,
num_processes=args.num_proc,
max_queue_size=hp.batch_size * 2)
mp_captcha.start()
# img, num = mp_captcha.get()
# print(img.shape)
# import numpy as np
# import cv2
# img = np.transpose(img, (1, 0))
# cv2.imwrite('captcha1.png', img * 255)
# import pdb; pdb.set_trace()
init_c = [('l%d_init_c' % l, (hp.batch_size, hp.num_hidden))
for l in range(hp.num_lstm_layer * 2)]
init_h = [('l%d_init_h' % l, (hp.batch_size, hp.num_hidden))
for l in range(hp.num_lstm_layer * 2)]
init_states = init_c + init_h
data_names = ['data'] + [x[0] for x in init_states]
data_train = OCRIter(hp.train_epoch_size // hp.batch_size,
hp.batch_size,
init_states,
captcha=mp_captcha,
num_label=hp.num_label,
name='train')
data_val = OCRIter(hp.eval_epoch_size // hp.batch_size,
hp.batch_size,
init_states,
captcha=mp_captcha,
num_label=hp.num_label,
name='val')
head = '%(asctime)-15s %(message)s'
logging.basicConfig(level=logging.DEBUG, format=head)
metrics = CtcMetrics(hp.seq_length)
fit(network=network,
data_train=data_train,
data_val=data_val,
metrics=metrics,
args=args,
hp=hp,
data_names=data_names)
mp_captcha.reset()
def run_cn_ocr(args):
hp = Hyperparams()
network = crnn_lstm(hp)
mp_data_train = MPOcrImages(args.data_root, args.train_file, (hp.img_width, hp.img_height), hp.num_label,
num_processes=args.num_proc, max_queue_size=hp.batch_size * 100)
# img, num = mp_data_train.get()
# print(img.shape)
# print(mp_data_train.shape)
# import pdb; pdb.set_trace()
# import numpy as np
# import cv2
# img = np.transpose(img, (1, 0))
# cv2.imwrite('captcha1.png', img * 255)
# import pdb; pdb.set_trace()
mp_data_test = MPOcrImages(args.data_root, args.test_file, (hp.img_width, hp.img_height), hp.num_label,
num_processes=max(args.num_proc // 2, 1), max_queue_size=hp.batch_size * 10)
mp_data_train.start()
mp_data_test.start()
# init_c = [('l%d_init_c' % l, (hp.batch_size, hp.num_hidden)) for l in range(hp.num_lstm_layer * 2)]
# init_h = [('l%d_init_h' % l, (hp.batch_size, hp.num_hidden)) for l in range(hp.num_lstm_layer * 2)]
# init_states = init_c + init_h
# data_names = ['data'] + [x[0] for x in init_states]
data_names = ['data']
data_train = OCRIter(
hp.train_epoch_size // hp.batch_size, hp.batch_size, captcha=mp_data_train, num_label=hp.num_label,
name='train')
data_val = OCRIter(
hp.eval_epoch_size // hp.batch_size, hp.batch_size, captcha=mp_data_test, num_label=hp.num_label,
name='val')
# data_train = ImageIterLstm(
# args.data_root, args.train_file, hp.batch_size, (hp.img_width, hp.img_height), hp.num_label, init_states, name="train")
# data_val = ImageIterLstm(
# args.data_root, args.test_file, hp.batch_size, (hp.img_width, hp.img_height), hp.num_label, init_states, name="val")
head = '%(asctime)-15s %(message)s'
logging.basicConfig(level=logging.DEBUG, format=head)
metrics = CtcMetrics(hp.seq_length)
fit(network=network, data_train=data_train, data_val=data_val, metrics=metrics, args=args, hp=hp, data_names=data_names)
mp_data_train.reset()
mp_data_test.reset()
