################################ Train
print('Training the Network')
for epoch in range(num_epochs):
ntwk.update_learning_rate(epoch)
edit_dist, tot_len = 0, 0
print('Epoch: {} '.format(epoch))
# keeping 1 backup file as data might get lost, if script is stopped while pickling
os.rename(network_fname, 'ntwk.bkp.pkl')
with open(network_fname, 'wb') as fh:
pickle.dump(ntwk, fh)
print('Network saved to {}'.format(network_fname))
for samp in range(num_samples):
x, _, y = scriber.get_text_image()
y_blanked = utils.insert_blanks(y, alphabet_size, num_blanks_at_start=2)
# if len(y_blanked) < 2:
# print(y_blanked, end=' ')
# continue
cst, pred, forward_probs = ntwk.trainer(x, y_blanked)
if np.isinf(cst):
printer.show_all(y, x, pred,
(forward_probs > 1e-20, 'Forward probabilities:', y_blanked))
print('Exiting on account of Inf Cost...')
break
if samp == 0 and epoch==num_epochs-1: # or len(y) == 0:
pred, hidden = ntwk.tester(x)
'nchars_per_sample': 30,
'height': 45
}
alphabet_size = len(telugu.symbols)
scriber = Scribe(language=telugu, **options)
if len(sys.argv) > 1:
target_dir = sys.argv[1]
samples = int(sys.argv[2])
else:
samples = 1000
target_dir = '../data/train/3/'
print(samples, target_dir)
try:
os.makedirs(target_dir)
except FileExistsError:
pass
for i in range(samples):
image, text, labels = scriber.get_text_image()
image = bin_arr_to_img(image)
base_name = '{}/{:04d}'.format(target_dir, i)
image.save(base_name + '.png')
with open(base_name + '.gt.txt', 'w') as fh:
fh.write(''.join(text))
'nchars_per_sample': 1,
'height': 45
}
alphabet_size = len(telugu.symbols)
scriber = Scribe(language=telugu, **options)
if len(sys.argv) > 1:
target_dir = sys.argv[1]
samples = int(sys.argv[2])
else:
samples = 100
target_dir = 'data'
print(samples, target_dir)
try:
os.makedirs(target_dir)
except FileExistsError:
pass
for i in range(samples):
image, text, labels = scriber.get_text_image()
image = bin_arr_to_img(image)
base_name = '{}/{:04d}'.format(target_dir, i)
image.save(base_name + '.png')
with open(base_name + '.gt.txt', 'w') as fh:
fh.write(''.join(text))
ntwk = nn.NeuralNet(scriber.height, alphabet_size, **nnet_args)
# Print
print('\nArguments:')
utils.write_dict(args)
print('FloatX: {}'.format(th.config.floatX))
print('Alphabet Size: {}'.format(alphabet_size))
################################ Train
print('Training the Network')
for epoch in range(num_epochs):
ntwk.update_learning_rate(epoch)
edit_dist, tot_len = 0, 0
for samp in range(num_samples):
x, _, y = scriber.get_text_image()
y_blanked = utils.insert_blanks(y, alphabet_size, num_blanks_at_start=2)
# if len(y_blanked) < 2:
# print(y_blanked, end=' ')
# continue
cst, pred, forward_probs = ntwk.trainer(x, y_blanked)
if np.isinf(cst):
printer.show_all(y, x, pred,
(forward_probs > 1e-20, 'Forward probabilities:', y_blanked))
print('Exiting on account of Inf Cost...')
break
if samp == 0 and epoch==num_epochs-1: # or len(y) == 0:
pred, hidden = ntwk.tester(x)