def lstm_init_states(batch_size):
""" Returns a tuple of names and zero arrays for LSTM init states"""
hp = Hyperparams()
init_shapes = lstm.init_states(batch_size=batch_size, num_lstm_layer=hp.num_lstm_layer, num_hidden=hp.num_hidden)
init_names = [s[0] for s in init_shapes]
init_arrays = [mx.nd.zeros(x[1]) for x in init_shapes]
return init_names, init_arrays
def lstm_init_states(batch_size):
""" Returns a tuple of names and zero arrays for LSTM init states"""
hp = Hyperparams()
init_shapes = lstm.init_states(batch_size=batch_size, num_lstm_layer=hp.num_lstm_layer, num_hidden=hp.num_hidden)
init_names = [s[0] for s in init_shapes]
init_arrays = [mx.nd.zeros(x[1]) for x in init_shapes]
return init_names, init_arrays
def lstm_init_states(batch_size):
hp = Hyperparams()
init_shapes = lstm.init_states(batch_size=batch_size, num_lstm_layer=hp.num_lstm_layer, num_hidden=hp.num_hidden)
init_names = [s[0] for s in init_shapes]
init_arrays = [mx.nd.zeros(x[1]) for x in init_shapes]
return init_names, init_arrays
def main():
"""Program entry point"""
args = parse_args()
if not any(args.loss == s for s in ['ctc', 'warpctc']):
raise ValueError(
"Invalid loss '{}' (must be 'ctc' or 'warpctc')".format(args.loss))
hp = Hyperparams()
# Start a multiprocessor captcha image generator
mp_captcha = MPDigitCaptcha(font_paths=get_fonts(args.font_path),
h=hp.seq_length,
w=30,
num_digit_min=3,
num_digit_max=4,
num_processes=args.num_proc,
max_queue_size=hp.batch_size * 2)
try:
# Must call start() before any call to mxnet module (https://github.com/apache/incubator-mxnet/issues/9213)
mp_captcha.start()
if args.gpu:
contexts = [mx.context.gpu(i) for i in range(args.gpu)]
else:
contexts = [mx.context.cpu(i) for i in range(args.cpu)]
init_states = lstm.init_states(hp.batch_size, hp.num_lstm_layer,
hp.num_hidden)
data_train = OCRIter(hp.train_epoch_size // hp.batch_size,
hp.batch_size,
init_states,
captcha=mp_captcha,
name='train')
data_val = OCRIter(hp.eval_epoch_size // hp.batch_size,
hp.batch_size,
init_states,
captcha=mp_captcha,
name='val')
symbol = lstm.lstm_unroll(num_lstm_layer=hp.num_lstm_layer,
seq_len=hp.seq_length,
num_hidden=hp.num_hidden,
num_label=hp.num_label,
loss_type=args.loss)
head = '%(asctime)-15s %(message)s'
logging.basicConfig(level=logging.DEBUG, format=head)
module = mx.mod.Module(symbol,
data_names=[
'data', 'l0_init_c', 'l0_init_h',
'l1_init_c', 'l1_init_h'
],
label_names=['label'],
context=contexts)
metrics = CtcMetrics(hp.seq_length)
module.fit(
train_data=data_train,
eval_data=data_val,
# use metrics.accuracy or metrics.accuracy_lcs
eval_metric=mx.gluon.metric.np(metrics.accuracy,
allow_extra_outputs=True),
optimizer='sgd',
optimizer_params={
'learning_rate': hp.learning_rate,
'momentum': hp.momentum,
'wd': 0.00001,
},
initializer=mx.init.Xavier(factor_type="in", magnitude=2.34),
num_epoch=hp.num_epoch,
batch_end_callback=mx.callback.Speedometer(hp.batch_size, 50),
epoch_end_callback=mx.callback.do_checkpoint(args.prefix),
)
except KeyboardInterrupt:
print("W: interrupt received, stopping...")
finally:
# Reset multiprocessing captcha generator to stop processes
mp_captcha.reset()
def main():
args = parse_args()
if not any(args.loss == s for s in ['ctc', 'warpctc']):
raise ValueError("Invalid loss '{}' (must be 'ctc' or 'warpctc')".format(args.loss))
hp = Hyperparams()
# Start a multiprocessor captcha image generator
mp_captcha = MPDigitCaptcha(
font_paths=get_fonts(args.font_path), h=hp.seq_length, w=30,
num_digit_min=3, num_digit_max=4, num_processes=args.num_proc, max_queue_size=hp.batch_size * 2)
try:
# Must call start() before any call to mxnet module (https://github.com/apache/incubator-mxnet/issues/9213)
mp_captcha.start()
if args.gpu:
contexts = [mx.context.gpu(i) for i in range(args.gpu)]
else:
contexts = [mx.context.cpu(i) for i in range(args.cpu)]
init_states = lstm.init_states(hp.batch_size, hp.num_lstm_layer, hp.num_hidden)
data_train = OCRIter(
hp.train_epoch_size // hp.batch_size, hp.batch_size, init_states, captcha=mp_captcha, name='train')
data_val = OCRIter(
hp.eval_epoch_size // hp.batch_size, hp.batch_size, init_states, captcha=mp_captcha, name='val')
symbol = lstm.lstm_unroll(
num_lstm_layer=hp.num_lstm_layer,
seq_len=hp.seq_length,
num_hidden=hp.num_hidden,
num_label=hp.num_label,
loss_type=args.loss)
head = '%(asctime)-15s %(message)s'
logging.basicConfig(level=logging.DEBUG, format=head)
module = mx.mod.Module(
symbol,
data_names=['data', 'l0_init_c', 'l0_init_h', 'l1_init_c', 'l1_init_h'],
label_names=['label'],
context=contexts)
metrics = CtcMetrics(hp.seq_length)
module.fit(train_data=data_train,
eval_data=data_val,
# use metrics.accuracy or metrics.accuracy_lcs
eval_metric=mx.metric.np(metrics.accuracy, allow_extra_outputs=True),
optimizer='sgd',
optimizer_params={'learning_rate': hp.learning_rate,
'momentum': hp.momentum,
'wd': 0.00001,
},
initializer=mx.init.Xavier(factor_type="in", magnitude=2.34),
num_epoch=hp.num_epoch,
batch_end_callback=mx.callback.Speedometer(hp.batch_size, 50),
epoch_end_callback=mx.callback.do_checkpoint(args.prefix),
)
except KeyboardInterrupt:
print("W: interrupt received, stopping...")
finally:
# Reset multiprocessing captcha generator to stop processes
mp_captcha.reset()
def main():
args = parse_args()
if not any(args.loss == s for s in ['ctc', 'warpctc']):
raise ValueError("Invalid loss {}".format(args.loss))
mp_captcha = MPDigitCaptcha(
font_paths=get_fonts(args.font_path), h=hp.seq_length, w=30,
num_digit_min=3, num_digit_max=4, num_processes=args.num_proc, max_queue_size=hp.batch_size*2)
try:
mp_captcha.strat()
if args.gpu:
contexts = [mx.context.gpu(i) for i in range(args.gpu)]
else:
contexts = [mx.context.cpu(i) for i in range(args.cpu)]
init_states = lstm.init_states(hp.batch_size, hp.num_lstm_layer, hp.num_hidden)
data_train = OCRIter(
hp.train_epoch_size // hp.batch_size, hp.batch_size, init_states, captcha=mp_captcha, name='train')
data_eval = OCRIter(
hp.eval_epoch_size // hp.batch_size, hp.batch_size, init_states, captcha=mp_captcha, name='eval')
symbol = lstm.unroll(
num_lstm_layer=hp.num_lstm_layer,
seq_len=seq_length,
num_hidden=hp.num_hidden,
num_label=hp.num_label,
loss_type=args.loss)
head = '%(asctime)-15s %(message)s'
logging.basicConfig(level=logging.DEBUG, format=head)
module = mx.mod.Module(
symbol,
data_names=['data', 'l0_init_c', 'l0_init_h', 'l1_init_c', 'l1_init_h'],
label_names=['label'],
context=contexts)
metrics = CtcMetrics(hp.seq_length)
module.fit(train_data=data_train,
eval_data=data_eval,
eval_metric=mx.metric.np(metrics.accuracy, allow_extra_outputs=True),
optimizer='sgd'
optimizer_params={
'learning_rate':hp.learning_rate,
'momentum':hp.momentum,
'wd':0.0001,
},
initializer=mx.init.Xavier(factor_type='in', magnitude=2.34),
num_epoch=hp.num_epoch,
batch_end_callback=mx.callback.Speedometer(hp.batch_size, 50),
epoch_end_callback=mx.callback.do_checkpoint(args.prefix),
)
except KeyboardInterrupt:
print("W: interrupt received, stopping...")
finally:
mp_captcha.reset()