def _sanitize_value(shape, value, dtype, device, is_param=False):
np_dtype = utils.sanitize_dtype_numpy(dtype)
cntk_dtype = utils.sanitize_dtype_cntk(dtype)
if value is None:
if shape is None:
raise ValueError('you need to specify at least shape or value')
shape = utils.sanitize_shape(shape)
if is_param:
# TODO: expose the initialization params
ndav = NDArrayView.random_uniform_float(shape, -0.05, 0.05, 1, device)
else:
ndav = utils.create_NDArrayView(shape, cntk_dtype, device)
else:
if not isinstance(value, np.ndarray) or value.dtype!=np_dtype:
value = np.asarray(value, dtype=np_dtype)
#TODO: check whether this copy operation from cpu to gpu is not needed
if device.type() != 0:
ndav_cpu = utils.create_NDArrayView_from_NumPy(value, dev=DeviceDescriptor.cpu_device())
ndav = utils.create_NDArrayView(value.shape, data_type=cntk_dtype, dev=device)
ndav.copy_from(ndav_cpu)
else:
ndav = utils.create_NDArrayView_from_NumPy(value, device)
return ndav
trainer = Trainer(classifier_output, ce, pe,
[sgd_learner(classifier_output.owner.parameters(), lr)])
# Get minibatches of sequences to train with and perform model training
minibatch_size = 200
training_progress_output_freq = 10
i = 0
while True:
mb = mb_source.get_next_minibatch(minibatch_size)
if len(mb) == 0:
break
# Specify the mapping of input variables in the model to actual minibatch data to be trained with
arguments = {
features: mb[features_si].m_data,
label: mb[labels_si].m_data
}
trainer.train_minibatch(arguments)
print_training_progress(trainer, i, training_progress_output_freq)
i += 1
if __name__ == '__main__':
# Specify the target device to be used for computing
target_device = DeviceDescriptor.cpu_device()
DeviceDescriptor.set_default_device(target_device)
train_sequence_classifier()
lr = learning_rates_per_sample(0.007)
momentum_time_constant = 1100
momentum_per_sample = momentums_per_sample(math.exp(-1.0 / momentum_time_constant))
clipping_threshold_per_sample = 2.3
gradient_clipping_with_truncation = True
trainer = Trainer(z, ce, errs, [momentum_sgd_learner(z.owner.parameters(), lr, momentum_per_sample, clipping_threshold_per_sample, gradient_clipping_with_truncation)])
# Get minibatches of sequences to train with and perform model training
minibatch_size = 72
training_progress_output_freq = 10
while True:
mb = mb_source.get_next_minibatch(minibatch_size)
if len(mb) == 0:
break
# Specify the mapping of input variables in the model to actual minibatch data to be trained with
arguments = {raw_input : mb[features_si].m_data, raw_labels : mb[labels_si].m_data}
trainer.train_minibatch(arguments)
print_training_progress(trainer, i, training_progress_output_freq)
i += 1
if __name__=='__main__':
# Specify the target device to be used for computing
target_device = DeviceDescriptor.cpu_device()
DeviceDescriptor.set_default_device(target_device)
train_sequence_to_sequence_translator()
