def bn_inception_train_and_eval(train_data, test_data, mean_data, num_quantization_bits=32, epoch_size=1281167, max_epochs=300, minibatch_size=None,
restore=True, log_to_file=None, num_mbs_per_log=100, gen_heartbeat=False, scale_up=False, profiling=False):
_cntk_py.set_computation_network_trace_level(0)
# NOTE: scaling up minibatch_size increases sample throughput. In 8-GPU machine,
# ResNet110 samples-per-second is ~7x of single GPU, comparing to ~3x without scaling
# up. However, bigger minibatch size on the same number of samples means less updates,
# thus leads to higher training error. This is a trade-off of speed and accuracy
if minibatch_size is None:
mb_size = 32 * (Communicator.num_workers() if scale_up else 1)
else:
mb_size = minibatch_size
progress_printer = ProgressPrinter(
freq=num_mbs_per_log,
tag='Training',
log_to_file=log_to_file,
rank=Communicator.rank(),
gen_heartbeat=gen_heartbeat,
num_epochs=max_epochs)
network = create_bn_inception()
trainer = create_trainer(network, epoch_size, max_epochs, mb_size, num_quantization_bits, progress_printer)
train_source = create_image_mb_source(train_data, mean_data, True, total_number_of_samples=max_epochs * epoch_size)
test_source = create_image_mb_source(test_data, mean_data, False, total_number_of_samples=FULL_DATA_SWEEP)
train_and_test(network, trainer, train_source, test_source, mb_size, epoch_size, restore, profiling)
def bn_inception_train_and_eval(train_data, test_data, mean_data, num_quantization_bits=32, epoch_size=50000, max_epochs=200, minibatch_size=None,
restore=True, log_to_file=None, num_mbs_per_log=100, gen_heartbeat=False, scale_up=False, profiling=False):
_cntk_py.set_computation_network_trace_level(0)
# NOTE: scaling up minibatch_size increases sample throughput. In 8-GPU machine,
# ResNet110 samples-per-second is ~7x of single GPU, comparing to ~3x without scaling
# up. However, bigger minibatch size on the same number of samples means less updates,
# thus leads to higher training error. This is a trade-off of speed and accuracy
if minibatch_size is None:
mb_size = 128 * (Communicator.num_workers() if scale_up else 1)
else:
mb_size = minibatch_size
progress_printer = ProgressPrinter(
freq=num_mbs_per_log,
tag='Training',
log_to_file=log_to_file,
rank=Communicator.rank(),
gen_heartbeat=gen_heartbeat,
num_epochs=max_epochs)
network = create_bn_inception()
trainer = create_trainer(network, epoch_size, max_epochs, mb_size, num_quantization_bits, progress_printer)
train_source = create_image_mb_source(train_data, mean_data, True, total_number_of_samples=max_epochs * epoch_size)
test_source = create_image_mb_source(test_data, mean_data, False, total_number_of_samples=FULL_DATA_SWEEP)
train_and_test(network, trainer, train_source, test_source, max_epochs, mb_size, epoch_size, restore, profiling)
def sequence_to_sequence_translator(train_data, test_data, epoch_size=908241, num_quantization_bits=default_quantization_bits, block_size=3200, warm_up=0, minibatch_size=72, max_epochs=10, randomize_data=False, log_to_file=None, num_mbs_per_log=10, gen_heartbeat=False):
cntk.debugging.set_computation_network_trace_level(0)
from _cntk_py import set_fixed_random_seed
set_fixed_random_seed(1)
from Sequence2Sequence import create_model
distributed_sync_report_freq = None
if block_size is not None:
distributed_sync_report_freq = 1
progress_printer = ProgressPrinter(freq=num_mbs_per_log,
tag='Training',
log_to_file=log_to_file,
rank=Communicator.rank(),
gen_heartbeat=gen_heartbeat,
num_epochs=max_epochs,
distributed_freq=distributed_sync_report_freq)
# create inputs and create model
model = create_model()
train_reader = create_reader(train_data, randomize_data, size=max_epochs*epoch_size)
test_reader = create_reader(test_data, False, size=max_epochs*epoch_size*10)
train_and_test(model, train_reader, test_reader, block_size, num_quantization_bits, max_epochs, epoch_size, minibatch_size, progress_printer, warm_up)
def sequence_to_sequence_translator(
train_data,
test_data,
epoch_size=908241,
num_quantization_bits=default_quantization_bits,
block_size=3200,
warm_up=0,
minibatch_size=72,
max_epochs=10,
randomize_data=False,
log_to_file=None,
num_mbs_per_log=10,
gen_heartbeat=False):
cntk.debugging.set_computation_network_trace_level(0)
from _cntk_py import set_fixed_random_seed
set_fixed_random_seed(1)
from Sequence2Sequence import create_model
distributed_sync_report_freq = None
if block_size is not None:
distributed_sync_report_freq = 1
progress_printer = ProgressPrinter(
freq=num_mbs_per_log,
tag='Training',
log_to_file=log_to_file,
rank=Communicator.rank(),
gen_heartbeat=gen_heartbeat,
num_epochs=max_epochs,
distributed_freq=distributed_sync_report_freq)
# create inputs and create model
model = create_model()
train_reader = create_reader(train_data,
randomize_data,
size=max_epochs * epoch_size)
test_reader = create_reader(test_data,
False,
size=max_epochs * epoch_size * 10)
train_and_test(model, train_reader, test_reader, block_size,
num_quantization_bits, max_epochs, epoch_size,
minibatch_size, progress_printer, warm_up)
def vgg19_train_and_eval(train_data,
test_data,
num_quantization_bits=32,
minibatch_size=128,
epoch_size=1281167,
max_epochs=80,
restore=True,
log_to_file=None,
num_mbs_per_log=None,
gen_heartbeat=False,
testing=False):
_cntk_py.set_computation_network_trace_level(0)
progress_printer = ProgressPrinter(freq=num_mbs_per_log,
tag='Training',
log_to_file=log_to_file,
rank=Communicator.rank(),
gen_heartbeat=gen_heartbeat,
num_epochs=max_epochs)
network = create_vgg19()
trainer = create_trainer(network, epoch_size, num_quantization_bits,
progress_printer)
train_source = create_image_mb_source(train_data,
True,
total_number_of_samples=max_epochs *
epoch_size)
if testing:
# reduce number of samples for validation when testing
num_of_validation_samples = max_epochs * epoch_size * 10
else:
num_of_validation_samples = FULL_DATA_SWEEP
test_source = create_image_mb_source(
test_data, False, total_number_of_samples=num_of_validation_samples)
train_and_test(network, trainer, train_source, test_source, minibatch_size,
epoch_size, restore)
def vgg19_train_and_eval(train_data, test_data, num_quantization_bits=32, minibatch_size=128, epoch_size = 1281167, max_epochs=80,
restore=True, log_to_file=None, num_mbs_per_log=None, gen_heartbeat=False, testing=False):
_cntk_py.set_computation_network_trace_level(0)
progress_printer = ProgressPrinter(
freq=num_mbs_per_log,
tag='Training',
log_to_file=log_to_file,
rank=Communicator.rank(),
gen_heartbeat=gen_heartbeat,
num_epochs=max_epochs)
network = create_vgg19()
trainer = create_trainer(network, epoch_size, num_quantization_bits, progress_printer)
train_source = create_image_mb_source(train_data, True, total_number_of_samples=max_epochs * epoch_size)
if testing:
# reduce number of samples for validation when testing
num_of_validation_samples = max_epochs * epoch_size * 10
else:
num_of_validation_samples = FULL_DATA_SWEEP
test_source = create_image_mb_source(test_data, False, total_number_of_samples=num_of_validation_samples)
train_and_test(network, trainer, train_source, test_source, minibatch_size, epoch_size, restore)