def test_load_save_constant(tmpdir):
c = constant(value=[1, 3])
root_node = c * 5
result = root_node.eval()
expected = [[[[5, 15]]]]
assert np.allclose(result, expected)
filename = str(tmpdir / 'c_plus_c.mod')
save_model(root_node, filename)
loaded_node = load_model(filename)
loaded_result = loaded_node.eval()
assert np.allclose(loaded_result, expected)
def test_load_save_unique_input(tmpdir):
i1 = input_variable((1, 2), name='i1')
root_node = softmax(i1)
input1 = [[[1, 2]]]
result = root_node.eval(input1)
expected = [[[[0.268941, 0.731059]]]]
assert np.allclose(result, expected)
filename = str(tmpdir / 'i_plus_0.mod')
save_model(root_node, filename)
loaded_node = load_model(filename)
# Test specifying the only value for an unique input
loaded_result = loaded_node.eval(input1)
assert np.allclose(loaded_result, expected)
def test_load_save_input(tmpdir):
i1 = input_variable((1, 2), name='i1')
root_node = abs(i1)
input1 = [[[-1, 2]]]
result = root_node.eval({i1: input1})
expected = [[[[1, 2]]]]
assert np.allclose(result, expected)
filename = str(tmpdir / 'i_plus_c_0.mod')
save_model(root_node, filename)
loaded_node = load_model(filename)
# Test spefying the input node names by order
loaded_result = loaded_node.eval([input1])
assert np.allclose(loaded_result, expected)
def test_load_save_inputs(tmpdir):
i1 = input_variable((1, 2), name='i1')
i2 = input_variable((2, 1), name='i2')
root_node = plus(i1, i2)
input1 = [[[1, 2]]]
input2 = [[[[1], [2]]]]
result = root_node.eval({i1: input1, i2: input2})
expected = [[[[2, 3], [3, 4]]]]
assert np.allclose(result, expected)
filename = str(tmpdir / 'i_plus_i_0.mod')
save_model(root_node, filename)
loaded_node = load_model(filename)
# Test specifying the input nodes by name
loaded_result = loaded_node.eval({'i1': input1, 'i2': input2})
assert np.allclose(loaded_result, expected)
def cifar_resnet_distributed(data_path,
run_test,
num_epochs,
communicator=None,
save_model_filename=None,
load_model_filename=None,
debug_output=False):
image_height = 32
image_width = 32
num_channels = 3
num_classes = 10
feats_stream_name = 'features'
labels_stream_name = 'labels'
minibatch_source = create_reader(os.path.join(data_path, 'train_map.txt'),
os.path.join(data_path,
'CIFAR-10_mean.xml'),
True,
distributed_communicator=communicator)
features_si = minibatch_source[feats_stream_name]
labels_si = minibatch_source[labels_stream_name]
# Instantiate the resnet classification model, or load from file
if load_model_filename:
print("Loading model:", load_model_filename)
classifier_output = persist.load_model(load_model_filename)
image_input = classifier_output.arguments[0]
else:
image_input = input_variable((num_channels, image_height, image_width),
features_si.m_element_type)
classifier_output = create_resnet_model(image_input, num_classes)
# Input variables denoting the features and label data
label_var = input_variable((num_classes), features_si.m_element_type)
ce = cross_entropy_with_softmax(classifier_output, label_var)
pe = classification_error(classifier_output, label_var)
# Instantiate the trainer object to drive the model training
mb_size = 128
num_mb_per_epoch = 100
num_mbs = num_mb_per_epoch * num_epochs
lr_schedule = [1.0 / mb_size] * 80 + [0.1 / mb_size] * 40 + [
0.01 / mb_size
]
lr_per_minibatch = learning_rate_schedule(lr_schedule, UnitType.minibatch,
mb_size * num_mb_per_epoch)
momentum_time_constant = momentum_as_time_constant_schedule(-mb_size /
np.log(0.9))
# create data parallel distributed trainer if needed
dist_trainer = distributed.data_parallel_distributed_trainer(
communicator, False) if communicator else None
# Instantiate the trainer object to drive the model training
trainer = Trainer(classifier_output,
ce,
pe, [
momentum_sgd(classifier_output.parameters,
lr=lr_per_minibatch,
momentum=momentum_time_constant,
l2_regularization_weight=0.0001)
],
distributed_trainer=dist_trainer)
# Get minibatches of images to train with and perform model training
training_progress_output_freq = 100 if communicator else 20
if debug_output:
training_progress_output_freq = training_progress_output_freq / 4
for i in range(0, num_mbs):
# NOTE: depends on network, the mb_size can be changed dynamically here
mb = minibatch_source.next_minibatch(mb_size)
# Specify the mapping of input variables in the model to actual
# minibatch data to be trained with
arguments = {image_input: mb[features_si], label_var: mb[labels_si]}
trainer.train_minibatch(arguments)
print_training_progress(trainer, i, training_progress_output_freq)
if save_model_filename:
print("Saving model:", save_model_filename)
persist.save_model(classifier_output, save_model_filename)
if run_test:
test_minibatch_source = create_reader(
os.path.join(data_path, 'test_map.txt'),
os.path.join(data_path, 'CIFAR-10_mean.xml'), False)
features_si = test_minibatch_source[feats_stream_name]
labels_si = test_minibatch_source[labels_stream_name]
mb_size = 128
num_mbs = 100
total_error = 0.0
for i in range(0, num_mbs):
mb = test_minibatch_source.next_minibatch(mb_size)
# Specify the mapping of input variables in the model to actual
# minibatch data to be trained with
arguments = {
image_input: mb[features_si],
label_var: mb[labels_si]
}
error = trainer.test_minibatch(arguments)
total_error += error
return total_error / num_mbs
else:
return 0
def convnet_cifar10_dataaug(reader_train,
reader_test,
distributed_trainer,
max_epochs=80):
set_computation_network_trace_level(0)
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width))
label_var = input_variable((num_classes))
# apply model to input
scaled_input = element_times(constant(0.00390625), input_var)
with default_options(activation=relu, pad=True):
z = Sequential([
LayerStack(
2, lambda: [
Convolution((3, 3), 64),
Convolution((3, 3), 64),
MaxPooling((3, 3), (2, 2))
]),
LayerStack(2, lambda i: [Dense([256, 128][i]),
Dropout(0.5)]),
Dense(num_classes, activation=None)
])(scaled_input)
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
# training config
epoch_size = 50000 # for now we manually specify epoch size
minibatch_size = 64
# Set learning parameters
lr_per_sample = [0.0015625] * 20 + [0.00046875] * 20 + [
0.00015625
] * 20 + [0.000046875] * 10 + [0.000015625]
lr_schedule = learning_rate_schedule(lr_per_sample,
unit=UnitType.sample,
epoch_size=epoch_size)
momentum_time_constant = [0] * 20 + [600] * 20 + [1200]
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant,
epoch_size=epoch_size)
l2_reg_weight = 0.002
# trainer object
learner = momentum_sgd(z.parameters,
lr_schedule,
mm_schedule,
l2_regularization_weight=l2_reg_weight)
trainer = Trainer(z, ce, pe, learner, distributed_trainer)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z)
print()
progress_printer = ProgressPrinter(tag='Training')
# perform model training
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(
min(minibatch_size, epoch_size - sample_count),
input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += trainer.previous_minibatch_sample_count # count samples processed so far
progress_printer.update_with_trainer(
trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
if distributed_trainer.communicator().current_worker(
).global_rank == 0:
persist.save_model(
z,
os.path.join(model_path,
"ConvNet_CIFAR10_DataAug_{}.dnn".format(epoch)))
### Evaluation action
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch,
input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += trainer.previous_minibatch_sample_count
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(
minibatch_index + 1, (metric_numer * 100.0) / metric_denom,
metric_denom))
print("")
return metric_numer / metric_denom
def convnet_cifar10(debug_output=False):
set_computation_network_trace_level(0)
image_height = 32
image_width = 32
num_channels = 3
input_dim = image_height * image_width * num_channels
num_output_classes = 10
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width),
np.float32)
label_var = input_variable(num_output_classes, np.float32)
# Instantiate the feedforward classification model
input_removemean = minus(input_var, constant(128))
scaled_input = element_times(constant(0.00390625), input_removemean)
with default_options(activation=relu, pad=True):
z = Sequential([
LayerStack(
2, lambda: [
Convolution((3, 3), 64),
Convolution((3, 3), 64),
MaxPooling((3, 3), (2, 2))
]),
LayerStack(2, lambda i: [Dense([256, 128][i]),
Dropout(0.5)]),
Dense(num_output_classes, activation=None)
])(scaled_input)
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
reader_train = create_reader(
os.path.join(data_path, 'Train_cntk_text.txt'), True, input_dim,
num_output_classes)
# training config
epoch_size = 50000 # for now we manually specify epoch size
minibatch_size = 64
# Set learning parameters
lr_per_sample = [0.0015625] * 10 + [0.00046875] * 10 + [0.00015625]
lr_schedule = learning_rate_schedule(lr_per_sample,
epoch_size=epoch_size,
unit=UnitType.sample)
momentum_time_constant = [0] * 20 + [-minibatch_size / np.log(0.9)]
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant,
epoch_size=epoch_size)
l2_reg_weight = 0.002
# Instantiate the trainer object to drive the model training
learner = momentum_sgd(z.parameters,
lr_schedule,
mm_schedule,
l2_regularization_weight=l2_reg_weight)
trainer = Trainer(z, ce, pe, learner)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z)
print()
progress_printer = ProgressPrinter(tag='Training')
# Get minibatches of images to train with and perform model training
max_epochs = 30
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(
min(minibatch_size, epoch_size - sample_count),
input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += trainer.previous_minibatch_sample_count # count samples processed so far
progress_printer.update_with_trainer(
trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
persist.save_model(
z, os.path.join(model_path,
"ConvNet_CIFAR10_{}.dnn".format(epoch)))
# Load test data
reader_test = create_reader(os.path.join(data_path, 'Test_cntk_text.txt'),
False, input_dim, num_output_classes)
input_map = {
input_var: reader_test.streams.features,
label_var: reader_test.streams.labels
}
# Test data for trained model
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch,
input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(
minibatch_index + 1, (metric_numer * 100.0) / metric_denom,
metric_denom))
print("")
return metric_numer / metric_denom
def convnet_mnist(debug_output=False):
image_height = 28
image_width = 28
num_channels = 1
input_dim = image_height * image_width * num_channels
num_output_classes = 10
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width),
np.float32)
label_var = input_variable(num_output_classes, np.float32)
# Instantiate the feedforward classification model
scaled_input = element_times(constant(0.00390625), input_var)
with default_options(activation=relu, pad=False):
conv1 = Convolution((5, 5), 32, pad=True)(scaled_input)
pool1 = MaxPooling((3, 3), (2, 2))(conv1)
conv2 = Convolution((3, 3), 48)(pool1)
pool2 = MaxPooling((3, 3), (2, 2))(conv2)
conv3 = Convolution((3, 3), 64)(pool2)
f4 = Dense(96)(conv3)
drop4 = Dropout(0.5)(f4)
z = Dense(num_output_classes, activation=None)(drop4)
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
reader_train = create_reader(
os.path.join(data_path, 'Train-28x28_cntk_text.txt'), True, input_dim,
num_output_classes)
# training config
epoch_size = 60000 # for now we manually specify epoch size
minibatch_size = 128
# Set learning parameters
lr_per_sample = [0.001] * 10 + [0.0005] * 10 + [0.0001]
lr_schedule = learning_rate_schedule(lr_per_sample, UnitType.sample,
epoch_size)
momentum_time_constant = [0] * 5 + [1024]
mn_schedule = momentum_schedule(momentum_time_constant, epoch_size)
# Instantiate the trainer object to drive the model training
learner = momentum_sgd(z.parameters, lr_schedule, mn_schedule)
trainer = Trainer(z, ce, pe, learner)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z)
print()
progress_printer = ProgressPrinter(tag='Training')
# Get minibatches of images to train with and perform model training
max_epochs = 40
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(
min(minibatch_size, epoch_size - sample_count),
input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += data[
label_var].num_samples # count samples processed so far
progress_printer.update_with_trainer(
trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
persist.save_model(
z, os.path.join(model_path, "ConvNet_MNIST_{}.dnn".format(epoch)))
# Load test data
reader_test = create_reader(
os.path.join(data_path, 'Test-28x28_cntk_text.txt'), False, input_dim,
num_output_classes)
input_map = {
input_var: reader_test.streams.features,
label_var: reader_test.streams.labels
}
# Test data for trained model
epoch_size = 10000
minibatch_size = 1024
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch,
input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += trainer.previous_minibatch_sample_count
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(
minibatch_index + 1, (metric_numer * 100.0) / metric_denom,
metric_denom))
print("")
return metric_numer / metric_denom
def train_and_evaluate(reader_train, reader_test, network_name, max_epochs):
set_computation_network_trace_level(0)
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width))
label_var = input_variable((num_classes))
# create model, and configure learning parameters
if network_name == 'resnet20':
z = create_cifar10_model(input_var, 3, num_classes)
lr_per_mb = [1.0] * 80 + [0.1] * 40 + [0.01]
elif network_name == 'resnet110':
z = create_cifar10_model(input_var, 18, num_classes)
lr_per_mb = [0.1] * 1 + [1.0] * 80 + [0.1] * 40 + [0.01]
else:
return RuntimeError("Unknown model name!")
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
# shared training parameters
epoch_size = 50000 # for now we manually specify epoch size
minibatch_size = 128
momentum_time_constant = -minibatch_size / np.log(0.9)
l2_reg_weight = 0.0001
# Set learning parameters
lr_per_sample = [lr / minibatch_size for lr in lr_per_mb]
lr_schedule = learning_rate_schedule(lr_per_sample,
epoch_size=epoch_size,
unit=UnitType.sample)
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)
# trainer object
learner = momentum_sgd(z.parameters,
lr_schedule,
mm_schedule,
l2_regularization_weight=l2_reg_weight)
trainer = Trainer(z, ce, pe, learner)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z)
print()
progress_printer = ProgressPrinter(tag='Training')
# perform model training
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(
min(minibatch_size, epoch_size - sample_count),
input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += trainer.previous_minibatch_sample_count # count samples processed so far
progress_printer.update_with_trainer(
trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
persist.save_model(
z, os.path.join(model_path,
network_name + "_{}.dnn".format(epoch)))
# Evaluation parameters
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch,
input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(
minibatch_index + 1, (metric_numer * 100.0) / metric_denom,
metric_denom))
print("")
return metric_numer / metric_denom
def convnet_cifar10_dataaug(reader_train, reader_test, max_epochs = 80):
set_computation_network_trace_level(0)
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width))
label_var = input_variable((num_classes))
# apply model to input
scaled_input = element_times(constant(0.00390625), input_var)
with default_options (activation=relu, pad=True):
z = Sequential([
LayerStack(2, lambda : [
Convolution((3,3), 64),
Convolution((3,3), 64),
MaxPooling((3,3), (2,2))
]),
LayerStack(2, lambda i: [
Dense([256,128][i]),
Dropout(0.5)
]),
Dense(num_classes, activation=None)
])(scaled_input)
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
# training config
epoch_size = 50000 # for now we manually specify epoch size
minibatch_size = 64
# Set learning parameters
lr_per_sample = [0.0015625]*20+[0.00046875]*20+[0.00015625]*20+[0.000046875]*10+[0.000015625]
lr_schedule = learning_rate_schedule(lr_per_sample, unit=UnitType.sample, epoch_size=epoch_size)
mm_time_constant = [0]*20+[600]*20+[1200]
mm_schedule = momentum_as_time_constant_schedule(mm_time_constant, epoch_size=epoch_size)
l2_reg_weight = 0.002
# trainer object
learner = momentum_sgd(z.parameters, lr_schedule, mm_schedule,
l2_regularization_weight = l2_reg_weight)
trainer = Trainer(z, ce, pe, learner)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z) ; print()
progress_printer = ProgressPrinter(tag='Training')
# perform model training
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(min(minibatch_size, epoch_size-sample_count), input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += trainer.previous_minibatch_sample_count # count samples processed so far
progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
persist.save_model(z, os.path.join(model_path, "ConvNet_CIFAR10_DataAug_{}.dnn".format(epoch)))
### Evaluation action
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch, input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
print("")
return metric_numer/metric_denom
def cifar_resnet_distributed(data_path, run_test, num_epochs, communicator=None, save_model_filename=None, load_model_filename=None, debug_output=False):
image_height = 32
image_width = 32
num_channels = 3
num_classes = 10
feats_stream_name = 'features'
labels_stream_name = 'labels'
minibatch_source = create_reader(os.path.join(data_path, 'train_map.txt'), os.path.join(data_path, 'CIFAR-10_mean.xml'), True,
distributed_communicator = communicator)
features_si = minibatch_source[feats_stream_name]
labels_si = minibatch_source[labels_stream_name]
# Instantiate the resnet classification model, or load from file
if load_model_filename:
print("Loading model:", load_model_filename)
classifier_output = persist.load_model(load_model_filename)
image_input = classifier_output.arguments[0]
else:
image_input = input_variable(
(num_channels, image_height, image_width), features_si.m_element_type)
classifier_output = create_resnet_model(image_input, num_classes)
# Input variables denoting the features and label data
label_var = input_variable((num_classes), features_si.m_element_type)
ce = cross_entropy_with_softmax(classifier_output, label_var)
pe = classification_error(classifier_output, label_var)
# Instantiate the trainer object to drive the model training
mb_size = 128
num_mb_per_epoch = 100
num_mbs = num_mb_per_epoch * num_epochs
lr_per_sample = [1/mb_size]*80+[0.1/mb_size]*40+[0.01/mb_size]
lr_schedule = learning_rate_schedule(lr_per_sample, units = mb_size * num_mb_per_epoch)
momentum_time_constant = -mb_size/np.log(0.9)
# create data parallel distributed trainer if needed
dist_trainer = distributed.data_parallel_distributed_trainer(communicator, False) if communicator else None
# Instantiate the trainer object to drive the model training
trainer = Trainer(classifier_output, ce, pe,
[momentum_sgd(classifier_output.parameters, lr_schedule, momentum_time_constant, l2_regularization_weight=0.0001)],
distributed_trainer = dist_trainer)
# Get minibatches of images to train with and perform model training
training_progress_output_freq = 100 if communicator else 20
if debug_output:
training_progress_output_freq = training_progress_output_freq/4
for i in range(0, num_mbs):
# NOTE: depends on network, the mb_size can be changed dynamically here
mb = minibatch_source.next_minibatch(mb_size)
# Specify the mapping of input variables in the model to actual
# minibatch data to be trained with
arguments = {
image_input: mb[features_si],
label_var: mb[labels_si]
}
trainer.train_minibatch(arguments)
print_training_progress(trainer, i, training_progress_output_freq)
if save_model_filename:
print("Saving model:", save_model_filename)
persist.save_model(classifier_output, save_model_filename)
if run_test:
test_minibatch_source = create_reader(os.path.join(data_path, 'test_map.txt'), os.path.join(data_path, 'CIFAR-10_mean.xml'), False)
features_si = test_minibatch_source[feats_stream_name]
labels_si = test_minibatch_source[labels_stream_name]
mb_size = 128
num_mbs = 100
total_error = 0.0
for i in range(0, num_mbs):
mb = test_minibatch_source.next_minibatch(mb_size)
# Specify the mapping of input variables in the model to actual
# minibatch data to be trained with
arguments = {
image_input: mb[features_si],
label_var: mb[labels_si]
}
error = trainer.test_minibatch(arguments)
total_error += error
return total_error / num_mbs
else:
return 0
def train_and_evaluate(reader_train, reader_test, network_name):
set_computation_network_trace_level(0)
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width))
label_var = input_variable((num_classes))
# create model, and configure learning parameters
if network_name == 'resnet20':
z = create_cifar10_model(input_var, 3, num_classes)
lr_per_mb = [1.0]*80+[0.1]*40+[0.01]
elif network_name == 'resnet110':
z = create_cifar10_model(input_var, 18, num_classes)
lr_per_mb = [0.1]*1+[1.0]*80+[0.1]*40+[0.01]
else:
return RuntimeError("Unknown model name!")
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
# shared training parameters
epoch_size = 50000 # for now we manually specify epoch size
minibatch_size = 128
max_epochs = 160
momentum_time_constant = -minibatch_size/np.log(0.9)
l2_reg_weight = 0.0001
# Set learning parameters
lr_per_sample = [lr/minibatch_size for lr in lr_per_mb]
lr_schedule = learning_rate_schedule(lr_per_sample, epoch_size=epoch_size)
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)
# trainer object
learner = momentum_sgd(z.parameters, lr_schedule, mm_schedule,
l2_regularization_weight = l2_reg_weight)
trainer = Trainer(z, ce, pe, learner)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z) ; print()
progress_printer = ProgressPrinter(tag='Training')
# perform model training
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(min(minibatch_size, epoch_size-sample_count), input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += data[label_var].num_samples # count samples processed so far
progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
persist.save_model(z, os.path.join(model_path, network_name + "_{}.dnn".format(epoch)))
# Evaluation parameters
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch, input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
print("")
return metric_numer/metric_denom
def convnet_cifar10(debug_output=False):
set_computation_network_trace_level(0)
image_height = 32
image_width = 32
num_channels = 3
input_dim = image_height * image_width * num_channels
num_output_classes = 10
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width), np.float32)
label_var = input_variable(num_output_classes, np.float32)
# Instantiate the feedforward classification model
input_removemean = minus(input_var, constant(128))
scaled_input = element_times(constant(0.00390625), input_removemean)
with default_options (activation=relu, pad=True):
z = Sequential([
LayerStack(2, lambda : [
Convolution((3,3), 64),
Convolution((3,3), 64),
MaxPooling((3,3), (2,2))
]),
LayerStack(2, lambda i: [
Dense([256,128][i]),
Dropout(0.5)
]),
Dense(num_output_classes, activation=None)
])(scaled_input)
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
reader_train = create_reader(os.path.join(data_path, 'Train_cntk_text.txt'), True, input_dim, num_output_classes)
# training config
epoch_size = 50000 # for now we manually specify epoch size
minibatch_size = 64
# Set learning parameters
lr_per_sample = [0.0015625]*10+[0.00046875]*10+[0.00015625]
lr_schedule = learning_rate_schedule(lr_per_sample, epoch_size=epoch_size)
momentum_time_constant = [0]*20+[-minibatch_size/np.log(0.9)]
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant, epoch_size=epoch_size)
l2_reg_weight = 0.002
# Instantiate the trainer object to drive the model training
learner = momentum_sgd(z.parameters, lr_schedule, mm_schedule, l2_regularization_weight = l2_reg_weight)
trainer = Trainer(z, ce, pe, learner)
# define mapping from reader streams to network inputs
input_map = {
input_var : reader_train.streams.features,
label_var : reader_train.streams.labels
}
log_number_of_parameters(z) ; print()
progress_printer = ProgressPrinter(tag='Training')
# Get minibatches of images to train with and perform model training
max_epochs = 30
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(min(minibatch_size, epoch_size - sample_count), input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += data[label_var].num_samples # count samples processed so far
progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
persist.save_model(z, os.path.join(model_path, "ConvNet_CIFAR10_{}.dnn".format(epoch)))
# Load test data
reader_test = create_reader(os.path.join(data_path, 'Test_cntk_text.txt'), False, input_dim, num_output_classes)
input_map = {
input_var : reader_test.streams.features,
label_var : reader_test.streams.labels
}
# Test data for trained model
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch, input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
print("")
return metric_numer/metric_denom
def convnet_mnist(debug_output=False):
image_height = 28
image_width = 28
num_channels = 1
input_dim = image_height * image_width * num_channels
num_output_classes = 10
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width), np.float32)
label_var = input_variable(num_output_classes, np.float32)
# Instantiate the feedforward classification model
scaled_input = element_times(constant(0.00390625), input_var)
with default_options (activation=relu, pad=False):
conv1 = Convolution((5,5), 32, pad=True)(scaled_input)
pool1 = MaxPooling((3,3), (2,2))(conv1)
conv2 = Convolution((3,3), 48)(pool1)
pool2 = MaxPooling((3,3), (2,2))(conv2)
conv3 = Convolution((3,3), 64)(pool2)
f4 = Dense(96)(conv3)
drop4 = Dropout(0.5)(f4)
z = Dense(num_output_classes, activation=None)(drop4)
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
reader_train = create_reader(os.path.join(data_path, 'Train-28x28_cntk_text.txt'), True, input_dim, num_output_classes)
# training config
epoch_size = 60000 # for now we manually specify epoch size
minibatch_size = 128
# Set learning parameters
lr_per_sample = [0.001]*10+[0.0005]*10+[0.0001]
lr_schedule = learning_rate_schedule(lr_per_sample, epoch_size)
momentum_time_constant = [0]*5+[1024]
# Instantiate the trainer object to drive the model training
learner = momentum_sgd(z.parameters, lr_schedule, momentum_time_constant)
trainer = Trainer(z, ce, pe, learner)
# define mapping from reader streams to network inputs
input_map = {
input_var : reader_train.streams.features,
label_var : reader_train.streams.labels
}
log_number_of_parameters(z) ; print()
progress_printer = ProgressPrinter(tag='Training')
# Get minibatches of images to train with and perform model training
max_epochs = 40
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(min(minibatch_size, epoch_size - sample_count), input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += data[label_var].num_samples # count samples processed so far
progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
persist.save_model(z, os.path.join(model_path, "ConvNet_MNIST_{}.dnn".format(epoch)))
# Load test data
reader_test = create_reader(os.path.join(data_path, 'Test-28x28_cntk_text.txt'), False, input_dim, num_output_classes)
input_map = {
input_var : reader_test.streams.features,
label_var : reader_test.streams.labels
}
# Test data for trained model
epoch_size = 10000
minibatch_size = 1024
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch, input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
print("")
return metric_numer/metric_denom
def train_and_evaluate(reader_train,
reader_test,
network_name,
max_epochs,
distributed_trainer,
scale_up=False):
set_computation_network_trace_level(0)
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width))
label_var = input_variable((num_classes))
# create model, and configure learning parameters
if network_name == 'resnet20':
z = create_cifar10_model(input_var, 3, num_classes)
lr_per_mb = [1.0] * 80 + [0.1] * 40 + [0.01]
elif network_name == 'resnet110':
z = create_cifar10_model(input_var, 18, num_classes)
lr_per_mb = [0.1] * 1 + [1.0] * 80 + [0.1] * 40 + [0.01]
else:
return RuntimeError("Unknown model name!")
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
# shared training parameters
epoch_size = 50000 # for now we manually specify epoch size
# 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 minimatch 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
minibatch_size = 128 * (len(distributed_trainer.communicator().workers())
if scale_up else 1)
momentum_time_constant = -minibatch_size / np.log(0.9)
l2_reg_weight = 0.0001
# Set learning parameters
lr_per_sample = [lr / minibatch_size for lr in lr_per_mb]
lr_schedule = learning_rate_schedule(lr_per_sample,
epoch_size=epoch_size,
unit=UnitType.sample)
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)
# trainer object
learner = momentum_sgd(z.parameters,
lr_schedule,
mm_schedule,
l2_regularization_weight=l2_reg_weight)
trainer = Trainer(z, ce, pe, learner, distributed_trainer)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z)
print()
progress_printer = ProgressPrinter(tag='Training')
# perform model training
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(
min(minibatch_size, epoch_size - sample_count),
input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += trainer.previous_minibatch_sample_count # count samples processed so far
progress_printer.update_with_trainer(
trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
# save model only in worker0, otherwise there will be file write conflicts for multi GPU on the same machine
if distributed_trainer.communicator().current_worker(
).global_rank == 0:
persist.save_model(
z,
os.path.join(model_path,
network_name + "_{}.dnn".format(epoch)))
# Evaluation parameters
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch,
input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(
minibatch_index + 1, (metric_numer * 100.0) / metric_denom,
metric_denom))
print("")
return metric_numer / metric_denom
def train_and_evaluate(reader_train, reader_test, max_epochs,
distributed_trainer):
# Input variables denoting the features and label data
input_var = input_variable((num_channels, image_height, image_width))
label_var = input_variable((num_classes))
# Normalize the input
feature_scale = 1.0 / 256.0
input_var_norm = element_times(feature_scale, input_var)
# apply model to input
z = create_resnet_model(input_var_norm, 10)
#
# Training action
#
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
# training config
epoch_size = 50000
minibatch_size = 128
# Set learning parameters
lr_per_minibatch = learning_rate_schedule([1] * 80 + [0.1] * 40 + [0.01],
UnitType.minibatch, epoch_size)
momentum_time_constant = momentum_as_time_constant_schedule(
-minibatch_size / np.log(0.9))
l2_reg_weight = 0.0001
# trainer object
learner = momentum_sgd(z.parameters,
lr=lr_per_minibatch,
momentum=momentum_time_constant,
l2_regularization_weight=l2_reg_weight)
trainer = Trainer(z, ce, pe, learner, distributed_trainer)
# define mapping from reader streams to network inputs
input_map = {
input_var: reader_train.streams.features,
label_var: reader_train.streams.labels
}
log_number_of_parameters(z)
print()
progress_printer = ProgressPrinter(tag='Training')
# perform model training
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = reader_train.next_minibatch(
minibatch_size, input_map=input_map) # fetch minibatch.
trainer.train_minibatch(data) # update model with it
sample_count += trainer.previous_minibatch_sample_count # count samples processed so far
progress_printer.update_with_trainer(
trainer, with_metric=True) # log progress
progress_printer.epoch_summary(with_metric=True)
if distributed_trainer.communicator().current_worker(
).global_rank == 0:
persist.save_model(
z,
os.path.join(model_path,
"CifarResNet_Distributed_{}.dnn".format(epoch)))
#
# Evaluation action
#
epoch_size = 10000
minibatch_size = 16
# process minibatches and evaluate the model
metric_numer = 0
metric_denom = 0
sample_count = 0
minibatch_index = 0
#progress_printer = ProgressPrinter(freq=100, first=10, tag='Eval')
while sample_count < epoch_size:
current_minibatch = min(minibatch_size, epoch_size - sample_count)
# Fetch next test min batch.
data = reader_test.next_minibatch(current_minibatch,
input_map=input_map)
# minibatch data to be trained with
metric_numer += trainer.test_minibatch(data) * current_minibatch
metric_denom += current_minibatch
# Keep track of the number of samples processed so far.
sample_count += data[label_var].num_samples
minibatch_index += 1
print("")
print("Final Results: Minibatch[1-{}]: errs = {:0.1f}% * {}".format(
minibatch_index + 1, (metric_numer * 100.0) / metric_denom,
metric_denom))
print("")
# return evaluation error.
return metric_numer / metric_denom
