def train():
global sentences, vocabulary, reverse_vocabulary
# function will create the trainer and train it for specified number of epochs
G.num_minibatches = G.train_words // G.minibatch_size
# Print loss 50 times while training
print_freqency = G.num_minibatches // 50
pp = ProgressPrinter(print_freqency)
# get the trainer
word_one_hot, context_one_hots, negative_one_hots, target, trainer, word_negative_context_product, embedding_layer = create_trainer(
)
# Get the input generator
minibatch_generator = cntk_minibatch_generator(G.minibatch_size, sentences,
vocabulary,
reverse_vocabulary)
for train_steps in range(G.num_minibatches):
# Get mini_batch and train for one minibatch
word, contexts, negatives, targets = next(minibatch_generator)
mapping = {word_one_hot: word, target: targets}
for i in range(context_size):
mapping[context_one_hots[i]] = contexts[i]
for i in range(G.negative):
mapping[negative_one_hots[i]] = negatives[i]
trainer.train_minibatch(mapping)
pp.update_with_trainer(trainer)
return word_negative_context_product
def train():
global sentences, vocabulary, reverse_vocabulary
# function will create the trainer and train it for specified number of epochs
# Print loss 50 times while training
print_freqency = 50
pp = ProgressPrinter(print_freqency)
# get the trainer
word_one_hot, context_one_hots, negative_one_hots, target, trainer, word_negative_context_product, embedding_layer = create_trainer(
)
# Train the network using instances form the input generator
training_instances = 0
# print("Calculating the number of training instances")
# start = time.time()
# prev_time = time.time()
# for word, contexts, negatives, targets in cntk_minibatch_generator(G.minibatch_size, sentences, vocabulary, reverse_vocabulary):
# training_instances += 1
# print(training_instances)
# print("time taken for 1 training instance = %.8fsecs" % (time.time() - prev_time))
# prev_time = time.time()
# end = time.time()
# print("Total training instances =", training_instances)
# print("Time taken in one entire loop = %.2fsecs" % (end - start))
training_instances = 0
start_batch_collection = time.time()
for word, contexts, negatives, targets in cntk_minibatch_generator(
G.minibatch_size, sentences, vocabulary, reverse_vocabulary):
end_batch_collection = time.time()
print("Batch collection time = %.6fsecs" %
(end_batch_collection - start_batch_collection))
print("Time taken to collect one training_instance = %.6fsecs" %
((end_batch_collection - start_batch_collection) /
G.minibatch_size))
start_mapping = time.time()
mapping = {word_one_hot: word, target: targets}
for i in range(context_size):
mapping[context_one_hots[i]] = contexts[i]
for i in range(G.negative):
mapping[negative_one_hots[i]] = negatives[i]
end_mapping = time.time()
print("Mapping time = %.6fsecs" % (end_mapping - start_mapping))
start_train = time.time()
trainer.train_minibatch(mapping)
end_train = time.time()
print("minibatch train time = %.6fsecs" % (end_train - start_train))
print("Time per training instance = %.6fsecs" %
((end_train - start_train) / G.minibatch_size))
pp.update_with_trainer(trainer)
training_instances += 1
if training_instances % 20000 == 0:
# Save embeddings temporarily
print("training instances till now =", training_instances)
save_embeddings(word_negative_context_product, vocabulary)
# start_batch_collection = time.time()
print("Total training instances =", training_instances)
return word_negative_context_product
def train_fast_rcnn(debug_output=False):
if debug_output:
print("Storing graphs and intermediate models to %s." % os.path.join(abs_path, "Output"))
# Create the minibatch source
minibatch_source = create_mb_source(image_height, image_width, num_channels,
num_classes, num_rois, base_path, "train")
# Input variables denoting features, rois and label data
image_input = input_variable((num_channels, image_height, image_width))
roi_input = input_variable((num_rois, 4))
label_input = input_variable((num_rois, num_classes))
# define mapping from reader streams to network inputs
input_map = {
image_input: minibatch_source[features_stream_name],
roi_input: minibatch_source[roi_stream_name],
label_input: minibatch_source[label_stream_name]
}
# Instantiate the Fast R-CNN prediction model and loss function
frcn_output = frcn_predictor(image_input, roi_input, num_classes)
ce = cross_entropy_with_softmax(frcn_output, label_input, axis=1)
pe = classification_error(frcn_output, label_input, axis=1)
if debug_output:
plot(frcn_output, os.path.join(abs_path, "Output", "graph_frcn.png"))
# Set learning parameters
l2_reg_weight = 0.0005
lr_per_sample = [0.00001] * 10 + [0.000001] * 5 + [0.0000001]
lr_schedule = learning_rate_schedule(lr_per_sample, unit=UnitType.sample)
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)
# Instantiate the trainer object
learner = momentum_sgd(frcn_output.parameters, lr_schedule, mm_schedule, l2_regularization_weight=l2_reg_weight)
trainer = Trainer(frcn_output, (ce, pe), learner)
# Get minibatches of images and perform model training
print("Training Fast R-CNN model for %s epochs." % max_epochs)
log_number_of_parameters(frcn_output)
progress_printer = ProgressPrinter(tag='Training', num_epochs=max_epochs)
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = minibatch_source.next_minibatch(min(mb_size, epoch_size-sample_count), input_map=input_map)
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 debug_output:
frcn_output.save(os.path.join(abs_path, "Output", "frcn_py_%s.model" % (epoch+1)))
return frcn_output
def train():
global sentences, vocabulary, reverse_vocabulary
# function will create the trainer and train it for specified number of epochs
# Print loss 50 times while training
print_freqency = 50
pp = ProgressPrinter(print_freqency)
# get the trainer
word_one_hot, context_one_hots, negative_one_hots, targets, trainer, word_negative_context_product, embedding_layer = create_trainer()
# Create a CTF reader which reads the sparse inputs
print("reader started")
reader = CTFDeserializer(G.CTF_input_file)
reader.map_input(G.word_input_field, dim=G.embedding_vocab_size, format="sparse")
# context inputs
for i in range(context_size):
reader.map_input(G.context_input_field.format(i), dim=G.embedding_vocab_size, format="sparse")
# negative inputs
for i in range(G.negative):
reader.map_input(G.negative_input_field.format(i), dim=G.embedding_vocab_size, format="sparse")
# targets
reader.map_input(G.target_input_field, dim=(G.negative + 1), format="dense")
print("reader done")
# Get minibatch source from reader
is_training = True
minibatch_source = MinibatchSource(reader, randomize=is_training, epoch_size=INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP)
minibatch_source.streams[targets] = minibatch_source.streams[G.target_input_field]
del minibatch_source.streams[G.target_input_field]
print("minibatch source done")
total_minibatches = total_training_instances // G.minibatch_size
print("traning started")
print("Total minibatches to train =", total_minibatches)
for i in range(total_minibatches):
# Collect minibatch
# start_batch_collection = time.time()
mb = minibatch_source.next_minibatch(G.minibatch_size, input_map=minibatch_source.streams)
# end_batch_collection = time.time()
# print("Batch collection time = %.6fsecs" % (end_batch_collection - start_batch_collection))
# print("Time taken to collect one training_instance = %.6fsecs" % ((end_batch_collection - start_batch_collection)/G.minibatch_size))
# Train minibatch
# start_train = time.time()
trainer.train_minibatch(mb)
# end_train = time.time()
# print("minibatch train time = %.6fsecs" % (end_train - start_train))
# print("Time per training instance = %.6fsecs" % ((end_train - start_train)/G.minibatch_size))
# Update progress printer
pp.update_with_trainer(trainer)
# start_batch_collection = time.time()
print("Total training instances =", total_training_instances)
return word_negative_context_product
def train_sequence_classifier(debug_output=False):
input_dim = 2000
cell_dim = 25
hidden_dim = 25
embedding_dim = 50
num_output_classes = 5
# Input variables denoting the features and label data
features = input_variable(shape=input_dim, is_sparse=True)
label = input_variable(num_output_classes,
dynamic_axes=[Axis.default_batch_axis()])
# Instantiate the sequence classification model
classifier_output = LSTM_sequence_classifer_net(features,
num_output_classes,
embedding_dim, hidden_dim,
cell_dim)
ce = cross_entropy_with_softmax(classifier_output, label)
pe = classification_error(classifier_output, label)
rel_path = ("../../../Tests/EndToEndTests/Text/" +
"SequenceClassification/Data/Train.ctf")
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)
reader = create_reader(path, True, input_dim, num_output_classes)
input_map = {
features: reader.streams.features,
label: reader.streams.labels
}
lr_per_sample = learning_rate_schedule(0.0005, UnitType.sample)
# Instantiate the trainer object to drive the model training
trainer = Trainer(classifier_output, (ce, pe),
sgd(classifier_output.parameters, lr=lr_per_sample))
# Get minibatches of sequences to train with and perform model training
minibatch_size = 200
pp = ProgressPrinter(0)
for i in range(255):
mb = reader.next_minibatch(minibatch_size, input_map=input_map)
trainer.train_minibatch(mb)
pp.update_with_trainer(trainer, True)
evaluation_average = float(trainer.previous_minibatch_evaluation_average)
loss_average = float(trainer.previous_minibatch_loss_average)
return evaluation_average, loss_average
def evaluate_decoding(reader, s2smodel, i2w):
model_decoding = create_model_greedy(
s2smodel) # wrap the greedy decoder around the model
progress_printer = ProgressPrinter(tag='Evaluation')
sparse_to_dense = create_sparse_to_dense(input_vocab_dim)
minibatch_size = 1024
num_total = 0
num_wrong = 0
while True:
mb = reader.next_minibatch(minibatch_size)
if not mb: # finish when end of test set reached
break
e = model_decoding(mb[reader.streams.features])
outputs = format_sequences(e, i2w)
labels = format_sequences(sparse_to_dense(mb[reader.streams.labels]),
i2w)
# prepend sentence start for comparison
outputs = ["<s> " + output for output in outputs]
num_total += len(outputs)
num_wrong += sum(
[label != output for output, label in zip(outputs, labels)])
rate = num_wrong / num_total
print("string error rate of {:.1f}% in {} samples".format(
100 * rate, num_total))
return rate
def train_sequence_classifier(debug_output=False):
input_dim = 2000
cell_dim = 25
hidden_dim = 25
embedding_dim = 50
num_output_classes = 5
# Input variables denoting the features and label data
features = input_variable(shape=input_dim, is_sparse=True)
label = input_variable(num_output_classes, dynamic_axes=[
Axis.default_batch_axis()])
# Instantiate the sequence classification model
classifier_output = LSTM_sequence_classifer_net(
features, num_output_classes, embedding_dim, hidden_dim, cell_dim)
ce = cross_entropy_with_softmax(classifier_output, label)
pe = classification_error(classifier_output, label)
rel_path = ("../../../Tests/EndToEndTests/Text/" +
"SequenceClassification/Data/Train.ctf")
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)
reader = create_reader(path, True, input_dim, num_output_classes)
input_map = {
features: reader.streams.features,
label: reader.streams.labels
}
lr_per_sample = learning_rate_schedule(0.0005, UnitType.sample)
# Instantiate the trainer object to drive the model training
trainer = Trainer(classifier_output, (ce, pe),
sgd(classifier_output.parameters, lr=lr_per_sample))
# Get minibatches of sequences to train with and perform model training
minibatch_size = 200
pp = ProgressPrinter(0)
for i in range(255):
mb = reader.next_minibatch(minibatch_size, input_map=input_map)
trainer.train_minibatch(mb)
pp.update_with_trainer(trainer, True)
evaluation_average = float(trainer.previous_minibatch_evaluation_average)
loss_average = float(trainer.previous_minibatch_loss_average)
return evaluation_average, loss_average
def train_model(base_model_file, feature_node_name, last_hidden_node_name,
image_width, image_height, num_channels, num_classes, train_map_file,
num_epochs, max_images=-1, freeze=False):
epoch_size = sum(1 for line in open(train_map_file))
if max_images > 0:
epoch_size = min(epoch_size, max_images)
# Create the minibatch source and input variables
minibatch_source = create_mb_source(train_map_file, image_width, image_height, num_channels, num_classes)
image_input = input_variable((num_channels, image_height, image_width))
label_input = input_variable(num_classes)
# Define mapping from reader streams to network inputs
input_map = {
image_input: minibatch_source[features_stream_name],
label_input: minibatch_source[label_stream_name]
}
# Instantiate the transfer learning model and loss function
tl_model = create_model(base_model_file, feature_node_name, last_hidden_node_name, num_classes, image_input, freeze)
ce = cross_entropy_with_softmax(tl_model, label_input)
pe = classification_error(tl_model, label_input)
# Instantiate the trainer object
lr_schedule = learning_rate_schedule(lr_per_mb, unit=UnitType.minibatch)
mm_schedule = momentum_schedule(momentum_per_mb)
learner = momentum_sgd(tl_model.parameters, lr_schedule, mm_schedule, l2_regularization_weight=l2_reg_weight)
trainer = Trainer(tl_model, (ce, pe), learner)
# Get minibatches of images and perform model training
print("Training transfer learning model for {0} epochs (epoch_size = {1}).".format(num_epochs, epoch_size))
log_number_of_parameters(tl_model)
progress_printer = ProgressPrinter(tag='Training', num_epochs=num_epochs)
for epoch in range(num_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = minibatch_source.next_minibatch(min(mb_size, epoch_size-sample_count), input_map=input_map)
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
if sample_count % (100 * mb_size) == 0:
print ("Processed {0} samples".format(sample_count))
progress_printer.epoch_summary(with_metric=True)
return tl_model
def ffnet():
inputs = 2
outputs = 2
layers = 2
hidden_dimension = 50
# input variables denoting the features and label data
features = C.input_variable((inputs), np.float32)
label = C.input_variable((outputs), np.float32)
# Instantiate the feedforward classification model
my_model = Sequential(
[Dense(hidden_dimension, activation=C.sigmoid),
Dense(outputs)])
z = my_model(features)
ce = C.cross_entropy_with_softmax(z, label)
pe = C.classification_error(z, label)
# Instantiate the trainer object to drive the model training
lr_per_minibatch = learning_rate_schedule(0.125, UnitType.minibatch)
trainer = C.Trainer(z, ce, pe, [sgd(z.parameters, lr=lr_per_minibatch)])
# Get minibatches of training data and perform model training
minibatch_size = 25
num_minibatches_to_train = 1024
pp = ProgressPrinter(0)
for i in range(num_minibatches_to_train):
train_features, labels = generate_random_data(minibatch_size, inputs,
outputs)
# Specify the mapping of input variables in the model to actual minibatch data to be trained with
trainer.train_minibatch({features: train_features, label: labels})
pp.update_with_trainer(trainer)
last_avg_error = pp.avg_loss_since_start()
test_features, test_labels = generate_random_data(minibatch_size, inputs,
outputs)
avg_error = trainer.test_minibatch({
features: test_features,
label: test_labels
})
print(' error rate on an unseen minibatch: {}'.format(avg_error))
return last_avg_error, avg_error
def train_fast_rcnn(debug_output=False):
if debug_output:
print("Storing graphs and intermediate models to %s." % os.path.join(abs_path, "Output"))
# Create the minibatch source
minibatch_source = create_mb_source(image_height, image_width, num_channels,
num_classes, num_rois, base_path, "train")
# Input variables denoting features, rois and label data
image_input = input_variable((num_channels, image_height, image_width))
roi_input = input_variable((num_rois, 4))
label_input = input_variable((num_rois, num_classes))
# define mapping from reader streams to network inputs
input_map = {
image_input: minibatch_source[features_stream_name],
roi_input: minibatch_source[roi_stream_name],
label_input: minibatch_source[label_stream_name]
}
# Instantiate the Fast R-CNN prediction model and loss function
frcn_output = frcn_predictor(image_input, roi_input, num_classes)
ce = cross_entropy_with_softmax(frcn_output, label_input, axis=1)
pe = classification_error(frcn_output, label_input, axis=1)
if debug_output:
plot(frcn_output, os.path.join(abs_path, "Output", "graph_frcn.png"))
# Set learning parameters
l2_reg_weight = 0.0005
lr_per_sample = [0.00001] * 10 + [0.000001] * 5 + [0.0000001]
lr_schedule = learning_rate_schedule(lr_per_sample, unit=UnitType.sample)
mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)
# Instantiate the trainer object
learner = momentum_sgd(frcn_output.parameters, lr_schedule, mm_schedule, l2_regularization_weight=l2_reg_weight)
progress_printer = ProgressPrinter(tag='Training', num_epochs=max_epochs)
trainer = Trainer(frcn_output, (ce, pe), learner, progress_printer)
# Get minibatches of images and perform model training
print("Training Fast R-CNN model for %s epochs." % max_epochs)
log_number_of_parameters(frcn_output)
for epoch in range(max_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = minibatch_source.next_minibatch(min(mb_size, epoch_size-sample_count), input_map=input_map)
trainer.train_minibatch(data) # update model with it
sample_count += trainer.previous_minibatch_sample_count # count samples processed so far
trainer.summarize_training_progress()
if debug_output:
frcn_output.save(os.path.join(abs_path, "Output", "frcn_py_%s.model" % (epoch+1)))
return frcn_output
def ffnet():
inputs = 2
outputs = 2
layers = 2
hidden_dimension = 50
# input variables denoting the features and label data
features = C.input_variable((inputs), np.float32)
label = C.input_variable((outputs), np.float32)
# Instantiate the feedforward classification model
my_model = Sequential ([
Dense(hidden_dimension, activation=C.sigmoid),
Dense(outputs)])
z = my_model(features)
ce = C.cross_entropy_with_softmax(z, label)
pe = C.classification_error(z, label)
# Instantiate the trainer object to drive the model training
lr_per_minibatch = learning_rate_schedule(0.125, UnitType.minibatch)
trainer = C.Trainer(z, (ce, pe), [sgd(z.parameters, lr=lr_per_minibatch)])
# Get minibatches of training data and perform model training
minibatch_size = 25
num_minibatches_to_train = 1024
pp = ProgressPrinter(0)
for i in range(num_minibatches_to_train):
train_features, labels = generate_random_data(minibatch_size, inputs, outputs)
# Specify the mapping of input variables in the model to actual minibatch data to be trained with
trainer.train_minibatch({features : train_features, label : labels})
pp.update_with_trainer(trainer)
last_avg_error = pp.avg_loss_since_start()
test_features, test_labels = generate_random_data(minibatch_size, inputs, outputs)
avg_error = trainer.test_minibatch({features : test_features, label : test_labels})
print(' error rate on an unseen minibatch: {}'.format(avg_error))
return last_avg_error, avg_error
def ffnet():
input_dim = 2
num_output_classes = 2
num_hidden_layers = 2
hidden_layers_dim = 50
# Input variables denoting the features and label data
input = input_variable((input_dim), np.float32)
label = input_variable((num_output_classes), np.float32)
# Instantiate the feedforward classification model
netout = fully_connected_classifier_net(
input, num_output_classes, hidden_layers_dim, num_hidden_layers, sigmoid)
ce = cross_entropy_with_softmax(netout, label)
pe = classification_error(netout, label)
lr_per_minibatch=learning_rate_schedule(0.5, UnitType.minibatch)
# Instantiate the trainer object to drive the model training
trainer = Trainer(netout, ce, pe, sgd(netout.parameters, lr=lr_per_minibatch))
# Get minibatches of training data and perform model training
minibatch_size = 25
pp = ProgressPrinter(128)
for i in range(1024):
features, labels = generate_random_data(
minibatch_size, input_dim, num_output_classes)
# Specify the mapping of input variables in the model to actual
# minibatch data to be trained with
trainer.train_minibatch({input: features, label: labels})
pp.update_with_trainer(trainer)
pp.epoch_summary()
test_features, test_labels = generate_random_data(
minibatch_size, input_dim, num_output_classes)
avg_error = trainer.test_minibatch(
{input: test_features, label: test_labels})
return avg_error
def _hyper_train_target_sub(self, **kwargs):
"""
Actual training procedure for specific set of hyper parameters.
"""
if self.saver.log_filename:
fh = logging.FileHandler(self.saver.log_filename)
self.logger.addHandler(fh)
self.logger.info("Training with parameters: {}".format(kwargs))
X_train, Y_train, X_val, Y_val = self.data_source(**kwargs)
input_var, label_var, output = self.model(**kwargs)
loss = cross_entropy_with_softmax(output, label_var)
label_error = classification_error(output, label_var)
learner = self.optimizer(
parameters=output.parameters,
momentum=0.9,
**kwargs)
progress_printer = ProgressPrinter(tag='Training', num_epochs=self.num_epoch)
trainer = Trainer(output, (loss, label_error), [learner], [progress_printer])
# input_map = {
# input_var: reader_train.streams.features,
# label_var: reader_train.streams.labels
# }
num_minibatches_to_train = X_train.shape[0] / self.data_source.batch_size
for i in range(0, int(num_minibatches_to_train)):
features = X_train[:self.data_source.batch_size]
labels = Y_train[:self.data_source.batch_size]
trainer.train_minibatch({input_var: features, label_var: labels})
if self.saver.log_filename:
self.logger.removeHandler(fh)
fh.close()
best_value = 0.0
return best_value
def ffnet():
input_dim = 2
num_output_classes = 2
num_hidden_layers = 2
hidden_layers_dim = 50
# Input variables denoting the features and label data
input = input_variable((input_dim), np.float32)
label = input_variable((num_output_classes), np.float32)
# Instantiate the feedforward classification model
netout = fully_connected_classifier_net(input, num_output_classes,
hidden_layers_dim,
num_hidden_layers, sigmoid)
ce = cross_entropy_with_softmax(netout, label)
pe = classification_error(netout, label)
lr_per_minibatch = learning_rate_schedule(0.5, UnitType.minibatch)
# Instantiate the trainer object to drive the model training
learner = sgd(netout.parameters, lr=lr_per_minibatch)
progress_printer = ProgressPrinter(128)
trainer = Trainer(netout, (ce, pe), learner, progress_printer)
# Get minibatches of training data and perform model training
minibatch_size = 25
for i in range(1024):
features, labels = generate_random_data(minibatch_size, input_dim,
num_output_classes)
# Specify the mapping of input variables in the model to actual
# minibatch data to be trained with
trainer.train_minibatch({input: features, label: labels})
trainer.summarize_training_progress()
test_features, test_labels = generate_random_data(minibatch_size,
input_dim,
num_output_classes)
avg_error = trainer.test_minibatch({
input: test_features,
label: test_labels
})
return avg_error
def main():
# Ensure we always get the same amount of randomness
np.random.seed(0)
global minibatch_size, skip_window
if len(sys.argv) < 2:
print(
'Insufficient number of arguments. For running the example case, run: $ python word2vec.py runexample'
)
exit(1)
filename = sys.argv[1]
process_text(filename)
inp, label, trainer = train(emb_size, vocab_size)
pp = ProgressPrinter(50)
for _epoch in range(num_epochs):
i = 0
while curr_epoch == _epoch:
features, labels = generate_batch(minibatch_size, skip_window)
features = get_one_hot(features)
labels = get_one_hot(labels)
trainer.train_minibatch({inp: features, label: labels})
pp.update_with_trainer(trainer)
i += 1
if i % 200 == 0:
print('Saving Embeddings..')
with open(embpickle, 'wb') as handle:
pickle.dump(embeddings.value, handle)
pp.epoch_summary()
test_features, test_labels = generate_batch(minibatch_size, skip_window)
test_features = get_one_hot(test_features)
test_labels = get_one_hot(test_labels)
avg_error = trainer.test_minibatch({
inp: test_features,
label: test_labels
})
print('Avg. Error on Test Set: ', avg_error)
def train_lm(training_file, max_num_minibatches):
# load the data and vocab
data, char_to_ix, ix_to_char, data_size, vocab_dim = load_data_and_vocab(training_file)
# Model the source and target inputs to the model
input_sequence, label_sequence = create_inputs(vocab_dim)
# create the model
model = create_model(vocab_dim)
# and apply it to the input sequence
z = model(input_sequence)
# setup the criterions (loss and metric)
ce = cross_entropy_with_softmax(z, label_sequence)
errs = classification_error(z, label_sequence)
# Instantiate the trainer object to drive the model training
lr_per_sample = learning_rate_schedule(0.001, UnitType.sample)
momentum_time_constant = momentum_as_time_constant_schedule(1100)
clipping_threshold_per_sample = 5.0
gradient_clipping_with_truncation = True
learner = momentum_sgd(z.parameters, lr_per_sample, momentum_time_constant,
gradient_clipping_threshold_per_sample=clipping_threshold_per_sample,
gradient_clipping_with_truncation=gradient_clipping_with_truncation)
trainer = Trainer(z, (ce, errs), learner)
sample_freq = 1000
epochs = 50
minibatches_per_epoch = int((data_size / minibatch_size))
minibatches = min(epochs * minibatches_per_epoch, max_num_minibatches)
# print out some useful training information
log_number_of_parameters(z) ; print()
progress_printer = ProgressPrinter(freq=100, tag='Training')
e = 0
p = 0
for i in range(0, minibatches):
if p + minibatch_size+1 >= data_size:
p = 0
e += 1
model_filename = "models/shakespeare_epoch%d.dnn" % e
z.save(model_filename)
print("Saved model to '%s'" % model_filename)
# get the data
features, labels = get_data(p, minibatch_size, data, char_to_ix, vocab_dim)
# Specify the mapping of input variables in the model to actual minibatch data to be trained with
# If it's the start of the data, we specify that we are looking at a new sequence (True)
mask = [False]
if p == 0:
mask = [True]
arguments = ({input_sequence : features, label_sequence : labels}, mask)
trainer.train_minibatch(arguments)
progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
if i % sample_freq == 0:
print(sample(z, ix_to_char, vocab_dim, char_to_ix))
p += minibatch_size
# Do a final save of the model
model_filename = "models/shakespeare_epoch%d.dnn" % e
z.save(model_filename)
return batch, labels
#Creating One-Hot set
def get_one_hot(origlabels):
global minibatch_size, vocab_size
labels = np.zeros(shape=(minibatch_size, vocab_size), dtype=np.float32)
for t in range(len(origlabels)):
if origlabels[t, 0] < vocab_size and origlabels[t, 0] >= 0:
labels[t, origlabels[t, 0]] = 1.0
return labels
#Testing & training
build_dataset()
inp, label, trainer = train(emb_size, vocab_size)
print('Model Creation Done.')
pp = ProgressPrinter(50)
for _epoch in range(num_epochs):
i = 0
while curr_epoch == _epoch:
features, labels = generate_batch(minibatch_size, skip_window)
features = get_one_hot(features)
labels = get_one_hot(labels)
trainer.train_minibatch({inp: features, label: labels})
pp.update_with_trainer(trainer)
i += 1
if i % 200 == 0:
print('Saving Embeddings..')
with open(embpickle, 'wb') as handle:
pickle.dump(embeddings.value, handle)
def train_lm(training_file, max_num_minibatches):
# load the data and vocab
data, char_to_ix, ix_to_char, data_size, vocab_dim = load_data_and_vocab(
training_file)
# Model the source and target inputs to the model
input_sequence, label_sequence = create_inputs(vocab_dim)
# create the model
model = create_model(vocab_dim)
# and apply it to the input sequence
z = model(input_sequence)
# setup the criterions (loss and metric)
ce = cross_entropy_with_softmax(z, label_sequence)
errs = classification_error(z, label_sequence)
# Instantiate the trainer object to drive the model training
lr_per_sample = learning_rate_schedule(0.001, UnitType.sample)
momentum_time_constant = momentum_as_time_constant_schedule(1100)
clipping_threshold_per_sample = 5.0
gradient_clipping_with_truncation = True
learner = momentum_sgd(
z.parameters,
lr_per_sample,
momentum_time_constant,
gradient_clipping_threshold_per_sample=clipping_threshold_per_sample,
gradient_clipping_with_truncation=gradient_clipping_with_truncation)
trainer = Trainer(z, (ce, errs), learner)
sample_freq = 1000
epochs = 50
minibatches_per_epoch = int((data_size / minibatch_size))
minibatches = min(epochs * minibatches_per_epoch, max_num_minibatches)
# print out some useful training information
log_number_of_parameters(z)
print()
progress_printer = ProgressPrinter(freq=100, tag='Training')
e = 0
p = 0
for i in range(0, minibatches):
if p + minibatch_size + 1 >= data_size:
p = 0
e += 1
model_filename = "models/shakespeare_epoch%d.dnn" % e
z.save(model_filename)
print("Saved model to '%s'" % model_filename)
# get the data
features, labels = get_data(p, minibatch_size, data, char_to_ix,
vocab_dim)
# Specify the mapping of input variables in the model to actual minibatch data to be trained with
# If it's the start of the data, we specify that we are looking at a new sequence (True)
mask = [False]
if p == 0:
mask = [True]
arguments = ({input_sequence: features, label_sequence: labels}, mask)
trainer.train_minibatch(arguments)
progress_printer.update_with_trainer(trainer,
with_metric=True) # log progress
if i % sample_freq == 0:
print(sample(z, ix_to_char, vocab_dim, char_to_ix))
p += minibatch_size
# Do a final save of the model
model_filename = "models/shakespeare_epoch%d.dnn" % e
z.save(model_filename)
def train_model(base_model_file,
feature_node_name,
last_hidden_node_name,
image_width,
image_height,
num_channels,
num_classes,
train_map_file,
num_epochs,
max_images=-1,
freeze=False):
epoch_size = sum(1 for line in open(train_map_file))
if max_images > 0:
epoch_size = min(epoch_size, max_images)
# Create the minibatch source and input variables
minibatch_source = create_mb_source(train_map_file, image_width,
image_height, num_channels,
num_classes)
image_input = input_variable((num_channels, image_height, image_width))
label_input = input_variable(num_classes)
# Define mapping from reader streams to network inputs
input_map = {
image_input: minibatch_source[features_stream_name],
label_input: minibatch_source[label_stream_name]
}
# Instantiate the transfer learning model and loss function
tl_model = create_model(base_model_file, feature_node_name,
last_hidden_node_name, num_classes, image_input,
freeze)
ce = cross_entropy_with_softmax(tl_model, label_input)
pe = classification_error(tl_model, label_input)
# Instantiate the trainer object
lr_schedule = learning_rate_schedule(lr_per_mb, unit=UnitType.minibatch)
mm_schedule = momentum_schedule(momentum_per_mb)
learner = momentum_sgd(tl_model.parameters,
lr_schedule,
mm_schedule,
l2_regularization_weight=l2_reg_weight)
trainer = Trainer(tl_model, (ce, pe), learner)
# Get minibatches of images and perform model training
print(
"Training transfer learning model for {0} epochs (epoch_size = {1}).".
format(num_epochs, epoch_size))
log_number_of_parameters(tl_model)
progress_printer = ProgressPrinter(tag='Training', num_epochs=num_epochs)
for epoch in range(num_epochs): # loop over epochs
sample_count = 0
while sample_count < epoch_size: # loop over minibatches in the epoch
data = minibatch_source.next_minibatch(min(
mb_size, epoch_size - sample_count),
input_map=input_map)
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
if sample_count % (100 * mb_size) == 0:
print("Processed {0} samples".format(sample_count))
progress_printer.epoch_summary(with_metric=True)
return tl_model
def train(train_reader, valid_reader, vocab, i2w, s2smodel, max_epochs,
epoch_size):
# Note: We would like to set the signature of 's2smodel' (s2smodel.update_signature()), but that will cause
# an error since the training criterion uses a reduced sequence axis for the labels.
# This is because it removes the initial <s> symbol. Hence, we must leave the model
# with unspecified input shapes and axes.
# create the training wrapper for the s2smodel, as well as the criterion function
model_train = create_model_train(s2smodel)
criterion = create_criterion_function(model_train)
# also wire in a greedy decoder so that we can properly log progress on a validation example
# This is not used for the actual training process.
model_greedy = create_model_greedy(s2smodel)
# This does not need to be done in training generally though
# Instantiate the trainer object to drive the model training
minibatch_size = 72
lr = 0.001 if use_attention else 0.005 # TODO: can we use the same value for both?
learner = adam_sgd(
model_train.parameters,
lr=learning_rate_schedule([lr] * 2 + [lr / 2] * 3 + [lr / 4],
UnitType.sample, epoch_size),
momentum=momentum_as_time_constant_schedule(1100),
gradient_clipping_threshold_per_sample=2.3,
gradient_clipping_with_truncation=True)
trainer = Trainer(None, criterion, learner)
# Get minibatches of sequences to train with and perform model training
total_samples = 0
mbs = 0
eval_freq = 100
# print out some useful training information
log_number_of_parameters(model_train)
print()
progress_printer = ProgressPrinter(freq=30, tag='Training')
#progress_printer = ProgressPrinter(freq=30, tag='Training', log_to_file=model_path_stem + ".log") # use this to log to file
sparse_to_dense = create_sparse_to_dense(input_vocab_dim)
for epoch in range(max_epochs):
print("Saving model to '%s'" % model_path(epoch))
s2smodel.save(model_path(epoch))
while total_samples < (epoch + 1) * epoch_size:
# get next minibatch of training data
mb_train = train_reader.next_minibatch(minibatch_size)
#trainer.train_minibatch(mb_train[train_reader.streams.features], mb_train[train_reader.streams.labels])
trainer.train_minibatch({
criterion.arguments[0]:
mb_train[train_reader.streams.features],
criterion.arguments[1]:
mb_train[train_reader.streams.labels]
})
progress_printer.update_with_trainer(
trainer, with_metric=True) # log progress
# every N MBs evaluate on a test sequence to visually show how we're doing
if mbs % eval_freq == 0:
mb_valid = valid_reader.next_minibatch(1)
# run an eval on the decoder output model (i.e. don't use the groundtruth)
e = model_greedy(mb_valid[valid_reader.streams.features])
print(
format_sequences(
sparse_to_dense(
mb_valid[valid_reader.streams.features]), i2w))
print("->")
print(format_sequences(e, i2w))
# debugging attention
if use_attention:
debug_attention(model_greedy,
mb_valid[valid_reader.streams.features])
total_samples += mb_train[train_reader.streams.labels].num_samples
mbs += 1
# log a summary of the stats for the epoch
progress_printer.epoch_summary(with_metric=True)
# done: save the final model
print("Saving final model to '%s'" % model_path(max_epochs))
s2smodel.save(model_path(max_epochs))
print("%d epochs complete." % max_epochs)
def simple_mnist():
input_dim = 784
num_output_classes = 10
num_hidden_layers = 1
hidden_layers_dim = 200
# Input variables denoting the features and label data
features = input_variable(input_dim, np.float32)
label = input_variable(num_output_classes, np.float32)
# Instantiate the feedforward classification model
scaled_input = element_times(constant(0.00390625), features)
netout = fully_connected_classifier_net(
scaled_input, num_output_classes, hidden_layers_dim, num_hidden_layers, relu)
ce = cross_entropy_with_softmax(netout, label)
pe = classification_error(netout, label)
try:
rel_path = os.path.join(os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
*"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/"))
except KeyError:
rel_path = os.path.join(*"../Image/DataSets/MNIST/Train-28x28_cntk_text.txt".split("/"))
path = os.path.normpath(os.path.join(abs_path, rel_path))
check_path(path)
reader_train = create_reader(path, True, input_dim, num_output_classes)
input_map = {
features: reader_train.streams.features,
label: reader_train.streams.labels
}
lr_per_minibatch = learning_rate_schedule(0.2, UnitType.minibatch)
# Instantiate the trainer object to drive the model training
trainer = Trainer(netout, (ce, pe), sgd(netout.parameters, lr=lr_per_minibatch))
# Instantiate a ProgressPrinter.
logdir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "mnist_log")
progress_printer = ProgressPrinter(tag='Training', freq=1, tensorboard_log_dir=logdir, model=netout)
# Get minibatches of images to train with and perform model training
minibatch_size = 64
num_samples_per_sweep = 6000
num_sweeps_to_train_with = 2
num_minibatches_to_train = (num_samples_per_sweep * num_sweeps_to_train_with) / minibatch_size
for minibatch_idx in range(0, int(num_minibatches_to_train)):
trainer.train_minibatch(reader_train.next_minibatch(minibatch_size, input_map=input_map))
# Take snapshot of loss and eval criterion for the previous minibatch.
progress_printer.update_with_trainer(trainer, with_metric=True)
# Log max/min/mean of each parameter tensor, so that we can confirm that the parameters change indeed.
# Don't want to do that very often though, otherwise will spend too much time computing min/max/mean.
if minibatch_idx % 10 == 9:
for p in netout.parameters:
progress_printer.update_value("mb_" + p.uid + "_max", reduce_max(p).eval(), minibatch_idx)
progress_printer.update_value("mb_" + p.uid + "_min", reduce_min(p).eval(), minibatch_idx)
progress_printer.update_value("mb_" + p.uid + "_mean", reduce_mean(p).eval(), minibatch_idx)
# Load test data
try:
rel_path = os.path.join(os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
*"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/"))
except KeyError:
rel_path = os.path.join(*"../Image/DataSets/MNIST/Test-28x28_cntk_text.txt".split("/"))
path = os.path.normpath(os.path.join(abs_path, rel_path))
check_path(path)
reader_test = create_reader(path, False, input_dim, num_output_classes)
input_map = {
features: reader_test.streams.features,
label: reader_test.streams.labels
}
# Test data for trained model
test_minibatch_size = 1024
num_samples = 10000
num_minibatches_to_test = num_samples / test_minibatch_size
test_result = 0.0
for i in range(0, int(num_minibatches_to_test)):
mb = reader_test.next_minibatch(test_minibatch_size, input_map=input_map)
test_result += trainer.test_minibatch(mb)
# Average of evaluation errors of all test minibatches
return test_result / num_minibatches_to_test
def simple_mnist():
input_dim = 784
num_output_classes = 10
num_hidden_layers = 1
hidden_layers_dim = 200
# Input variables denoting the features and label data
input = input_variable(input_dim, np.float32)
label = input_variable(num_output_classes, np.float32)
# Instantiate the feedforward classification model
scaled_input = element_times(constant(0.00390625), input)
z = fully_connected_classifier_net(scaled_input, num_output_classes,
hidden_layers_dim, num_hidden_layers,
relu)
ce = cross_entropy_with_softmax(z, label)
pe = classification_error(z, label)
data_dir = os.path.join(abs_path, "..", "..", "..", "DataSets", "MNIST")
path = os.path.normpath(os.path.join(data_dir,
"Train-28x28_cntk_text.txt"))
check_path(path)
reader_train = create_reader(path, True, input_dim, num_output_classes)
input_map = {
input: reader_train.streams.features,
label: reader_train.streams.labels
}
lr_per_minibatch = learning_rate_schedule(0.2, UnitType.minibatch)
# Instantiate the trainer object to drive the model training
trainer = Trainer(z, (ce, pe), sgd(z.parameters, lr=lr_per_minibatch))
# Get minibatches of images to train with and perform model training
minibatch_size = 64
num_samples_per_sweep = 60000
num_sweeps_to_train_with = 10
#training_progress_output_freq = 100
progress_printer = ProgressPrinter(
#freq=training_progress_output_freq,
tag='Training',
num_epochs=num_sweeps_to_train_with)
session = training_session(
training_minibatch_source=reader_train,
trainer=trainer,
mb_size_schedule=minibatch_size_schedule(minibatch_size),
progress_printer=progress_printer,
model_inputs_to_mb_source_mapping=input_map,
progress_frequency=num_samples_per_sweep,
max_training_samples=num_samples_per_sweep * num_sweeps_to_train_with)
session.train()
# Load test data
path = os.path.normpath(os.path.join(data_dir, "Test-28x28_cntk_text.txt"))
check_path(path)
reader_test = create_reader(path, False, input_dim, num_output_classes)
input_map = {
input: reader_test.streams.features,
label: reader_test.streams.labels
}
# Test data for trained model
test_minibatch_size = 1024
num_samples = 10000
num_minibatches_to_test = num_samples / test_minibatch_size
test_result = 0.0
for i in range(0, int(num_minibatches_to_test)):
mb = reader_test.next_minibatch(test_minibatch_size,
input_map=input_map)
eval_error = trainer.test_minibatch(mb)
test_result = test_result + eval_error
# Average of evaluation errors of all test minibatches
return test_result / num_minibatches_to_test
def simple_mnist():
input_dim = 784
num_output_classes = 10
num_hidden_layers = 1
hidden_layers_dim = 200
# Input variables denoting the features and label data
features = input_variable(input_dim, np.float32)
label = input_variable(num_output_classes, np.float32)
# Instantiate the feedforward classification model
scaled_input = element_times(constant(0.00390625), features)
netout = fully_connected_classifier_net(scaled_input, num_output_classes,
hidden_layers_dim,
num_hidden_layers, relu)
ce = cross_entropy_with_softmax(netout, label)
pe = classification_error(netout, label)
try:
rel_path = os.path.join(
os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
*"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/"))
except KeyError:
rel_path = os.path.join(
*"../Image/DataSets/MNIST/Train-28x28_cntk_text.txt".split("/"))
path = os.path.normpath(os.path.join(abs_path, rel_path))
check_path(path)
reader_train = create_reader(path, True, input_dim, num_output_classes)
input_map = {
features: reader_train.streams.features,
label: reader_train.streams.labels
}
lr_per_minibatch = learning_rate_schedule(0.2, UnitType.minibatch)
# Instantiate the trainer object to drive the model training
trainer = Trainer(netout, ce, pe,
sgd(netout.parameters, lr=lr_per_minibatch))
# Instantiate a ProgressPrinter.
logdir = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"mnist_log")
progress_printer = ProgressPrinter(tag='Training',
freq=1,
tensorboard_log_dir=logdir,
model=netout)
# Get minibatches of images to train with and perform model training
minibatch_size = 64
num_samples_per_sweep = 6000
num_sweeps_to_train_with = 2
num_minibatches_to_train = (num_samples_per_sweep *
num_sweeps_to_train_with) / minibatch_size
for minibatch_idx in range(0, int(num_minibatches_to_train)):
trainer.train_minibatch(
reader_train.next_minibatch(minibatch_size, input_map=input_map))
# Take snapshot of loss and eval criterion for the previous minibatch.
progress_printer.update_with_trainer(trainer, with_metric=True)
# Log max/min/mean of each parameter tensor, so that we can confirm that the parameters change indeed.
# Don't want to do that very often though, otherwise will spend too much time computing min/max/mean.
if minibatch_idx % 10 == 9:
for p in netout.parameters:
progress_printer.update_value("mb_" + p.uid + "_max",
reduce_max(p).eval(),
minibatch_idx)
progress_printer.update_value("mb_" + p.uid + "_min",
reduce_min(p).eval(),
minibatch_idx)
progress_printer.update_value("mb_" + p.uid + "_mean",
reduce_mean(p).eval(),
minibatch_idx)
# Load test data
try:
rel_path = os.path.join(
os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
*"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/"))
except KeyError:
rel_path = os.path.join(
*"../Image/DataSets/MNIST/Test-28x28_cntk_text.txt".split("/"))
path = os.path.normpath(os.path.join(abs_path, rel_path))
check_path(path)
reader_test = create_reader(path, False, input_dim, num_output_classes)
input_map = {
features: reader_test.streams.features,
label: reader_test.streams.labels
}
# Test data for trained model
test_minibatch_size = 1024
num_samples = 10000
num_minibatches_to_test = num_samples / test_minibatch_size
test_result = 0.0
for i in range(0, int(num_minibatches_to_test)):
mb = reader_test.next_minibatch(test_minibatch_size,
input_map=input_map)
test_result += trainer.test_minibatch(mb)
# Average of evaluation errors of all test minibatches
return test_result / num_minibatches_to_test
def train(train_reader, valid_reader, vocab, i2w, s2smodel, max_epochs, epoch_size):
# Note: We would like to set the signature of 's2smodel' (s2smodel.update_signature()), but that will cause
# an error since the training criterion uses a reduced sequence axis for the labels.
# This is because it removes the initial <s> symbol. Hence, we must leave the model
# with unspecified input shapes and axes.
# create the training wrapper for the s2smodel, as well as the criterion function
model_train = create_model_train(s2smodel)
criterion = create_criterion_function(model_train)
# also wire in a greedy decoder so that we can properly log progress on a validation example
# This is not used for the actual training process.
model_greedy = create_model_greedy(s2smodel)
# This does not need to be done in training generally though
# Instantiate the trainer object to drive the model training
minibatch_size = 72
lr = 0.001 if use_attention else 0.005 # TODO: can we use the same value for both?
learner = adam_sgd(model_train.parameters,
lr = learning_rate_schedule([lr]*2+[lr/2]*3+[lr/4], UnitType.sample, epoch_size),
momentum = momentum_as_time_constant_schedule(1100),
gradient_clipping_threshold_per_sample=2.3,
gradient_clipping_with_truncation=True)
trainer = Trainer(None, criterion, learner)
# Get minibatches of sequences to train with and perform model training
total_samples = 0
mbs = 0
eval_freq = 100
# print out some useful training information
log_number_of_parameters(model_train) ; print()
progress_printer = ProgressPrinter(freq=30, tag='Training')
#progress_printer = ProgressPrinter(freq=30, tag='Training', log_to_file=model_path_stem + ".log") # use this to log to file
sparse_to_dense = create_sparse_to_dense(input_vocab_dim)
for epoch in range(max_epochs):
print("Saving model to '%s'" % model_path(epoch))
s2smodel.save(model_path(epoch))
while total_samples < (epoch+1) * epoch_size:
# get next minibatch of training data
mb_train = train_reader.next_minibatch(minibatch_size)
#trainer.train_minibatch(mb_train[train_reader.streams.features], mb_train[train_reader.streams.labels])
trainer.train_minibatch({criterion.arguments[0]: mb_train[train_reader.streams.features], criterion.arguments[1]: mb_train[train_reader.streams.labels]})
progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
# every N MBs evaluate on a test sequence to visually show how we're doing
if mbs % eval_freq == 0:
mb_valid = valid_reader.next_minibatch(1)
# run an eval on the decoder output model (i.e. don't use the groundtruth)
e = model_greedy(mb_valid[valid_reader.streams.features])
print(format_sequences(sparse_to_dense(mb_valid[valid_reader.streams.features]), i2w))
print("->")
print(format_sequences(e, i2w))
# debugging attention
if use_attention:
debug_attention(model_greedy, mb_valid[valid_reader.streams.features])
total_samples += mb_train[train_reader.streams.labels].num_samples
mbs += 1
# log a summary of the stats for the epoch
progress_printer.epoch_summary(with_metric=True)
# done: save the final model
print("Saving final model to '%s'" % model_path(max_epochs))
s2smodel.save(model_path(max_epochs))
print("%d epochs complete." % max_epochs)
