updated some files to master copies
This commit is contained in:
Nikos Karampatziakis
Родитель
50b1510cfc
Коммит
9ee35dd057
|
|
@ -118,7 +118,7 @@ class MinibatchSource(cntk_py.MinibatchSource):
|
|||
the next minibatch. Must be > 0.
|
||||
minibatch_size_in_sequences (`int`, defaults to `None`): number of
|
||||
samples to retrieve for the next minibatch. Must be > 0.
|
||||
input_map (`dict`): mapping of :class:`cntk.ops.variables.Variable`
|
||||
input_map (`dict`): mapping of :class:`cntk.ops.variabls.Variable`
|
||||
to :class:`StreamInformation` which will be used to convert the
|
||||
returned data.
|
||||
device (`DeviceDescriptor`, defaults to `None`): CNTK DeviceDescriptor
|
||||
|
|
@ -126,7 +126,7 @@ class MinibatchSource(cntk_py.MinibatchSource):
|
|||
Returns:
|
||||
A mapping of :class:`StramInformation` to :class:`MinibatchData` if
|
||||
``input_map`` was not specified. Otherwise, the returned value will
|
||||
be a mapping of :class:`cntk.ops.variables.Variable` to class:`MinibatchData`.
|
||||
be a mapping of :class:`cntk.ops.variabls.Variable` to class:`MinibatchData`.
|
||||
'''
|
||||
if device is None:
|
||||
device = use_default_device()
|
||||
|
|
@ -223,8 +223,7 @@ class ReaderConfig(dict):
|
|||
deserializers ('list', default is empty): list of deserializers
|
||||
(:class:`ImageDeserializer` for now).
|
||||
randomize (`bool`, default True): randomize images before every epoch
|
||||
epoch_size (`int`): epoch size. FULL_DATA_SWEEP means one pass;
|
||||
INFINITELY_REPEAT means duplicate infinitely (with different randomization each time).
|
||||
epoch_size (`int`): epoch size
|
||||
'''
|
||||
|
||||
def __init__(self, deserializers=None, randomize=True, epoch_size=INFINITELY_REPEAT):
|
||||
|
|
@ -235,7 +234,6 @@ class ReaderConfig(dict):
|
|||
self['deserializers'] = self.deserializers = deserializers or []
|
||||
self['randomize'] = randomize
|
||||
|
||||
# TODO: This should be deleted; do it the other way round and create MinibatchSource() directly with the same parameter
|
||||
@typemap
|
||||
def minibatch_source(self):
|
||||
'''
|
||||
|
|
@ -417,9 +415,9 @@ class ImageDeserializer(Deserializer):
|
|||
class CTFDeserializer(Deserializer):
|
||||
'''
|
||||
This class configures the text reader that reads text-encoded files from a file with lines of the form
|
||||
[Sequence_Id](Sample)+
|
||||
[Sequence_Id](Sample)+
|
||||
where
|
||||
Sample=|Input_Name (Value )*
|
||||
Sample=|Input_Name (Value )*
|
||||
Args:
|
||||
filename (`str`): file name containing the text input
|
||||
See also:
|
||||
|
|
@ -440,17 +438,17 @@ class CTFDeserializer(Deserializer):
|
|||
# TODO: should be a private method; use constructor only
|
||||
def map_input(self, node, dim, format="dense", alias=None):
|
||||
'''
|
||||
Maps node (either node instance or node name) to a part of the text input,
|
||||
Maps node (either node instance or node name) to a part of the text input,
|
||||
either specified by the node name or the alias in the text file.
|
||||
Example: for node name 'Apples' an input line could look like this:
|
||||
|Apples 0 1 2 3 4 5 6 7 8 9
|
||||
Args:
|
||||
node (`str` or input node): node or its name
|
||||
dim (`int`): specifies the dimension of the input value vector
|
||||
(for dense input this directly corresponds to the number of values in each sample,
|
||||
dim (`int`): specifies the dimension of the input value vector
|
||||
(for dense input this directly corresponds to the number of values in each sample,
|
||||
for sparse this represents the upper bound on the range of possible index values).
|
||||
format (`str`, default 'dense'): 'dense' or 'sparse'. Specifies the input type.
|
||||
alias (`str`, default None): None or alias name. Optional abbreviated name that
|
||||
format (`str`, default 'dense'): 'dense' or 'sparse'. Specifies the input type.
|
||||
alias (`str`, default None): None or alias name. Optional abbreviated name that
|
||||
is used in the text file to avoid repeating long input names. For details please
|
||||
see https://github.com/Microsoft/CNTK/wiki/CNTKTextFormat-Reader
|
||||
'''
|
||||
|
|
@ -504,6 +502,22 @@ class StreamConfiguration(cntk_py.StreamConfiguration):
|
|||
return super(StreamConfiguration, self).__init__(name, dim, is_sparse, stream_alias)
|
||||
|
||||
|
||||
# wrapper around text_format_minibatch_source() that attaches a record of streams
|
||||
# TODO: This should not exist; use MinibatchSource(CTFDeserializer(...))
|
||||
def _unused_CNTKTextFormatMinibatchSource(path, streams, epoch_size=None): # TODO: delete this
|
||||
from cntk.utils import _ClassFromDict
|
||||
# convert streams into StreamConfiguration format
|
||||
# TODO: stream_alias should default to 'key'
|
||||
stream_configs = [ StreamConfiguration(key, dim=value.dim, is_sparse=value.is_sparse, stream_alias=value.stream_alias) for (key, value) in streams.items() ]
|
||||
if epoch_size is not None: # TODO: use MAX_UI64, now that we have access
|
||||
source = text_format_minibatch_source(path, stream_configs, epoch_size)
|
||||
else:
|
||||
source = text_format_minibatch_source(path, stream_configs)
|
||||
# attach a dictionary of the streams
|
||||
source.streams = _ClassFromDict({ name : source.stream_info(name) for name in streams.keys() })
|
||||
return source
|
||||
|
||||
|
||||
# stream definition for use in StreamDefs
|
||||
# returns a record { stream_alias, is_sparse, optional dim, optional transforms }
|
||||
from cntk.utils import Record
|
||||
|
|
|
|||
|
|
@ -147,7 +147,6 @@ class ProgressPrinter:
|
|||
else:
|
||||
print(' Minibatch[{:4d}-{:4d}]: loss = {:0.6f} * {:d}'.format(
|
||||
first_mb, self.updates, avg_loss, samples))
|
||||
return self.samples_since_start # so that we can trigger on this
|
||||
|
||||
def update_with_trainer(self, trainer, with_metric=False):
|
||||
'''
|
||||
|
|
@ -158,7 +157,7 @@ class ProgressPrinter:
|
|||
trainer (:class:`cntk.trainer.Trainer`): trainer from which information is gathered
|
||||
with_metric (`bool`): whether to update the metric accumulators
|
||||
'''
|
||||
self.update(trainer.previous_minibatch_loss_average, trainer.previous_minibatch_sample_count, trainer.previous_minibatch_evaluation_average if with_metric else None)
|
||||
self.update(trainer.previous_minibatch_loss_average,trainer.previous_minibatch_sample_count, trainer.previous_minibatch_evaluation_average if with_metric else None)
|
||||
|
||||
|
||||
# print the total number of parameters to log
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
<SchemaVersion>2.0</SchemaVersion>
|
||||
<ProjectGuid>{1a078fc2-21c0-4f42-9a5b-0e84e944bc74}</ProjectGuid>
|
||||
<ProjectHome />
|
||||
<StartupFile>CifarConvNet\CifarConvNet.py</StartupFile>
|
||||
<StartupFile>test\language_understanding_test.py</StartupFile>
|
||||
<SearchPath>$(RepoRootPath)$(Platform)\$(Configuration);$(RepoRootPath)bindings\python;$(RepoRootPath)bindings\python\examples</SearchPath>
|
||||
<WorkingDirectory>.</WorkingDirectory>
|
||||
<OutputPath>.</OutputPath>
|
||||
|
|
|
|||
|
|
@ -17,11 +17,9 @@ from cntk import Trainer
|
|||
from cntk.learner import momentum_sgd, learning_rate_schedule
|
||||
from cntk.ops import cross_entropy_with_softmax, classification_error, relu, convolution, pooling, PoolingType_Max
|
||||
|
||||
########################
|
||||
# variables and paths #
|
||||
########################
|
||||
|
||||
# paths (are relative to current python file)
|
||||
#
|
||||
# Paths relative to current python file.
|
||||
#
|
||||
abs_path = os.path.dirname(os.path.abspath(__file__))
|
||||
cntk_path = os.path.normpath(os.path.join(abs_path, "..", "..", "..", ".."))
|
||||
data_path = os.path.join(cntk_path, "Examples", "Image", "Datasets", "CIFAR-10")
|
||||
|
|
@ -44,9 +42,9 @@ def create_reader(map_file, mean_file, train):
|
|||
|
||||
# transformation pipeline for the features has jitter/crop only when training
|
||||
transforms = []
|
||||
if is_training:
|
||||
if train:
|
||||
transforms += [
|
||||
ImageDeserializer.crop(crop_type='Random', ratio=0.8, jitter_type='uniRatio') # is_training uses jitter
|
||||
ImageDeserializer.crop(crop_type='Random', ratio=0.8, jitter_type='uniRatio') # train uses jitter
|
||||
]
|
||||
transforms += [
|
||||
ImageDeserializer.scale(width=image_width, height=image_height, channels=num_channels, interpolations='linear'),
|
||||
|
|
@ -56,11 +54,7 @@ def create_reader(map_file, mean_file, train):
|
|||
return MinibatchSource(ImageDeserializer(map_file, StreamDefs(
|
||||
features = StreamDef(field='image', transforms=transforms), # first column in map file is referred to as 'image'
|
||||
labels = StreamDef(field='label', shape=num_classes) # and second as 'label'
|
||||
)), randomize=is_training, epoch_size = INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP)
|
||||
|
||||
########################
|
||||
# define the model #
|
||||
########################
|
||||
)))
|
||||
|
||||
#
|
||||
# Define a VGG like network for Cifar dataset.
|
||||
|
|
@ -122,12 +116,11 @@ def train_and_evaluate(reader_train, reader_test, max_epochs):
|
|||
|
||||
# loss and metric
|
||||
ce = cross_entropy_with_softmax(z, label_var)
|
||||
pe = classification_error (z, label_var)
|
||||
pe = classification_error(z, label_var)
|
||||
|
||||
# training config
|
||||
epoch_size = 50000
|
||||
minibatch_size = 64
|
||||
epoch_size = 1000 ; max_epochs = 1 # for faster testing
|
||||
|
||||
# For basic model
|
||||
lr_per_sample = [0.00015625]*10+[0.000046875]*10+[0.0000156]
|
||||
|
|
@ -147,8 +140,7 @@ def train_and_evaluate(reader_train, reader_test, max_epochs):
|
|||
}
|
||||
|
||||
log_number_of_parameters(z) ; print()
|
||||
progress_printer = ProgressPrinter(freq=100, first=10, tag='Training')
|
||||
#progress_printer = ProgressPrinter(tag='Training')
|
||||
progress_printer = ProgressPrinter(tag='Training')
|
||||
|
||||
# perform model training
|
||||
for epoch in range(max_epochs): # loop over epochs
|
||||
|
|
@ -159,14 +151,13 @@ def train_and_evaluate(reader_train, reader_test, max_epochs):
|
|||
|
||||
sample_count += data[label_var].num_samples # count samples processed so far
|
||||
progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
|
||||
loss, metric, actual_samples = progress_printer.epoch_summary(with_metric=True)
|
||||
|
||||
#return loss, metric # return values from last epoch
|
||||
|
||||
progress_printer.epoch_summary(with_metric=True)
|
||||
|
||||
#
|
||||
# Evaluation action
|
||||
#
|
||||
minibatch_size = 1000
|
||||
epoch_size = 10000
|
||||
minibatch_size = 16
|
||||
|
||||
# process minibatches and evaluate the model
|
||||
metric_numer = 0
|
||||
|
|
|
|||
|
|
@ -94,9 +94,10 @@ def create_resnet_model(input, num_classes):
|
|||
bn_time_const = 4096
|
||||
|
||||
c_map1 = 16
|
||||
|
||||
feat_scale = 0.00390625
|
||||
|
||||
# feat_scale = 0.00390625
|
||||
# input_norm = element_times(feat_scale, input)
|
||||
input_norm = element_times(feat_scale, input)
|
||||
|
||||
conv = conv_bn_relu_layer(input, c_map1, [3, 3], [1, 1], bn_time_const)
|
||||
r1_1 = resnet_basic_stack3(conv, c_map1, bn_time_const)
|
||||
|
|
|
|||
|
|
@ -10,16 +10,15 @@ from cntk.blocks import * # non-layer like building blocks such as LSTM()
|
|||
from cntk.layers import * # layer-like stuff such as Linear()
|
||||
from cntk.models import * # higher abstraction level, e.g. entire standard models and also operators like Sequential()
|
||||
from cntk.utils import *
|
||||
from cntk.io import MinibatchSource, CTFDeserializer, StreamDef, StreamDefs, INFINITELY_REPEAT, FULL_DATA_SWEEP
|
||||
from cntk.io import MinibatchSource, CTFDeserializer, StreamDef, StreamDefs
|
||||
from cntk import Trainer
|
||||
from cntk.learner import adam_sgd, learning_rate_schedule, momentum_schedule
|
||||
from cntk.ops import cross_entropy_with_softmax, classification_error
|
||||
|
||||
########################
|
||||
# variables and paths #
|
||||
# variables and stuff #
|
||||
########################
|
||||
|
||||
# paths
|
||||
cntk_dir = os.path.dirname(os.path.abspath(__file__)) + "/../../../.." # data resides in the CNTK folder
|
||||
data_dir = cntk_dir + "/Examples/Tutorials/SLUHandsOn" # under Examples/Tutorials
|
||||
vocab_size = 943 ; num_labels = 129 ; num_intents = 26 # number of words in vocab, slot labels, and intent labels
|
||||
|
|
@ -36,12 +35,12 @@ hidden_dim = 300
|
|||
# define the reader #
|
||||
########################
|
||||
|
||||
def create_reader(path, is_training):
|
||||
def create_reader(path):
|
||||
return MinibatchSource(CTFDeserializer(path, StreamDefs(
|
||||
query = StreamDef(field='S0', shape=input_dim, is_sparse=True),
|
||||
intent_unused = StreamDef(field='S1', shape=num_intents, is_sparse=True), # BUGBUG: unused, and should infer dim
|
||||
slot_labels = StreamDef(field='S2', shape=label_dim, is_sparse=True)
|
||||
)), randomize=is_training, epoch_size = INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP)
|
||||
)))
|
||||
|
||||
########################
|
||||
# define the model #
|
||||
|
|
@ -74,7 +73,6 @@ def train(reader, model, max_epochs):
|
|||
# training config
|
||||
epoch_size = 36000
|
||||
minibatch_size = 70
|
||||
epoch_size = 1000 ; max_epochs = 1 # for faster testing
|
||||
num_mbs_to_show_result = 100
|
||||
momentum_as_time_constant = minibatch_size / -math.log(0.9) # TODO: Change to round number. This is 664.39. 700?
|
||||
|
||||
|
|
@ -117,45 +115,6 @@ def train(reader, model, max_epochs):
|
|||
#trace_node('stabilizer_param')
|
||||
loss, metric, actual_samples = progress_printer.epoch_summary(with_metric=True)
|
||||
|
||||
return loss, metric # return values from last epoch
|
||||
|
||||
########################
|
||||
# eval action #
|
||||
########################
|
||||
|
||||
def evaluate(reader, model):
|
||||
# Input variables denoting the features and label data
|
||||
query = Input(input_dim, is_sparse=False)
|
||||
slot_labels = Input(num_labels, is_sparse=True) # TODO: make sparse once it works
|
||||
|
||||
# apply model to input
|
||||
z = model(query)
|
||||
|
||||
# loss and metric
|
||||
ce = cross_entropy_with_softmax(z, slot_labels)
|
||||
pe = classification_error (z, slot_labels)
|
||||
|
||||
# define mapping from reader streams to network inputs
|
||||
input_map = {
|
||||
query : reader.streams.query,
|
||||
slot_labels : reader.streams.slot_labels
|
||||
}
|
||||
|
||||
# process minibatches and perform evaluation
|
||||
dummy_learner = adam_sgd(z.parameters, lr_per_sample=1, momentum_time_constant=0, low_memory=True) # BUGBUG: should not be needed
|
||||
evaluator = Trainer(z, ce, pe, [dummy_learner])
|
||||
progress_printer = ProgressPrinter(freq=100, first=10, tag='Evaluation') # more detailed logging
|
||||
#progress_printer = ProgressPrinter(tag='Evaluation')
|
||||
|
||||
while True:
|
||||
minibatch_size = 1000
|
||||
data = reader.next_minibatch(minibatch_size, input_map=input_map) # fetch minibatch
|
||||
if not data: # until we hit the end
|
||||
break
|
||||
metric = evaluator.test_minibatch(data) # evaluate minibatch
|
||||
progress_printer.update(0, data[slot_labels].num_samples, metric) # log progress
|
||||
loss, metric, actual_samples = progress_printer.epoch_summary(with_metric=True)
|
||||
|
||||
return loss, metric
|
||||
|
||||
#############################
|
||||
|
|
@ -169,13 +128,10 @@ if __name__=='__main__':
|
|||
set_fixed_random_seed(1) # BUGBUG: has no effect at present # TODO: remove debugging facilities once this all works
|
||||
force_deterministic_algorithms()
|
||||
|
||||
# create the model
|
||||
reader = create_reader(data_dir + "/atis.train.ctf")
|
||||
model = create_model()
|
||||
|
||||
# train
|
||||
reader = create_reader(data_dir + "/atis.train.ctf", is_training=True)
|
||||
train(reader, model, max_epochs=8)
|
||||
|
||||
# test
|
||||
reader = create_reader(data_dir + "/atis.test.ctf", is_training=False)
|
||||
evaluate(reader, model)
|
||||
# test (TODO)
|
||||
reader = create_reader(data_dir + "/atis.test.ctf")
|
||||
#test(reader, model_dir + "/slu.cmf") # TODO: what is the correct pattern here?
|
||||
|
|
|
|||
|
|
@ -10,6 +10,7 @@ import sys
|
|||
from cntk.utils import cntk_device
|
||||
from cntk.cntk_py import DeviceKind_GPU
|
||||
from cntk.device import set_default_device
|
||||
from cntk.io import ReaderConfig, ImageDeserializer
|
||||
import pytest
|
||||
|
||||
from examples.CifarResNet.CifarResNet import train_and_evaluate, create_reader
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ def test_seq_classification_error(device_id):
|
|||
|
||||
# test of the example itself
|
||||
# this emulates the main code in the PY file
|
||||
reader = create_reader(data_dir + "/atis.train.ctf", is_training=True)
|
||||
reader = create_reader(data_dir + "/atis.train.ctf")
|
||||
model = create_model()
|
||||
loss_avg, evaluation_avg = train(reader, model, max_epochs=1)
|
||||
expected_avg = [0.15570838301766451, 0.7846451368305728]
|
||||
|
|
@ -45,7 +45,7 @@ def test_seq_classification_error(device_id):
|
|||
|
||||
# test of a config like in the example but with additions to test many code paths
|
||||
if device_id >= 0: # BatchNormalization currently does not run on CPU
|
||||
reader = create_reader(data_dir + "/atis.train.ctf", is_training=True)
|
||||
reader = create_reader(data_dir + "/atis.train.ctf")
|
||||
model = create_test_model()
|
||||
loss_avg, evaluation_avg = train(reader, model, max_epochs=1)
|
||||
log_number_of_parameters(model, trace_level=1) ; print()
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче