def ptb_producer(raw_data, batch_size, num_steps, name=None):
with tf.name_scope(name, "PTBProducer", [raw_data, batch_size, num_steps]):
raw_data = tf.convert_to_tensor(raw_data, name="raw_data", dtype=tf.int32)
data_len = tf.size(raw_data)
batch_len = data_len // batch_size
data = tf.reshape(raw_data[0 : batch_size * batch_len],
[batch_size, batch_len])
epoch_size = (batch_len - 1) // num_steps
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(data, [0, i * num_steps],
[batch_size, (i + 1) * num_steps],
#tf.ones_like([0, i * num_steps]))
[1,1])
x.set_shape([batch_size, num_steps])
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1],
#tf.ones_like([0, i * num_steps]))
[1,1])
y.set_shape([batch_size, num_steps])
return x, y
python类strided_slice()的实例源码
def decode(self, memories, keys, num_keys=None):
keys = self._normalize(keys)
num_memories = memories.get_shape().as_list()
num_memories[0] = self.num_models if num_memories[0] is None else num_memories[0]
num_keys = keys.get_shape().as_list()[0] if num_keys is None else num_keys
print 'decode: numkeys = ', num_keys, ' | num_memories = ', num_memories
# re-gather keys to avoid mixing between different keys.
perms = self.perm_keys(keys, self.perms, num_keys=num_keys)
pshp = perms.get_shape().as_list()
pshp[0] = num_keys*self.num_models if pshp[0] is None else pshp[0]
pshp[1] = num_memories[1] if pshp[1] is None else pshp[1]
permed_keys = tf.concat(0, [tf.strided_slice(perms, [i, 0], pshp, [num_keys, 1])
for i in range(num_keys)])
print 'memories = ', num_memories, \
'| dec_perms =', permed_keys.get_shape().as_list()
return self.conv_func(memories, permed_keys,
num_memories[0],
self.num_models,
num_keys=num_keys*self.num_models,
conj=True)
def __init__(self, cfg, data, name):
self.steps = ((len(data) // cfg.batch_size) - 1) // cfg.num_steps
with tf.name_scope(name, values=[data, cfg.batch_size, cfg.num_steps]):
raw_data = tf.convert_to_tensor(data)
data_len = tf.size(raw_data)
batch_len = data_len // cfg.batch_size
data = tf.reshape(raw_data[0: cfg.batch_size * batch_len], [cfg.batch_size, batch_len])
epoch_size = (batch_len - 1) // cfg.num_steps
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
begin_x = [0, i * cfg.num_steps]
self.inputs = tf.strided_slice(
data, begin_x, [cfg.batch_size, (i + 1) * cfg.num_steps], tf.ones_like(begin_x))
self.inputs.set_shape([cfg.batch_size, cfg.num_steps])
begin_y = [0, i * cfg.num_steps + 1]
self.targets = tf.strided_slice(
data, begin_y, [cfg.batch_size, (i + 1) * cfg.num_steps + 1], tf.ones_like(begin_y))
self.targets.set_shape([cfg.batch_size, cfg.num_steps])
def process_decoder_input(target_data, target_vocab_to_int, batch_size):
# Take off the last column
sliced = tf.strided_slice(target_data, [0, 0], [batch_size, -1], [1, 1])
# Append a column filled with <GO>
decoder_input = tf.concat([tf.fill([batch_size, 1], target_vocab_to_int['<GO>']), sliced], 1)
return decoder_input
def StridedSlice_FwGrad(op, dx, dy, dz, du, _op_table=None, _grad_table=None):
if dx is None:
return None
y = op.inputs[1]
z = op.inputs[2]
u = op.inputs[3]
return tf.strided_slice(dx, begin=y, end=z, strides=u)
###############################################################################
# Element-wise operators. elemwise.
###############################################################################
process_inputs.py 文件源码
项目：language-translation-english-to-french
作者: Satyaki0924
项目源码
文件源码
阅读 25
收藏 0
点赞 0
评论 0
def process_decoding_input(target_data, target_vocab_to_int, batch_size):
l_word = tf.strided_slice(target_data, [0, 0], [batch_size, -1], [1, 1])
return tf.concat([tf.fill([batch_size, 1], target_vocab_to_int['<GO>']), l_word], 1)
def unit_norm(inputs, dim, epsilon=1e-7, scope=None):
"""Normalizes the given input across the specified dimension to unit length.
Note that the rank of `input` must be known.
Args:
inputs: A `Tensor` of arbitrary size.
dim: The dimension along which the input is normalized.
epsilon: A small value to add to the inputs to avoid dividing by zero.
scope: Optional scope for variable_scope.
Returns:
The normalized `Tensor`.
Raises:
ValueError: If dim is larger than the number of dimensions in 'inputs'.
"""
with tf.variable_scope(scope, 'UnitNorm', [inputs]):
if not inputs.get_shape():
raise ValueError('The input rank must be known.')
input_rank = len(inputs.get_shape().as_list())
if dim < 0 or dim >= input_rank:
raise ValueError(
'dim must be positive but smaller than the input rank.')
lengths = tf.sqrt(
epsilon + tf.reduce_sum(tf.square(inputs), dim, True))
multiples = []
if dim > 0:
multiples.append(tf.ones([dim], tf.int32))
multiples.append(tf.strided_slice(
tf.shape(inputs), [dim], [dim + 1], [1]))
if dim < (input_rank - 1):
multiples.append(tf.ones([input_rank - 1 - dim], tf.int32))
multiples = tf.concat(multiples, 0)
return tf.div(inputs, tf.tile(lengths, multiples))
def call(self, data, mask=None):
tmp1 = tf.strided_slice(data,[0,0,0,0],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
tmp2 = tf.strided_slice(data,[0,0,0,1],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
tmp3 = tf.strided_slice(data,[0,0,1,0],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
tmp4 = tf.strided_slice(data,[0,0,1,1],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
if int(tf.__version__[0]) < 1:
return tf.concat(1,[tmp1, tmp2, tmp3, tmp4])
else:
return tf.concat([tmp1, tmp2, tmp3, tmp4],1)
def ptb_producer(raw_data, batch_size, num_steps, name=None):
"""Iterate on the raw PTB data.
This chunks up raw_data into batches of examples and returns Tensors that
are drawn from these batches.
Args:
raw_data: one of the raw data outputs from ptb_raw_data.
batch_size: int, the batch size.
num_steps: int, the number of unrolls.
name: the name of this operation (optional).
Returns:
A pair of Tensors, each shaped [batch_size, num_steps]. The second element
of the tuple is the same data time-shifted to the right by one.
Raises:
tf.errors.InvalidArgumentError: if batch_size or num_steps are too high.
"""
with tf.name_scope(name, "PTBProducer", [raw_data, batch_size, num_steps]):
raw_data = tf.convert_to_tensor(raw_data, name="raw_data", dtype=tf.int32)
data_len = tf.size(raw_data)
batch_len = data_len // batch_size
data = tf.reshape(raw_data[0 : batch_size * batch_len],
[batch_size, batch_len])
epoch_size = (batch_len - 1) // num_steps
assertion = tf.assert_positive(
epoch_size,
message="epoch_size == 0, decrease batch_size or num_steps")
with tf.control_dependencies([assertion]):
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(data, [0, i * num_steps],
[batch_size, (i + 1) * num_steps])
x.set_shape([batch_size, num_steps])
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1])
y.set_shape([batch_size, num_steps])
return x, y
def call(self, data, mask=None):
tmp1 = tf.strided_slice(data,[0,0,0,0],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
tmp2 = tf.strided_slice(data,[0,0,0,1],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
tmp3 = tf.strided_slice(data,[0,0,1,0],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
tmp4 = tf.strided_slice(data,[0,0,1,1],[1024,tf.to_int32(data.get_shape()[1]),tf.to_int32(data.get_shape()[2]),tf.to_int32(data.get_shape()[3])],[1,1,2,2])
if int(tf.__version__[0]) < 1:
return tf.concat(1,[tmp1, tmp2, tmp3, tmp4])
else:
return tf.concat([tmp1, tmp2, tmp3, tmp4],1)
def _crop(image, offset_height, offset_width, crop_height, crop_width):
"""Crops the given image using the provided offsets and sizes.
Note that the method doesn't assume we know the input image size but it does
assume we know the input image rank.
Args:
image: an image of shape [height, width, channels].
offset_height: a scalar tensor indicating the height offset.
offset_width: a scalar tensor indicating the width offset.
crop_height: the height of the cropped image.
crop_width: the width of the cropped image.
Returns:
the cropped (and resized) image.
Raises:
InvalidArgumentError: if the rank is not 3 or if the image dimensions are
less than the crop size.
"""
original_shape = tf.shape(image)
rank_assertion = tf.Assert(
tf.equal(tf.rank(image), 3),
['Rank of image must be equal to 3.'])
with tf.control_dependencies([rank_assertion]):
cropped_shape = tf.stack([crop_height, crop_width, original_shape[2]])
size_assertion = tf.Assert(
tf.logical_and(
tf.greater_equal(original_shape[0], crop_height),
tf.greater_equal(original_shape[1], crop_width)),
['Crop size greater than the image size.'])
offsets = tf.to_int32(tf.stack([offset_height, offset_width, 0]))
# Use tf.strided_slice instead of crop_to_bounding box as it accepts tensors
# to define the crop size.
with tf.control_dependencies([size_assertion]):
image = tf.strided_slice(image, offsets, offsets + cropped_shape,
strides=tf.ones_like(offsets))
return tf.reshape(image, cropped_shape)
def __init__(self, config):
self.config = config
tf.reset_default_graph()
self.X1 = tf.placeholder(tf.int32, name='X1', shape=(None, config['data1_maxlen']))
self.X2 = tf.placeholder(tf.int32, name='X2', shape=(None, config['data2_maxlen']))
self.X1_len = tf.placeholder(tf.int32, name='X1_len', shape=(None, ))
self.X2_len = tf.placeholder(tf.int32, name='X2_len', shape=(None, ))
self.Y = tf.placeholder(tf.int32, name='Y', shape=(None, ))
self.F = tf.placeholder(tf.float32, name='F', shape=(None, config['feat_size']))
self.dpool_index = tf.placeholder(tf.int32, name='dpool_index', shape=(None, config['data1_maxlen'], config['data2_maxlen'], 3))
self.batch_size = tf.shape(self.X1)[0]
self.embedding = tf.get_variable('embedding', initializer = config['embedding'], dtype=tf.float32, trainable=False)
self.embed1 = tf.nn.embedding_lookup(self.embedding, self.X1)
self.embed2 = tf.nn.embedding_lookup(self.embedding, self.X2)
# batch_size * X1_maxlen * X2_maxlen
self.cross = tf.einsum('abd,acd->abc', self.embed1, self.embed2)
self.cross_img = tf.expand_dims(self.cross, 3)
# convolution
self.w1 = tf.get_variable('w1', initializer=tf.truncated_normal_initializer(mean=0.0, stddev=0.2, dtype=tf.float32) , dtype=tf.float32, shape=[2, 10, 1, 8])
self.b1 = tf.get_variable('b1', initializer=tf.constant_initializer() , dtype=tf.float32, shape=[8])
# batch_size * X1_maxlen * X2_maxlen * feat_out
self.conv1 = tf.nn.relu(tf.nn.conv2d(self.cross_img, self.w1, [1, 1, 1, 1], "SAME") + self.b1)
# dynamic pooling
self.conv1_expand = tf.gather_nd(self.conv1, self.dpool_index)
self.pool1 = tf.nn.max_pool(self.conv1_expand,
[1, config['data1_maxlen'] / config['data1_psize'], config['data2_maxlen'] / config['data2_psize'], 1],
[1, config['data1_maxlen'] / config['data1_psize'], config['data2_maxlen'] / config['data2_psize'], 1], "VALID")
with tf.variable_scope('fc1'):
self.fc1 = tf.nn.relu(tf.contrib.layers.linear(tf.reshape(self.pool1, [self.batch_size, config['data1_psize'] * config['data2_psize'] * 8]), 20))
self.pred = tf.contrib.layers.linear(self.fc1, 1)
pos = tf.strided_slice(self.pred, [0], [self.batch_size], [2])
neg = tf.strided_slice(self.pred, [1], [self.batch_size], [2])
self.loss = tf.reduce_mean(tf.maximum(1.0 + neg - pos, 0.0))
self.train_model = tf.train.AdamOptimizer().minimize(self.loss)
self.saver = tf.train.Saver(max_to_keep=20)
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def ptb_producer(raw_data, batch_size, num_steps, name=None):
"""Iterate on the raw PTB data.
This chunks up raw_data into batches of examples and returns Tensors that
are drawn from these batches.
Args:
raw_data: one of the raw data outputs from ptb_raw_data.
batch_size: int, the batch size.
num_steps: int, the number of unrolls.
name: the name of this operation (optional).
Returns:
A pair of Tensors, each shaped [batch_size, num_steps]. The second element
of the tuple is the same data time-shifted to the right by one.
Raises:
tf.errors.InvalidArgumentError: if batch_size or num_steps are too high.
"""
with tf.name_scope(name, "PTBProducer", [raw_data, batch_size, num_steps]):
raw_data = tf.convert_to_tensor(raw_data, name="raw_data", dtype=tf.int32)
data_len = tf.size(raw_data)
batch_len = data_len // batch_size
data = tf.reshape(raw_data[0 : batch_size * batch_len],
[batch_size, batch_len])
epoch_size = (batch_len - 1) // num_steps
assertion = tf.assert_positive(
epoch_size,
message="epoch_size == 0, decrease batch_size or num_steps")
with tf.control_dependencies([assertion]):
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(data, [0, i * num_steps],
[batch_size, (i + 1) * num_steps])
x.set_shape([batch_size, num_steps])
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1])
y.set_shape([batch_size, num_steps])
return x, y
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def batch_producer(enc, dec, batch_size, name=None):
data_len = enc.shape[0]
seq_len = enc.shape[1]
epoch_size = data_len // batch_size
print("epoch size: %d " % epoch_size)
with tf.name_scope(name, "batch", [enc, dec, batch_size]):
enc = tf.convert_to_tensor(enc, name="enc", dtype=tf.float32)
dec = tf.convert_to_tensor(dec, name="dec", dtype=tf.int32)
# generator
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(enc, [0, 0, 0],
[batch_size, seq_len, 2],
[1, 1, 1])
x.set_shape([batch_size, seq_len, 2 ])
y = tf.strided_slice(dec, [0, 0],
[batch_size, seq_len],
[1, 1])
y.set_shape([batch_size, seq_len])
return x, y
# for test
#if __name__ == "__main__":
# enc_in, dec_out = _load_data("./convex_hull_50_train.txt")
# print(enc_in.shape)
# print(dec_out.shape)
# #print(enc_in)
# x_batch, y_batch = batch_producer(enc_in, dec_out, batch_size=20)
# with tf.Session() as sess:
# coord = tf.train.Coordinator()
# threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# print(sess.run([x_batch, y_batch]))
# coord.request_stop()
# coord.join(threads)
# ====================
# visualization
# ====================
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def read_data(file_q):
# Code from https://github.com/tensorflow/models/blob/master/tutorials/image/cifar10/cifar10_input.py
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(file_q)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
reshaped_image = tf.cast(result.uint8image, tf.float32)
height = 24
width = 24
# Image processing for evaluation.
# Crop the central [height, width] of the image.
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
height, width)
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_standardization(resized_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
result.label.set_shape([1])
return float_image, result.label
cifar10_input.py 文件源码
项目：visual-interaction-networks_tensorflow
作者: jaesik817
项目源码
文件源码
阅读 34
收藏 0
点赞 0
评论 0
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def ptb_producer(raw_data, batch_size, num_steps, name=None):
"""Iterate on the raw PTB data.
This chunks up raw_data into batches of examples and returns Tensors that
are drawn from these batches.
Args:
raw_data: one of the raw data outputs from ptb_raw_data.
batch_size: int, the batch size.
num_steps: int, the number of unrolls.
name: the name of this operation (optional).
Returns:
A pair of Tensors, each shaped [batch_size, num_steps]. The second element
of the tuple is the same data time-shifted to the right by one.
Raises:
tf.errors.InvalidArgumentError: if batch_size or num_steps are too high.
"""
with tf.name_scope(name, "PTBProducer", [raw_data, batch_size, num_steps]):
raw_data = tf.convert_to_tensor(raw_data, name="raw_data", dtype=tf.int32)
data_len = tf.size(raw_data)
batch_len = data_len // batch_size
data = tf.reshape(raw_data[0: batch_size * batch_len],
[batch_size, batch_len])
epoch_size = (batch_len - 1) // num_steps
assertion = tf.assert_positive(
epoch_size,
message="epoch_size == 0, decrease batch_size or num_steps")
with tf.control_dependencies([assertion]):
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(data, [0, i * num_steps],
[batch_size, (i + 1) * num_steps])
x.set_shape([batch_size, num_steps])
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1])
y.set_shape([batch_size, num_steps])
return x, y
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def gather(self, src, force_copy=False):
"""Fetches the data corresponding to ``src`` from the base array.
Parameters
----------
src : :class:`.TensorSignal`
Signal indicating the data to be read from base array
force_copy : bool, optional
If True, always perform a gather, not a slice (this forces a
copy). Note that setting ``force_copy=False`` does not guarantee
that a copy won't be performed.
Returns
-------
``tf.Tensor``
Tensor object corresponding to a dense subset of data from the
base array
"""
if src.tf_indices is None:
raise BuildError("Indices for %s have not been loaded into "
"TensorFlow" % src)
logger.debug("gather")
logger.debug("src %s", src)
logger.debug("indices %s", src.indices)
logger.debug("src base %s", self.bases[src.key])
var = self.bases[src.key]
# we prefer to get the data via `strided_slice` or `identity` if
# possible, as it is more efficient
if force_copy or src.as_slice is None:
result = tf.gather(var, src.tf_indices)
elif (src.indices[0] == 0 and
src.indices[-1] == var.get_shape()[0].value - 1 and
len(src.indices) == var.get_shape()[0]):
result = var
else:
result = tf.strided_slice(var, *src.as_slice)
# for some reason the shape inference doesn't work in some cases
result.set_shape(src.tf_indices.get_shape()[:1].concatenate(
var.get_shape()[1:]))
# reshape the data according to the shape set in `src`, if there is
# one, otherwise keep the shape of the base array
if result.get_shape() != src.full_shape:
result = tf.reshape(result, src.tf_shape)
result.set_shape(src.full_shape)
# whenever we read from an array we use this to mark it as "read"
# (so that any future writes to the array will be scheduled after
# the read)
self.mark_gather(src)
return result
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def ptb_producer(raw_data, batch_size, num_steps, name=None):
"""Iterate on the raw PTB data.
This chunks up raw_data into batches of examples and returns Tensors that
are drawn from these batches.
Args:
raw_data: one of the raw data outputs from ptb_raw_data.
batch_size: int, the batch size.
num_steps: int, the number of unrolls.
name: the name of this operation (optional).
Returns:
A pair of Tensors, each shaped [batch_size, num_steps]. The second element
of the tuple is the same data time-shifted to the right by one.
Raises:
tf.errors.InvalidArgumentError: if batch_size or num_steps are too high.
"""
with tf.name_scope(name, "PTBProducer", [raw_data, batch_size, num_steps]):
raw_data = tf.convert_to_tensor(raw_data, name="raw_data", dtype=tf.int32)
data_len = tf.size(raw_data)
batch_len = data_len // batch_size
data = tf.reshape(raw_data[0 : batch_size * batch_len],
[batch_size, batch_len])
epoch_size = (batch_len - 1) // num_steps
assertion = tf.assert_positive(
epoch_size,
message="epoch_size == 0, decrease batch_size or num_steps")
with tf.control_dependencies([assertion]):
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(data, [0, i * num_steps],
[batch_size, (i + 1) * num_steps])
x.set_shape([batch_size, num_steps])
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1])
y.set_shape([batch_size, num_steps])
return x, y
def resnet_atrous_conv(x, channels, size=3, padding='SAME', stride=1, hole=1, batch_norm=False,
phase_test=None, activation=tf.nn.relu, name=None,
parameter_name=None, bn_name=None, scale_name=None, summarize_scale=False, info=DummyDict(), parameters={},
pre_adjust_batch_norm=False):
if parameter_name is None:
parameter_name = name
if scale_name is None:
scale_name = parameter_name
with tf.name_scope(name):
features = int(x.get_shape()[3])
f = channels
shape = [size, size, features, f]
W_init, W_shape = _pretrained_resnet_conv_weights_initializer(parameter_name, parameters,
info=info.get('init'),
pre_adjust_batch_norm=pre_adjust_batch_norm,
bn_name=bn_name, scale_name=scale_name)
b_init, b_shape = _pretrained_resnet_biases_initializer(scale_name, parameters,
info=info.get('init'),
pre_adjust_batch_norm=pre_adjust_batch_norm,
bn_name=bn_name)
assert W_shape is None or tuple(W_shape) == tuple(shape), "Incorrect weights shape for {} (file: {}, spec: {})".format(name, W_shape, shape)
assert b_shape is None or tuple(b_shape) == (f,), "Incorrect bias shape for {} (file: {}, spec; {})".format(name, b_shape, (f,))
with tf.variable_scope(name):
W = tf.get_variable('weights', shape, dtype=tf.float32,
initializer=W_init)
b = tf.get_variable('biases', [f], dtype=tf.float32,
initializer=b_init)
if hole == 1:
raw_conv0 = tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding=padding)
else:
assert stride == 1
raw_conv0 = tf.nn.atrous_conv2d(x, W, rate=hole, padding=padding)
#conv0 = tf.nn.conv2d(x, W, strides=[1, stride, stride, 1], padding=padding)
if stride > 1:
conv0 = tf.strided_slice(raw_conv0, [0, 0, 0, 0], raw_conv0.get_shape(), [1, stride, stride, 1])
else:
conv0 = raw_conv0
h1 = tf.reshape(tf.nn.bias_add(conv0, b), conv0.get_shape())
z = h1
if activation is not None:
z = activation(z)
if info.get('scale_summary'):
with tf.name_scope('activation'):
tf.summary.scalar('activation/' + name, tf.sqrt(tf.reduce_mean(z**2)))
info['activations'][name] = z
return z
def ptb_producer(raw_data, batch_size, num_steps, name=None):
"""Iterate on the raw PTB data.
This chunks up raw_data into batches of examples and returns Tensors that
are drawn from these batches.
Args:
raw_data: one of the raw data outputs from ptb_raw_data.
batch_size: int, the batch size.
num_steps: int, the number of unrolls.
name: the name of this operation (optional).
Returns:
A pair of Tensors, each shaped [batch_size, num_steps]. The second element
of the tuple is the same data time-shifted to the right by one.
Raises:
tf.errors.InvalidArgumentError: if batch_size or num_steps are too high.
"""
with tf.name_scope(name, "PTBProducer", [raw_data, batch_size, num_steps]):
raw_data = tf.convert_to_tensor(raw_data, name="raw_data", dtype=tf.int32)
data_len = tf.size(raw_data)
batch_len = data_len // batch_size
data = tf.reshape(raw_data[0: batch_size * batch_len],
[batch_size, batch_len])
epoch_size = (batch_len - 1) // num_steps
assertion = tf.assert_positive(
epoch_size,
message="epoch_size == 0, decrease batch_size or num_steps")
with tf.control_dependencies([assertion]):
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(data, [0, i * num_steps],
[batch_size, (i + 1) * num_steps])
x.set_shape([batch_size, num_steps])
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1])
y.set_shape([batch_size, num_steps])
return x, y
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
def ptb_producer(raw_data, batch_size, num_steps, name=None):
"""Iterate on the raw PTB data.
This chunks up raw_data into batches of examples and returns Tensors that
are drawn from these batches.
Args:
raw_data: one of the raw data outputs from ptb_raw_data.
batch_size: int, the batch size.
num_steps: int, the number of unrolls.
name: the name of this operation (optional).
Returns:
A pair of Tensors, each shaped [batch_size, num_steps]. The second element
of the tuple is the same data time-shifted to the right by one.
Raises:
tf.errors.InvalidArgumentError: if batch_size or num_steps are too high.
"""
with tf.name_scope(name, "PTBProducer", [raw_data, batch_size, num_steps]):
raw_data = tf.convert_to_tensor(raw_data, name="raw_data", dtype=tf.int32)
data_len = tf.size(raw_data)
batch_len = data_len // batch_size
data = tf.reshape(raw_data[0 : batch_size * batch_len],
[batch_size, batch_len])
epoch_size = (batch_len - 1) // num_steps
assertion = tf.assert_positive(
epoch_size,
message="epoch_size == 0, decrease batch_size or num_steps")
with tf.control_dependencies([assertion]):
epoch_size = tf.identity(epoch_size, name="epoch_size")
i = tf.train.range_input_producer(epoch_size, shuffle=False).dequeue()
x = tf.strided_slice(data, [0, i * num_steps],
[batch_size, (i + 1) * num_steps])
x.set_shape([batch_size, num_steps])
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1])
y.set_shape([batch_size, num_steps])
return x, y
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
