def minibatch(self,
dataset,
subset,
use_datasets,
cache_data,
shift_ratio=-1):
if shift_ratio < 0:
shift_ratio = self.shift_ratio
with tf.name_scope('batch_processing'):
# Build final results per split.
images = [[] for _ in range(self.num_splits)]
labels = [[] for _ in range(self.num_splits)]
if use_datasets:
ds = data_utils.create_dataset(self.batch_size,
self.num_splits,
self.batch_size_per_split,
self.parse_and_preprocess,
dataset, subset, self.train,
cache_data)
ds_iterator = data_utils.create_iterator(ds)
for d in xrange(self.num_splits):
labels[d], images[d] = ds_iterator.get_next()
else:
record_input = data_flow_ops.RecordInput(
file_pattern=dataset.tf_record_pattern(subset),
seed=301,
parallelism=64,
buffer_size=10000,
batch_size=self.batch_size,
shift_ratio=shift_ratio,
name='record_input')
records = record_input.get_yield_op()
records = tf.split(records, self.batch_size, 0)
records = [tf.reshape(record, []) for record in records]
for idx in xrange(self.batch_size):
value = records[idx]
(label, image) = self.parse_and_preprocess(value, idx)
split_index = idx % self.num_splits
labels[split_index].append(label)
images[split_index].append(image)
for split_index in xrange(self.num_splits):
if not use_datasets:
images[split_index] = tf.parallel_stack(
images[split_index])
labels[split_index] = tf.concat(labels[split_index], 0)
images[split_index] = tf.reshape(images[split_index],
shape=[
self.batch_size_per_split,
self.height, self.width,
self.depth
])
labels[split_index] = tf.reshape(labels[split_index],
[self.batch_size_per_split])
return images, labels
def minibatch(self,
dataset,
subset,
use_datasets,
cache_data,
shift_ratio=-1):
if shift_ratio < 0:
shift_ratio = self.shift_ratio
self.example_decoder = tf_example_decoder.TfExampleDecoder()
with tf.name_scope('batch_processing'):
images = [[] for _ in range(self.num_splits)]
labels = [[] for _ in range(self.num_splits)]
glob_pattern = dataset.tf_record_pattern(subset)
filenames = gfile.Glob(glob_pattern)
ssd_input = ssd_dataloader.SSDInputReader(filenames,
subset == 'train')
ds = ssd_input({
'batch_size_per_split': self.batch_size_per_split,
'num_splits': self.num_splits
})
ds_iterator = data_utils.create_iterator(ds)
for d in range(self.num_splits):
images[d], labels[d] = ds_iterator.get_next()
for split_index in xrange(self.num_splits):
images[split_index] = tf.reshape(images[split_index],
shape=[
self.batch_size_per_split,
self.height, self.width,
self.depth
])
labels[split_index] = tf.reshape(
labels[split_index],
# Encoded tensor with object category, number of bounding boxes and
# their locations. The 0th dimension is batch size, and for each
# item in batch the tensor looks like this ((x, y, w, h) is the
# cordinates and size of a bounding box, c is class):
#
# [[x, y, w, h, c ], ^
# [x, y, w, h, c ], |
# [..., ..., ..., ..., ... ], NUM_SSD_BOXES+1
# [x, y, w, h, c ], |
# [nboxes, nboxes, nboxes, nboxes, nboxes]] v
#
# |<---------- 4 cordinates + 1 ---------->|
shape=[
self.batch_size_per_split,
ssd_constants.NUM_SSD_BOXES + 1, 5
])
return images, labels
def minibatch(self,
dataset,
subset,
use_datasets,
cache_data,
shift_ratio=-1):
try:
import ssd_dataloader # pylint: disable=g-import-not-at-top
except ImportError:
raise ImportError(
'To use the COCO dataset, you must clone the '
'repo https://github.com/tensorflow/models and add '
'tensorflow/models and tensorflow/models/research to '
'the PYTHONPATH, and compile the protobufs by '
'following https://github.com/tensorflow/models/blob/'
'master/research/object_detection/g3doc/installation.md'
'#protobuf-compilation')
if shift_ratio < 0:
shift_ratio = self.shift_ratio
with tf.name_scope('batch_processing'):
images = [[] for _ in range(self.num_splits)]
labels = [[] for _ in range(self.num_splits)]
glob_pattern = dataset.tf_record_pattern(subset)
filenames = gfile.Glob(glob_pattern)
ssd_input = ssd_dataloader.SSDInputReader(filenames,
subset == 'train')
ds = ssd_input({
'batch_size_per_split': self.batch_size_per_split,
'num_splits': self.num_splits
})
ds_iterator = data_utils.create_iterator(ds)
for d in range(self.num_splits):
images[d], labels[d] = ds_iterator.get_next()
for split_index in xrange(self.num_splits):
images[split_index] = tf.reshape(images[split_index],
shape=[
self.batch_size_per_split,
self.height, self.width,
self.depth
])
return images, labels
def minibatch(self,
dataset,
subset,
use_datasets,
cache_data,
shift_ratio=-1):
try:
from object_detection.data_decoders import tf_example_decoder # pylint: disable=g-import-not-at-top
import ssd_dataloader # pylint: disable=g-import-not-at-top
except ImportError:
raise ImportError(
'To use the COCO dataset, you must clone the '
'repo https://github.com/tensorflow/models and add '
'tensorflow/models and tensorflow/models/research to '
'the PYTHONPATH, and compile the protobufs by '
'following https://github.com/tensorflow/models/blob/'
'master/research/object_detection/g3doc/installation.md'
'#protobuf-compilation')
if shift_ratio < 0:
shift_ratio = self.shift_ratio
self.example_decoder = tf_example_decoder.TfExampleDecoder()
with tf.name_scope('batch_processing'):
images = [[] for _ in range(self.num_splits)]
labels = [[] for _ in range(self.num_splits)]
glob_pattern = dataset.tf_record_pattern(subset)
filenames = gfile.Glob(glob_pattern)
ssd_input = ssd_dataloader.SSDInputReader(filenames,
subset == 'train')
ds = ssd_input({
'batch_size_per_split': self.batch_size_per_split,
'num_splits': self.num_splits
})
ds_iterator = data_utils.create_iterator(ds)
for d in range(self.num_splits):
images[d], labels[d] = ds_iterator.get_next()
for split_index in xrange(self.num_splits):
images[split_index] = tf.reshape(images[split_index],
shape=[
self.batch_size_per_split,
self.height, self.width,
self.depth
])
labels[split_index] = tf.reshape(
labels[split_index],
# Encoded tensor with object category, number of bounding boxes and
# their locations. The 0th dimension is batch size, and for each
# item in batch the tensor looks like this ((x, y, w, h) is the
# cordinates and size of a bounding box, c is class):
#
# [[x, y, w, h, c ], ^
# [x, y, w, h, c ], |
# [..., ..., ..., ..., ... ], NUM_SSD_BOXES+1
# [x, y, w, h, c ], |
# [nboxes, nboxes, nboxes, nboxes, nboxes]] v
#
# |<---------- 4 cordinates + 1 ---------->|
shape=[
self.batch_size_per_split,
ssd_constants.NUM_SSD_BOXES + 1, 5
])
return images, labels
