def testForwardpassDeepLabv3plus(self):
crop_size = [33, 33]
outputs_to_num_classes = {'semantic': 3}
model_options = common.ModelOptions(
outputs_to_num_classes, crop_size,
output_stride=16)._replace(add_image_level_feature=True,
aspp_with_batch_norm=True,
logits_kernel_size=1,
model_variant='mobilenet_v2'
) # Employ MobileNetv2 for fast test.
g = tf.Graph()
with g.as_default():
with self.test_session(graph=g) as sess:
inputs = tf.random_uniform((1, crop_size[0], crop_size[1], 3))
outputs_to_scales_to_logits = model.multi_scale_logits(
inputs, model_options, image_pyramid=[1.0])
sess.run(tf.global_variables_initializer())
outputs_to_scales_to_logits = sess.run(
outputs_to_scales_to_logits)
# Check computed results for each output type.
for output in outputs_to_num_classes:
scales_to_logits = outputs_to_scales_to_logits[output]
# Expect only one output.
self.assertEquals(len(scales_to_logits), 1)
for logits in scales_to_logits.values():
self.assertTrue(logits.any())
def main(unused_argv):
tf.logging.set_verbosity(tf.logging.INFO)
tf.logging.info('Prepare to export model to: %s', FLAGS.export_path)
with tf.Graph().as_default():
image, image_size, resized_image_size = _create_input_tensors()
model_options = common.ModelOptions(
outputs_to_num_classes={common.OUTPUT_TYPE: FLAGS.num_classes},
crop_size=FLAGS.crop_size,
atrous_rates=FLAGS.atrous_rates,
output_stride=FLAGS.output_stride)
if tuple(FLAGS.inference_scales) == (1.0, ):
tf.logging.info('Exported model performs single-scale inference.')
predictions = model.predict_labels(
image,
model_options=model_options,
image_pyramid=FLAGS.image_pyramid)
else:
tf.logging.info('Exported model performs multi-scale inference.')
predictions = model.predict_labels_multi_scale(
image,
model_options=model_options,
eval_scales=FLAGS.inference_scales,
add_flipped_images=FLAGS.add_flipped_images)
# Crop the valid regions from the predictions.
semantic_predictions = tf.slice(
predictions[common.OUTPUT_TYPE], [0, 0, 0],
[1, resized_image_size[0], resized_image_size[1]])
# Resize back the prediction to the original image size.
def _resize_label(label, label_size):
# Expand dimension of label to [1, height, width, 1] for resize operation.
label = tf.expand_dims(label, 3)
resized_label = tf.image.resize_images(
label,
label_size,
method=tf.image.ResizeMethod.NEAREST_NEIGHBOR,
align_corners=True)
return tf.squeeze(resized_label, 3)
semantic_predictions = _resize_label(semantic_predictions, image_size)
semantic_predictions = tf.identity(semantic_predictions,
name=_OUTPUT_NAME)
saver = tf.train.Saver(tf.model_variables())
tf.gfile.MakeDirs(os.path.dirname(FLAGS.export_path))
freeze_graph.freeze_graph_with_def_protos(
tf.get_default_graph().as_graph_def(add_shapes=True),
saver.as_saver_def(),
FLAGS.checkpoint_path,
_OUTPUT_NAME,
restore_op_name=None,
filename_tensor_name=None,
output_graph=FLAGS.export_path,
clear_devices=True,
initializer_nodes=None)
def _build_deeplab(inputs_queue, outputs_to_num_classes, ignore_label):
"""Builds a clone of DeepLab.
Args:
inputs_queue: A prefetch queue for images and labels.
outputs_to_num_classes: A map from output type to the number of classes.
For example, for the task of semantic segmentation with 21 semantic
classes, we would have outputs_to_num_classes['semantic'] = 21.
ignore_label: Ignore label.
Returns:
A map of maps from output_type (e.g., semantic prediction) to a
dictionary of multi-scale logits names to logits. For each output_type,
the dictionary has keys which correspond to the scales and values which
correspond to the logits. For example, if `scales` equals [1.0, 1.5],
then the keys would include 'merged_logits', 'logits_1.00' and
'logits_1.50'.
"""
samples = inputs_queue.dequeue()
# add name to input and label nodes so we can add to summary
samples[common.IMAGE] = tf.identity(samples[common.IMAGE], name = common.IMAGE)
samples[common.LABEL] = tf.identity(samples[common.LABEL], name = common.LABEL)
model_options = common.ModelOptions(
outputs_to_num_classes=outputs_to_num_classes,
atrous_rates=FLAGS.atrous_rates,
output_stride=FLAGS.output_stride)
outputs_to_scales_to_logits = model.multi_scale_logits(
samples[common.IMAGE],
model_options=model_options,
weight_decay=FLAGS.weight_decay,
is_training=True,
fine_tune_batch_norm=FLAGS.fine_tune_batch_norm)
# add name to graph node so we can add to summary
outputs_to_scales_to_logits[common.OUTPUT_TYPE][model._MERGED_LOGITS_SCOPE] = tf.identity(
outputs_to_scales_to_logits[common.OUTPUT_TYPE][model._MERGED_LOGITS_SCOPE],
name = common.OUTPUT_TYPE
)
for output, num_classes in six.iteritems(outputs_to_num_classes):
train_utils.add_softmax_cross_entropy_loss_for_each_scale(
outputs_to_scales_to_logits[output],
samples[common.LABEL],
num_classes,
ignore_label,
loss_weight=1.0,
upsample_logits=FLAGS.upsample_logits,
scope=output)
return outputs_to_scales_to_logits
def testBuildDeepLabv2(self):
batch_size = 2
crop_size = [41, 41]
# Test with two image_pyramids.
image_pyramids = [[1], [0.5, 1]]
# Test two model variants.
model_variants = ['xception_65', 'mobilenet_v2']
# Test with two output_types.
outputs_to_num_classes = {'semantic': 3, 'direction': 2}
expected_endpoints = [['merged_logits'],
['merged_logits', 'logits_0.50', 'logits_1.00']]
expected_num_logits = [1, 3]
for model_variant in model_variants:
model_options = common.ModelOptions(
outputs_to_num_classes)._replace(
add_image_level_feature=False,
aspp_with_batch_norm=False,
aspp_with_separable_conv=False,
model_variant=model_variant)
for i, image_pyramid in enumerate(image_pyramids):
g = tf.Graph()
with g.as_default():
with self.test_session(graph=g):
inputs = tf.random_uniform(
(batch_size, crop_size[0], crop_size[1], 3))
outputs_to_scales_to_logits = model.multi_scale_logits(
inputs, model_options, image_pyramid=image_pyramid)
# Check computed results for each output type.
for output in outputs_to_num_classes:
scales_to_logits = outputs_to_scales_to_logits[
output]
self.assertListEqual(
sorted(scales_to_logits.keys()),
sorted(expected_endpoints[i]))
# Expected number of logits = len(image_pyramid) + 1, since the
# last logits is merged from all the scales.
self.assertEqual(len(scales_to_logits),
expected_num_logits[i])
def main(unused_argv):
tf.logging.set_verbosity(tf.logging.INFO)
# Get dataset-dependent information.
dataset = segmentation_dataset.get_dataset(FLAGS.dataset,
FLAGS.eval_split,
dataset_dir=FLAGS.dataset_dir)
tf.gfile.MakeDirs(FLAGS.eval_logdir)
tf.logging.info('Evaluating on %s set', FLAGS.eval_split)
with tf.Graph().as_default():
samples = input_generator.get(dataset,
FLAGS.eval_crop_size,
FLAGS.eval_batch_size,
min_resize_value=FLAGS.min_resize_value,
max_resize_value=FLAGS.max_resize_value,
resize_factor=FLAGS.resize_factor,
dataset_split=FLAGS.eval_split,
is_training=False,
model_variant=FLAGS.model_variant)
model_options = common.ModelOptions(
outputs_to_num_classes={common.OUTPUT_TYPE: dataset.num_classes},
crop_size=FLAGS.eval_crop_size,
atrous_rates=FLAGS.atrous_rates,
output_stride=FLAGS.output_stride)
if tuple(FLAGS.eval_scales) == (1.0, ):
tf.logging.info('Performing single-scale test.')
predictions = model.predict_labels(
samples[common.IMAGE],
model_options,
image_pyramid=FLAGS.image_pyramid)
else:
tf.logging.info('Performing multi-scale test.')
predictions = model.predict_labels_multi_scale(
samples[common.IMAGE],
model_options=model_options,
eval_scales=FLAGS.eval_scales,
add_flipped_images=FLAGS.add_flipped_images)
predictions = predictions[common.OUTPUT_TYPE]
predictions = tf.reshape(predictions, shape=[-1])
labels = tf.reshape(samples[common.LABEL], shape=[-1])
weights = tf.to_float(tf.not_equal(labels, dataset.ignore_label))
# Set ignore_label regions to label 0, because metrics.mean_iou requires
# range of labels = [0, dataset.num_classes). Note the ignore_label regions
# are not evaluated since the corresponding regions contain weights = 0.
labels = tf.where(tf.equal(labels, dataset.ignore_label),
tf.zeros_like(labels), labels)
predictions_tag = 'miou'
for eval_scale in FLAGS.eval_scales:
predictions_tag += '_' + str(eval_scale)
if FLAGS.add_flipped_images:
predictions_tag += '_flipped'
# Define the evaluation metric.
metric_map = {}
metric_map[predictions_tag] = tf.metrics.mean_iou(predictions,
labels,
dataset.num_classes,
weights=weights)
metrics_to_values, metrics_to_updates = (
tf.contrib.metrics.aggregate_metric_map(metric_map))
for metric_name, metric_value in six.iteritems(metrics_to_values):
slim.summaries.add_scalar_summary(metric_value,
metric_name,
print_summary=True)
num_batches = int(
math.ceil(dataset.num_samples / float(FLAGS.eval_batch_size)))
tf.logging.info('Eval num images %d', dataset.num_samples)
tf.logging.info('Eval batch size %d and num batch %d',
FLAGS.eval_batch_size, num_batches)
num_eval_iters = None
if FLAGS.max_number_of_evaluations > 0:
num_eval_iters = FLAGS.max_number_of_evaluations
slim.evaluation.evaluation_loop(
master=FLAGS.master,
checkpoint_dir=FLAGS.checkpoint_dir,
logdir=FLAGS.eval_logdir,
num_evals=num_batches,
eval_op=list(metrics_to_updates.values()),
max_number_of_evaluations=num_eval_iters,
eval_interval_secs=FLAGS.eval_interval_secs)
def main(unused_argv):
tf.logging.set_verbosity(tf.logging.INFO)
# Get dataset-dependent information.
dataset = segmentation_dataset.get_dataset(FLAGS.dataset,
FLAGS.vis_split,
dataset_dir=FLAGS.dataset_dir)
train_id_to_eval_id = None
if dataset.name == segmentation_dataset.get_cityscapes_dataset_name():
tf.logging.info('Cityscapes requires converting train_id to eval_id.')
train_id_to_eval_id = _CITYSCAPES_TRAIN_ID_TO_EVAL_ID
# Prepare for visualization.
tf.gfile.MakeDirs(FLAGS.vis_logdir)
save_dir = os.path.join(FLAGS.vis_logdir, _SEMANTIC_PREDICTION_SAVE_FOLDER)
tf.gfile.MakeDirs(save_dir)
raw_save_dir = os.path.join(FLAGS.vis_logdir,
_RAW_SEMANTIC_PREDICTION_SAVE_FOLDER)
tf.gfile.MakeDirs(raw_save_dir)
tf.logging.info('Visualizing on %s set', FLAGS.vis_split)
g = tf.Graph()
with g.as_default():
samples = input_generator.get(dataset,
FLAGS.vis_crop_size,
FLAGS.vis_batch_size,
min_resize_value=FLAGS.min_resize_value,
max_resize_value=FLAGS.max_resize_value,
resize_factor=FLAGS.resize_factor,
dataset_split=FLAGS.vis_split,
is_training=False,
model_variant=FLAGS.model_variant)
model_options = common.ModelOptions(
outputs_to_num_classes={common.OUTPUT_TYPE: dataset.num_classes},
crop_size=FLAGS.vis_crop_size,
atrous_rates=FLAGS.atrous_rates,
output_stride=FLAGS.output_stride)
if tuple(FLAGS.eval_scales) == (1.0, ):
tf.logging.info('Performing single-scale test.')
predictions = model.predict_labels(
samples[common.IMAGE],
model_options=model_options,
image_pyramid=FLAGS.image_pyramid)
else:
tf.logging.info('Performing multi-scale test.')
predictions = model.predict_labels_multi_scale(
samples[common.IMAGE],
model_options=model_options,
eval_scales=FLAGS.eval_scales,
add_flipped_images=FLAGS.add_flipped_images)
predictions = predictions[common.OUTPUT_TYPE]
if FLAGS.min_resize_value and FLAGS.max_resize_value:
# Only support batch_size = 1, since we assume the dimensions of original
# image after tf.squeeze is [height, width, 3].
assert FLAGS.vis_batch_size == 1
# Reverse the resizing and padding operations performed in preprocessing.
# First, we slice the valid regions (i.e., remove padded region) and then
# we reisze the predictions back.
original_image = tf.squeeze(samples[common.ORIGINAL_IMAGE])
original_image_shape = tf.shape(original_image)
predictions = tf.slice(
predictions, [0, 0, 0],
[1, original_image_shape[0], original_image_shape[1]])
resized_shape = tf.to_int32([
tf.squeeze(samples[common.HEIGHT]),
tf.squeeze(samples[common.WIDTH])
])
predictions = tf.squeeze(
tf.image.resize_images(
tf.expand_dims(predictions, 3),
resized_shape,
method=tf.image.ResizeMethod.NEAREST_NEIGHBOR,
align_corners=True), 3)
tf.train.get_or_create_global_step()
saver = tf.train.Saver(slim.get_variables_to_restore())
sv = tf.train.Supervisor(graph=g,
logdir=FLAGS.vis_logdir,
init_op=tf.global_variables_initializer(),
summary_op=None,
summary_writer=None,
global_step=None,
saver=saver)
num_batches = int(
math.ceil(dataset.num_samples / float(FLAGS.vis_batch_size)))
last_checkpoint = None
# Loop to visualize the results when new checkpoint is created.
num_iters = 0
while (FLAGS.max_number_of_iterations <= 0
or num_iters < FLAGS.max_number_of_iterations):
num_iters += 1
last_checkpoint = slim.evaluation.wait_for_new_checkpoint(
FLAGS.checkpoint_dir, last_checkpoint)
start = time.time()
tf.logging.info('Starting visualization at ' +
time.strftime('%Y-%m-%d-%H:%M:%S', time.gmtime()))
tf.logging.info('Visualizing with model %s', last_checkpoint)
with sv.managed_session(FLAGS.master,
start_standard_services=False) as sess:
sv.start_queue_runners(sess)
sv.saver.restore(sess, last_checkpoint)
graph = tf.get_default_graph()
input_feature = graph.get_tensor_by_name(
'xception_65/entry_flow/conv1_2/Relu:0')
middle_feature = graph.get_tensor_by_name(
'xception_65/middle_flow/block1/unit_3/xception_module/Relu:0'
)
for i in range(4):
aspp[i] = graph.get_tensor_by_name('aspp' + str(i) + (
'' if i == 0 else '_pointwise') + '/Relu:0')
image_id_offset = 0
for batch in range(num_batches):
tf.logging.info('Visualizing batch %d / %d', batch + 1,
num_batches)
_process_batch(
sess=sess,
original_images=samples[common.ORIGINAL_IMAGE],
semantic_predictions=predictions,
image_names=samples[common.IMAGE_NAME],
image_heights=samples[common.HEIGHT],
image_widths=samples[common.WIDTH],
image_id_offset=image_id_offset,
save_dir=save_dir,
raw_save_dir=raw_save_dir,
train_id_to_eval_id=train_id_to_eval_id,
input_feature,
middle_feature,
aspp)
image_id_offset += FLAGS.vis_batch_size
tf.logging.info('Finished visualization at ' +
time.strftime('%Y-%m-%d-%H:%M:%S', time.gmtime()))
time_to_next_eval = start + FLAGS.eval_interval_secs - time.time()
if time_to_next_eval > 0:
time.sleep(time_to_next_eval)
def testWrongDeepLabVariant(self):
model_options = common.ModelOptions(
[])._replace(model_variant='no_such_variant')
with self.assertRaises(ValueError):
model._get_logits(images=[], model_options=model_options)