def test_tags(self):
"""Tests proper tags for each event/tensor."""
tensor_data = test_utils.get_random_mesh(100,
add_faces=True,
add_colors=True)
config_dict = {"foo": 1}
name = "foo"
events = self.mesh_events(
name,
tensor_data.vertices,
faces=tensor_data.faces,
colors=tensor_data.colors,
config_dict=config_dict,
step=333,
)
expected_names_set = frozenset(
name_tpl % name
for name_tpl in ["%s_VERTEX", "%s_FACE", "%s_COLOR"])
actual_names_set = frozenset(
[event.summary.value[0].tag for event in events])
self.assertEqual(expected_names_set, actual_names_set)
expected_bitmask = metadata.get_components_bitmask([
plugin_data_pb2.MeshPluginData.VERTEX,
plugin_data_pb2.MeshPluginData.FACE,
plugin_data_pb2.MeshPluginData.COLOR,
])
for event in events:
self.assertEqual(expected_bitmask,
self.get_metadata(event).components)
def mesh_pb(tag,
vertices,
faces=None,
colors=None,
config_dict=None,
description=None):
"""Create a mesh summary to save in pb format.
Args:
tag: String tag for the summary.
vertices: numpy array of shape `[dim_1, ..., dim_n, 3]` representing the 3D
coordinates of vertices.
faces: numpy array of shape `[dim_1, ..., dim_n, 3]` containing indices of
vertices within each triangle.
colors: numpy array of shape `[dim_1, ..., dim_n, 3]` containing colors for
each vertex.
config_dict: Dictionary with ThreeJS classes names and configuration.
description: Optional long-form description for this summary, as a
constant `str`. Markdown is supported. Defaults to empty.
Returns:
Instance of tf.Summary class.
"""
json_config = _get_json_config(config_dict)
summaries = []
tensors = [
metadata.MeshTensor(vertices, plugin_data_pb2.MeshPluginData.VERTEX,
tf.float32),
metadata.MeshTensor(faces, plugin_data_pb2.MeshPluginData.FACE,
tf.int32),
metadata.MeshTensor(colors, plugin_data_pb2.MeshPluginData.COLOR,
tf.uint8),
]
tensors = [tensor for tensor in tensors if tensor.data is not None]
components = metadata.get_components_bitmask(
[tensor.content_type for tensor in tensors])
for tensor in tensors:
shape = tensor.data.shape
shape = [dim if dim is not None else -1 for dim in shape]
tensor_proto = tensor_util.make_tensor_proto(tensor.data,
dtype=tensor.data_type)
summary_metadata = metadata.create_summary_metadata(
tag,
None, # display_name
tensor.content_type,
components,
shape,
description,
json_config=json_config,
)
instance_tag = metadata.get_instance_name(tag, tensor.content_type)
summaries.append((instance_tag, summary_metadata, tensor_proto))
summary = summary_pb2.Summary()
for instance_tag, summary_metadata, tensor_proto in summaries:
summary.value.add(tag=instance_tag,
metadata=summary_metadata,
tensor=tensor_proto)
return summary
def op(name,
vertices,
faces=None,
colors=None,
display_name=None,
description=None,
collections=None,
config_dict=None):
"""Creates a TensorFlow summary op for mesh rendering.
Args:
name: A name for this summary operation.
vertices: Tensor of shape `[dim_1, ..., dim_n, 3]` representing the 3D
coordinates of vertices.
faces: Tensor of shape `[dim_1, ..., dim_n, 3]` containing indices of
vertices within each triangle.
colors: Tensor of shape `[dim_1, ..., dim_n, 3]` containing colors for each
vertex.
display_name: If set, will be used as the display name in TensorBoard.
Defaults to `name`.
description: A longform readable description of the summary data. Markdown
is supported.
collections: Which TensorFlow graph collections to add the summary op to.
Defaults to `['summaries']`. Can usually be ignored.
config_dict: Dictionary with ThreeJS classes names and configuration.
Returns:
Merged summary for mesh/point cloud representation.
"""
display_name = _get_display_name(name, display_name)
json_config = _get_json_config(config_dict)
# All tensors representing a single mesh will be represented as separate
# summaries internally. Those summaries will be regrouped on the client before
# rendering.
summaries = []
tensors = [
metadata.MeshTensor(vertices, plugin_data_pb2.MeshPluginData.VERTEX,
tf.float32),
metadata.MeshTensor(faces, plugin_data_pb2.MeshPluginData.FACE,
tf.int32),
metadata.MeshTensor(colors, plugin_data_pb2.MeshPluginData.COLOR,
tf.uint8)
]
tensors = [tensor for tensor in tensors if tensor.data is not None]
components = metadata.get_components_bitmask(
[tensor.content_type for tensor in tensors])
for tensor in tensors:
summaries.append(
_get_tensor_summary(name, display_name, description, tensor.data,
tensor.content_type, components, json_config,
collections))
all_summaries = tf.compat.v1.summary.merge(summaries,
collections=collections,
name=name)
return all_summaries
def mesh(name,
vertices,
faces=None,
colors=None,
config_dict=None,
step=None,
description=None):
"""Writes a TensorFlow mesh summary.
Args:
name: A name for this summary. The summary tag used for TensorBoard will
be this name prefixed by any active name scopes.
vertices: Tensor of shape `[dim_1, ..., dim_n, 3]` representing the 3D
coordinates of vertices.
faces: Tensor of shape `[dim_1, ..., dim_n, 3]` containing indices of
vertices within each triangle.
colors: Tensor of shape `[dim_1, ..., dim_n, 3]` containing colors for each
vertex.
config_dict: Dictionary with ThreeJS classes names and configuration.
step: Explicit `int64`-castable monotonic step value for this summary. If
omitted, this defaults to `tf.summary.experimental.get_step()`, which must
not be None.
description: Optional long-form description for this summary, as a
constant `str`. Markdown is supported. Defaults to empty.
Returns:
True if all components of the mesh were saved successfully and False
otherwise.
"""
json_config = _get_json_config(config_dict)
# All tensors representing a single mesh will be represented as separate
# summaries internally. Those summaries will be regrouped on the client before
# rendering.
tensors = [
metadata.MeshTensor(vertices, plugin_data_pb2.MeshPluginData.VERTEX,
tf.float32),
metadata.MeshTensor(faces, plugin_data_pb2.MeshPluginData.FACE,
tf.int32),
metadata.MeshTensor(colors, plugin_data_pb2.MeshPluginData.COLOR,
tf.uint8)
]
tensors = [tensor for tensor in tensors if tensor.data is not None]
components = metadata.get_components_bitmask(
[tensor.content_type for tensor in tensors])
summary_scope = (getattr(tf.summary.experimental, 'summary_scope', None)
or tf.summary.summary_scope)
all_success = True
with summary_scope(name, 'mesh_summary', values=tensors):
for tensor in tensors:
all_success = all_success and _write_summary(
name, description, tensor.data, tensor.content_type,
components, json_config, step)
return all_success
def mesh(tag,
vertices,
colors,
faces,
config_dict,
display_name=None,
description=None):
"""Outputs a merged `Summary` protocol buffer with a mesh/point cloud.
Args:
tag: A name for this summary operation.
vertices: Tensor of shape `[dim_1, ..., dim_n, 3]` representing the 3D
coordinates of vertices.
faces: Tensor of shape `[dim_1, ..., dim_n, 3]` containing indices of
vertices within each triangle.
colors: Tensor of shape `[dim_1, ..., dim_n, 3]` containing colors for each
vertex.
display_name: If set, will be used as the display name in TensorBoard.
Defaults to `name`.
description: A longform readable description of the summary data. Markdown
is supported.
config_dict: Dictionary with ThreeJS classes names and configuration.
Returns:
Merged summary for mesh/point cloud representation.
"""
from tensorboard.plugins.mesh.plugin_data_pb2 import MeshPluginData
from tensorboard.plugins.mesh import metadata
json_config = _get_json_config(config_dict)
summaries = []
tensors = [
(vertices, MeshPluginData.VERTEX),
(faces, MeshPluginData.FACE),
(colors, MeshPluginData.COLOR),
]
tensors = [tensor for tensor in tensors if tensor[0] is not None]
components = metadata.get_components_bitmask(
[content_type for (tensor, content_type) in tensors])
for tensor, content_type in tensors:
summaries.append(
_get_tensor_summary(
tag,
display_name,
description,
tensor,
content_type,
components,
json_config,
))
return Summary(value=summaries)
def pb(name,
vertices,
faces=None,
colors=None,
display_name=None,
description=None,
config_dict=None):
"""Create a mesh summary to save in pb format.
Args:
name: A name for this summary operation.
vertices: numpy array of shape `[dim_1, ..., dim_n, 3]` representing the 3D
coordinates of vertices.
faces: numpy array of shape `[dim_1, ..., dim_n, 3]` containing indices of
vertices within each triangle.
colors: numpy array of shape `[dim_1, ..., dim_n, 3]` containing colors for
each vertex.
display_name: If set, will be used as the display name in TensorBoard.
Defaults to `name`.
description: A longform readable description of the summary data. Markdown
is supported.
config_dict: Dictionary with ThreeJS classes names and configuration.
Returns:
Instance of tf.Summary class.
"""
display_name = _get_display_name(name, display_name)
json_config = _get_json_config(config_dict)
summaries = []
tensors = [
metadata.MeshTensor(
vertices, plugin_data_pb2.MeshPluginData.VERTEX, tf.float32),
metadata.MeshTensor(faces, plugin_data_pb2.MeshPluginData.FACE, tf.int32),
metadata.MeshTensor(
colors, plugin_data_pb2.MeshPluginData.COLOR, tf.uint8)
]
tensors = [tensor for tensor in tensors if tensor.data is not None]
components = metadata.get_components_bitmask([
tensor.content_type for tensor in tensors])
for tensor in tensors:
shape = tensor.data.shape
shape = [dim if dim is not None else -1 for dim in shape]
tensor_proto = tf.compat.v1.make_tensor_proto(
tensor.data, dtype=tensor.data_type)
summary_metadata = metadata.create_summary_metadata(
name,
display_name,
tensor.content_type,
components,
shape,
description,
json_config=json_config)
tag = metadata.get_instance_name(name, tensor.content_type)
summaries.append((tag, summary_metadata, tensor_proto))
summary = tf.Summary()
for tag, summary_metadata, tensor_proto in summaries:
tf_summary_metadata = tf.SummaryMetadata.FromString(
summary_metadata.SerializeToString())
summary.value.add(
tag=tag, metadata=tf_summary_metadata, tensor=tensor_proto)
return summary
