Merge pull request #3739 from kinaryml:image-segmenter-python-impl
PiperOrigin-RevId: 484922757
This commit is contained in:
commit
7bcf322625
|
@ -88,6 +88,7 @@ cc_library(
|
|||
name = "builtin_task_graphs",
|
||||
deps = [
|
||||
"//mediapipe/tasks/cc/vision/image_classifier:image_classifier_graph",
|
||||
"//mediapipe/tasks/cc/vision/image_segmenter:image_segmenter_graph",
|
||||
"//mediapipe/tasks/cc/vision/object_detector:object_detector_graph",
|
||||
],
|
||||
)
|
||||
|
|
|
@ -56,3 +56,19 @@ py_test(
|
|||
"//mediapipe/tasks/python/vision/core:vision_task_running_mode",
|
||||
],
|
||||
)
|
||||
|
||||
py_test(
|
||||
name = "image_segmenter_test",
|
||||
srcs = ["image_segmenter_test.py"],
|
||||
data = [
|
||||
"//mediapipe/tasks/testdata/vision:test_images",
|
||||
"//mediapipe/tasks/testdata/vision:test_models",
|
||||
],
|
||||
deps = [
|
||||
"//mediapipe/python:_framework_bindings",
|
||||
"//mediapipe/tasks/python/core:base_options",
|
||||
"//mediapipe/tasks/python/test:test_utils",
|
||||
"//mediapipe/tasks/python/vision:image_segmenter",
|
||||
"//mediapipe/tasks/python/vision/core:vision_task_running_mode",
|
||||
],
|
||||
)
|
||||
|
|
353
mediapipe/tasks/python/test/vision/image_segmenter_test.py
Normal file
353
mediapipe/tasks/python/test/vision/image_segmenter_test.py
Normal file
|
@ -0,0 +1,353 @@
|
|||
# Copyright 2022 The MediaPipe Authors. All Rights Reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
"""Tests for image segmenter."""
|
||||
|
||||
import enum
|
||||
from typing import List
|
||||
from unittest import mock
|
||||
|
||||
from absl.testing import absltest
|
||||
from absl.testing import parameterized
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
from mediapipe.python._framework_bindings import image as image_module
|
||||
from mediapipe.python._framework_bindings import image_frame
|
||||
from mediapipe.tasks.python.core import base_options as base_options_module
|
||||
from mediapipe.tasks.python.test import test_utils
|
||||
from mediapipe.tasks.python.vision import image_segmenter
|
||||
from mediapipe.tasks.python.vision.core import vision_task_running_mode
|
||||
|
||||
_BaseOptions = base_options_module.BaseOptions
|
||||
_Image = image_module.Image
|
||||
_ImageFormat = image_frame.ImageFormat
|
||||
_OutputType = image_segmenter.OutputType
|
||||
_Activation = image_segmenter.Activation
|
||||
_ImageSegmenter = image_segmenter.ImageSegmenter
|
||||
_ImageSegmenterOptions = image_segmenter.ImageSegmenterOptions
|
||||
_RUNNING_MODE = vision_task_running_mode.VisionTaskRunningMode
|
||||
|
||||
_MODEL_FILE = 'deeplabv3.tflite'
|
||||
_IMAGE_FILE = 'segmentation_input_rotation0.jpg'
|
||||
_SEGMENTATION_FILE = 'segmentation_golden_rotation0.png'
|
||||
_MASK_MAGNIFICATION_FACTOR = 10
|
||||
_MASK_SIMILARITY_THRESHOLD = 0.98
|
||||
|
||||
|
||||
def _similar_to_uint8_mask(actual_mask, expected_mask):
|
||||
actual_mask_pixels = actual_mask.numpy_view().flatten()
|
||||
expected_mask_pixels = expected_mask.numpy_view().flatten()
|
||||
|
||||
consistent_pixels = 0
|
||||
num_pixels = len(expected_mask_pixels)
|
||||
|
||||
for index in range(num_pixels):
|
||||
consistent_pixels += (
|
||||
actual_mask_pixels[index] *
|
||||
_MASK_MAGNIFICATION_FACTOR == expected_mask_pixels[index])
|
||||
|
||||
return consistent_pixels / num_pixels >= _MASK_SIMILARITY_THRESHOLD
|
||||
|
||||
|
||||
class ModelFileType(enum.Enum):
|
||||
FILE_CONTENT = 1
|
||||
FILE_NAME = 2
|
||||
|
||||
|
||||
class ImageSegmenterTest(parameterized.TestCase):
|
||||
|
||||
def setUp(self):
|
||||
super().setUp()
|
||||
# Load the test input image.
|
||||
self.test_image = _Image.create_from_file(
|
||||
test_utils.get_test_data_path(_IMAGE_FILE))
|
||||
# Loads ground truth segmentation file.
|
||||
gt_segmentation_data = cv2.imread(
|
||||
test_utils.get_test_data_path(_SEGMENTATION_FILE), cv2.IMREAD_GRAYSCALE)
|
||||
self.test_seg_image = _Image(_ImageFormat.GRAY8, gt_segmentation_data)
|
||||
self.model_path = test_utils.get_test_data_path(_MODEL_FILE)
|
||||
|
||||
def test_create_from_file_succeeds_with_valid_model_path(self):
|
||||
# Creates with default option and valid model file successfully.
|
||||
with _ImageSegmenter.create_from_model_path(self.model_path) as segmenter:
|
||||
self.assertIsInstance(segmenter, _ImageSegmenter)
|
||||
|
||||
def test_create_from_options_succeeds_with_valid_model_path(self):
|
||||
# Creates with options containing model file successfully.
|
||||
base_options = _BaseOptions(model_asset_path=self.model_path)
|
||||
options = _ImageSegmenterOptions(base_options=base_options)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
self.assertIsInstance(segmenter, _ImageSegmenter)
|
||||
|
||||
def test_create_from_options_fails_with_invalid_model_path(self):
|
||||
# Invalid empty model path.
|
||||
with self.assertRaisesRegex(
|
||||
ValueError,
|
||||
r"ExternalFile must specify at least one of 'file_content', "
|
||||
r"'file_name', 'file_pointer_meta' or 'file_descriptor_meta'."):
|
||||
base_options = _BaseOptions(model_asset_path='')
|
||||
options = _ImageSegmenterOptions(base_options=base_options)
|
||||
_ImageSegmenter.create_from_options(options)
|
||||
|
||||
def test_create_from_options_succeeds_with_valid_model_content(self):
|
||||
# Creates with options containing model content successfully.
|
||||
with open(self.model_path, 'rb') as f:
|
||||
base_options = _BaseOptions(model_asset_buffer=f.read())
|
||||
options = _ImageSegmenterOptions(base_options=base_options)
|
||||
segmenter = _ImageSegmenter.create_from_options(options)
|
||||
self.assertIsInstance(segmenter, _ImageSegmenter)
|
||||
|
||||
@parameterized.parameters((ModelFileType.FILE_NAME,),
|
||||
(ModelFileType.FILE_CONTENT,))
|
||||
def test_segment_succeeds_with_category_mask(self, model_file_type):
|
||||
# Creates segmenter.
|
||||
if model_file_type is ModelFileType.FILE_NAME:
|
||||
base_options = _BaseOptions(model_asset_path=self.model_path)
|
||||
elif model_file_type is ModelFileType.FILE_CONTENT:
|
||||
with open(self.model_path, 'rb') as f:
|
||||
model_content = f.read()
|
||||
base_options = _BaseOptions(model_asset_buffer=model_content)
|
||||
else:
|
||||
# Should never happen
|
||||
raise ValueError('model_file_type is invalid.')
|
||||
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=base_options, output_type=_OutputType.CATEGORY_MASK)
|
||||
segmenter = _ImageSegmenter.create_from_options(options)
|
||||
|
||||
# Performs image segmentation on the input.
|
||||
category_masks = segmenter.segment(self.test_image)
|
||||
self.assertLen(category_masks, 1)
|
||||
category_mask = category_masks[0]
|
||||
result_pixels = category_mask.numpy_view().flatten()
|
||||
|
||||
# Check if data type of `category_mask` is correct.
|
||||
self.assertEqual(result_pixels.dtype, np.uint8)
|
||||
|
||||
self.assertTrue(
|
||||
_similar_to_uint8_mask(category_masks[0], self.test_seg_image),
|
||||
f'Number of pixels in the candidate mask differing from that of the '
|
||||
f'ground truth mask exceeds {_MASK_SIMILARITY_THRESHOLD}.')
|
||||
|
||||
# Closes the segmenter explicitly when the segmenter is not used in
|
||||
# a context.
|
||||
segmenter.close()
|
||||
|
||||
def test_segment_succeeds_with_confidence_mask(self):
|
||||
# Creates segmenter.
|
||||
base_options = _BaseOptions(model_asset_path=self.model_path)
|
||||
|
||||
# Run segmentation on the model in CATEGORY_MASK mode.
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=base_options, output_type=_OutputType.CATEGORY_MASK)
|
||||
segmenter = _ImageSegmenter.create_from_options(options)
|
||||
category_masks = segmenter.segment(self.test_image)
|
||||
category_mask = category_masks[0].numpy_view()
|
||||
|
||||
# Run segmentation on the model in CONFIDENCE_MASK mode.
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=base_options,
|
||||
output_type=_OutputType.CONFIDENCE_MASK,
|
||||
activation=_Activation.SOFTMAX)
|
||||
segmenter = _ImageSegmenter.create_from_options(options)
|
||||
confidence_masks = segmenter.segment(self.test_image)
|
||||
|
||||
# Check if confidence mask shape is correct.
|
||||
self.assertLen(
|
||||
confidence_masks, 21,
|
||||
'Number of confidence masks must match with number of categories.')
|
||||
|
||||
# Gather the confidence masks in a single array `confidence_mask_array`.
|
||||
confidence_mask_array = np.array(
|
||||
[confidence_mask.numpy_view() for confidence_mask in confidence_masks])
|
||||
|
||||
# Check if data type of `confidence_masks` are correct.
|
||||
self.assertEqual(confidence_mask_array.dtype, np.float32)
|
||||
|
||||
# Compute the category mask from the created confidence mask.
|
||||
calculated_category_mask = np.argmax(confidence_mask_array, axis=0)
|
||||
self.assertListEqual(
|
||||
calculated_category_mask.tolist(), category_mask.tolist(),
|
||||
'Confidence mask does not match with the category mask.')
|
||||
|
||||
# Closes the segmenter explicitly when the segmenter is not used in
|
||||
# a context.
|
||||
segmenter.close()
|
||||
|
||||
@parameterized.parameters((ModelFileType.FILE_NAME),
|
||||
(ModelFileType.FILE_CONTENT))
|
||||
def test_segment_in_context(self, model_file_type):
|
||||
if model_file_type is ModelFileType.FILE_NAME:
|
||||
base_options = _BaseOptions(model_asset_path=self.model_path)
|
||||
elif model_file_type is ModelFileType.FILE_CONTENT:
|
||||
with open(self.model_path, 'rb') as f:
|
||||
model_contents = f.read()
|
||||
base_options = _BaseOptions(model_asset_buffer=model_contents)
|
||||
else:
|
||||
# Should never happen
|
||||
raise ValueError('model_file_type is invalid.')
|
||||
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=base_options, output_type=_OutputType.CATEGORY_MASK)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
# Performs image segmentation on the input.
|
||||
category_masks = segmenter.segment(self.test_image)
|
||||
self.assertLen(category_masks, 1)
|
||||
|
||||
self.assertTrue(
|
||||
_similar_to_uint8_mask(category_masks[0], self.test_seg_image),
|
||||
f'Number of pixels in the candidate mask differing from that of the '
|
||||
f'ground truth mask exceeds {_MASK_SIMILARITY_THRESHOLD}.')
|
||||
|
||||
def test_missing_result_callback(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.LIVE_STREAM)
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'result callback must be provided'):
|
||||
with _ImageSegmenter.create_from_options(options) as unused_segmenter:
|
||||
pass
|
||||
|
||||
@parameterized.parameters((_RUNNING_MODE.IMAGE), (_RUNNING_MODE.VIDEO))
|
||||
def test_illegal_result_callback(self, running_mode):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=running_mode,
|
||||
result_callback=mock.MagicMock())
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'result callback should not be provided'):
|
||||
with _ImageSegmenter.create_from_options(options) as unused_segmenter:
|
||||
pass
|
||||
|
||||
def test_calling_segment_for_video_in_image_mode(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.IMAGE)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'not initialized with the video mode'):
|
||||
segmenter.segment_for_video(self.test_image, 0)
|
||||
|
||||
def test_calling_segment_async_in_image_mode(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.IMAGE)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'not initialized with the live stream mode'):
|
||||
segmenter.segment_async(self.test_image, 0)
|
||||
|
||||
def test_calling_segment_in_video_mode(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.VIDEO)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'not initialized with the image mode'):
|
||||
segmenter.segment(self.test_image)
|
||||
|
||||
def test_calling_segment_async_in_video_mode(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.VIDEO)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'not initialized with the live stream mode'):
|
||||
segmenter.segment_async(self.test_image, 0)
|
||||
|
||||
def test_segment_for_video_with_out_of_order_timestamp(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.VIDEO)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
unused_result = segmenter.segment_for_video(self.test_image, 1)
|
||||
with self.assertRaisesRegex(
|
||||
ValueError, r'Input timestamp must be monotonically increasing'):
|
||||
segmenter.segment_for_video(self.test_image, 0)
|
||||
|
||||
def test_segment_for_video(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
output_type=_OutputType.CATEGORY_MASK,
|
||||
running_mode=_RUNNING_MODE.VIDEO)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
for timestamp in range(0, 300, 30):
|
||||
category_masks = segmenter.segment_for_video(self.test_image, timestamp)
|
||||
self.assertLen(category_masks, 1)
|
||||
self.assertTrue(
|
||||
_similar_to_uint8_mask(category_masks[0], self.test_seg_image),
|
||||
f'Number of pixels in the candidate mask differing from that of the '
|
||||
f'ground truth mask exceeds {_MASK_SIMILARITY_THRESHOLD}.')
|
||||
|
||||
def test_calling_segment_in_live_stream_mode(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.LIVE_STREAM,
|
||||
result_callback=mock.MagicMock())
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'not initialized with the image mode'):
|
||||
segmenter.segment(self.test_image)
|
||||
|
||||
def test_calling_segment_for_video_in_live_stream_mode(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.LIVE_STREAM,
|
||||
result_callback=mock.MagicMock())
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
with self.assertRaisesRegex(ValueError,
|
||||
r'not initialized with the video mode'):
|
||||
segmenter.segment_for_video(self.test_image, 0)
|
||||
|
||||
def test_segment_async_calls_with_illegal_timestamp(self):
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
running_mode=_RUNNING_MODE.LIVE_STREAM,
|
||||
result_callback=mock.MagicMock())
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
segmenter.segment_async(self.test_image, 100)
|
||||
with self.assertRaisesRegex(
|
||||
ValueError, r'Input timestamp must be monotonically increasing'):
|
||||
segmenter.segment_async(self.test_image, 0)
|
||||
|
||||
def test_segment_async_calls(self):
|
||||
observed_timestamp_ms = -1
|
||||
|
||||
def check_result(result: List[image_module.Image], output_image: _Image,
|
||||
timestamp_ms: int):
|
||||
# Get the output category mask.
|
||||
category_mask = result[0]
|
||||
self.assertEqual(output_image.width, self.test_image.width)
|
||||
self.assertEqual(output_image.height, self.test_image.height)
|
||||
self.assertEqual(output_image.width, self.test_seg_image.width)
|
||||
self.assertEqual(output_image.height, self.test_seg_image.height)
|
||||
self.assertTrue(
|
||||
_similar_to_uint8_mask(category_mask, self.test_seg_image),
|
||||
f'Number of pixels in the candidate mask differing from that of the '
|
||||
f'ground truth mask exceeds {_MASK_SIMILARITY_THRESHOLD}.')
|
||||
self.assertLess(observed_timestamp_ms, timestamp_ms)
|
||||
self.observed_timestamp_ms = timestamp_ms
|
||||
|
||||
options = _ImageSegmenterOptions(
|
||||
base_options=_BaseOptions(model_asset_path=self.model_path),
|
||||
output_type=_OutputType.CATEGORY_MASK,
|
||||
running_mode=_RUNNING_MODE.LIVE_STREAM,
|
||||
result_callback=check_result)
|
||||
with _ImageSegmenter.create_from_options(options) as segmenter:
|
||||
for timestamp in range(0, 300, 30):
|
||||
segmenter.segment_async(self.test_image, timestamp)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
absltest.main()
|
|
@ -58,3 +58,22 @@ py_library(
|
|||
"//mediapipe/tasks/python/vision/core:vision_task_running_mode",
|
||||
],
|
||||
)
|
||||
|
||||
py_library(
|
||||
name = "image_segmenter",
|
||||
srcs = [
|
||||
"image_segmenter.py",
|
||||
],
|
||||
deps = [
|
||||
"//mediapipe/python:_framework_bindings",
|
||||
"//mediapipe/python:packet_creator",
|
||||
"//mediapipe/python:packet_getter",
|
||||
"//mediapipe/tasks/cc/components/proto:segmenter_options_py_pb2",
|
||||
"//mediapipe/tasks/cc/vision/image_segmenter/proto:image_segmenter_options_py_pb2",
|
||||
"//mediapipe/tasks/python/core:base_options",
|
||||
"//mediapipe/tasks/python/core:optional_dependencies",
|
||||
"//mediapipe/tasks/python/core:task_info",
|
||||
"//mediapipe/tasks/python/vision/core:base_vision_task_api",
|
||||
"//mediapipe/tasks/python/vision/core:vision_task_running_mode",
|
||||
],
|
||||
)
|
||||
|
|
253
mediapipe/tasks/python/vision/image_segmenter.py
Normal file
253
mediapipe/tasks/python/vision/image_segmenter.py
Normal file
|
@ -0,0 +1,253 @@
|
|||
# Copyright 2022 The MediaPipe Authors. All Rights Reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
"""MediaPipe image segmenter task."""
|
||||
|
||||
import dataclasses
|
||||
import enum
|
||||
from typing import Callable, List, Mapping, Optional
|
||||
|
||||
from mediapipe.python import packet_creator
|
||||
from mediapipe.python import packet_getter
|
||||
from mediapipe.python._framework_bindings import image as image_module
|
||||
from mediapipe.python._framework_bindings import packet
|
||||
from mediapipe.python._framework_bindings import task_runner
|
||||
from mediapipe.tasks.cc.components.proto import segmenter_options_pb2
|
||||
from mediapipe.tasks.cc.vision.image_segmenter.proto import image_segmenter_options_pb2
|
||||
from mediapipe.tasks.python.core import base_options as base_options_module
|
||||
from mediapipe.tasks.python.core import task_info as task_info_module
|
||||
from mediapipe.tasks.python.core.optional_dependencies import doc_controls
|
||||
from mediapipe.tasks.python.vision.core import base_vision_task_api
|
||||
from mediapipe.tasks.python.vision.core import vision_task_running_mode
|
||||
|
||||
_BaseOptions = base_options_module.BaseOptions
|
||||
_SegmenterOptionsProto = segmenter_options_pb2.SegmenterOptions
|
||||
_ImageSegmenterOptionsProto = image_segmenter_options_pb2.ImageSegmenterOptions
|
||||
_RunningMode = vision_task_running_mode.VisionTaskRunningMode
|
||||
_TaskInfo = task_info_module.TaskInfo
|
||||
_TaskRunner = task_runner.TaskRunner
|
||||
|
||||
_SEGMENTATION_OUT_STREAM_NAME = 'segmented_mask_out'
|
||||
_SEGMENTATION_TAG = 'GROUPED_SEGMENTATION'
|
||||
_IMAGE_IN_STREAM_NAME = 'image_in'
|
||||
_IMAGE_OUT_STREAM_NAME = 'image_out'
|
||||
_IMAGE_TAG = 'IMAGE'
|
||||
_TASK_GRAPH_NAME = 'mediapipe.tasks.vision.ImageSegmenterGraph'
|
||||
_MICRO_SECONDS_PER_MILLISECOND = 1000
|
||||
|
||||
|
||||
class OutputType(enum.Enum):
|
||||
UNSPECIFIED = 0
|
||||
CATEGORY_MASK = 1
|
||||
CONFIDENCE_MASK = 2
|
||||
|
||||
|
||||
class Activation(enum.Enum):
|
||||
NONE = 0
|
||||
SIGMOID = 1
|
||||
SOFTMAX = 2
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
class ImageSegmenterOptions:
|
||||
"""Options for the image segmenter task.
|
||||
|
||||
Attributes:
|
||||
base_options: Base options for the image segmenter task.
|
||||
running_mode: The running mode of the task. Default to the image mode. Image
|
||||
segmenter task has three running modes: 1) The image mode for segmenting
|
||||
objects on single image inputs. 2) The video mode for segmenting objects
|
||||
on the decoded frames of a video. 3) The live stream mode for segmenting
|
||||
objects on a live stream of input data, such as from camera.
|
||||
output_type: The output mask type allows specifying the type of
|
||||
post-processing to perform on the raw model results.
|
||||
activation: Activation function to apply to input tensor.
|
||||
result_callback: The user-defined result callback for processing live stream
|
||||
data. The result callback should only be specified when the running mode
|
||||
is set to the live stream mode.
|
||||
"""
|
||||
base_options: _BaseOptions
|
||||
running_mode: _RunningMode = _RunningMode.IMAGE
|
||||
output_type: Optional[OutputType] = OutputType.CATEGORY_MASK
|
||||
activation: Optional[Activation] = Activation.NONE
|
||||
result_callback: Optional[Callable[
|
||||
[List[image_module.Image], image_module.Image, int], None]] = None
|
||||
|
||||
@doc_controls.do_not_generate_docs
|
||||
def to_pb2(self) -> _ImageSegmenterOptionsProto:
|
||||
"""Generates an ImageSegmenterOptions protobuf object."""
|
||||
base_options_proto = self.base_options.to_pb2()
|
||||
base_options_proto.use_stream_mode = False if self.running_mode == _RunningMode.IMAGE else True
|
||||
segmenter_options_proto = _SegmenterOptionsProto(
|
||||
output_type=self.output_type.value, activation=self.activation.value)
|
||||
return _ImageSegmenterOptionsProto(
|
||||
base_options=base_options_proto,
|
||||
segmenter_options=segmenter_options_proto)
|
||||
|
||||
|
||||
class ImageSegmenter(base_vision_task_api.BaseVisionTaskApi):
|
||||
"""Class that performs image segmentation on images."""
|
||||
|
||||
@classmethod
|
||||
def create_from_model_path(cls, model_path: str) -> 'ImageSegmenter':
|
||||
"""Creates an `ImageSegmenter` object from a TensorFlow Lite model and the default `ImageSegmenterOptions`.
|
||||
|
||||
Note that the created `ImageSegmenter` instance is in image mode, for
|
||||
performing image segmentation on single image inputs.
|
||||
|
||||
Args:
|
||||
model_path: Path to the model.
|
||||
|
||||
Returns:
|
||||
`ImageSegmenter` object that's created from the model file and the default
|
||||
`ImageSegmenterOptions`.
|
||||
|
||||
Raises:
|
||||
ValueError: If failed to create `ImageSegmenter` object from the provided
|
||||
file such as invalid file path.
|
||||
RuntimeError: If other types of error occurred.
|
||||
"""
|
||||
base_options = _BaseOptions(model_asset_path=model_path)
|
||||
options = ImageSegmenterOptions(
|
||||
base_options=base_options, running_mode=_RunningMode.IMAGE)
|
||||
return cls.create_from_options(options)
|
||||
|
||||
@classmethod
|
||||
def create_from_options(cls,
|
||||
options: ImageSegmenterOptions) -> 'ImageSegmenter':
|
||||
"""Creates the `ImageSegmenter` object from image segmenter options.
|
||||
|
||||
Args:
|
||||
options: Options for the image segmenter task.
|
||||
|
||||
Returns:
|
||||
`ImageSegmenter` object that's created from `options`.
|
||||
|
||||
Raises:
|
||||
ValueError: If failed to create `ImageSegmenter` object from
|
||||
`ImageSegmenterOptions` such as missing the model.
|
||||
RuntimeError: If other types of error occurred.
|
||||
"""
|
||||
|
||||
def packets_callback(output_packets: Mapping[str, packet.Packet]):
|
||||
if output_packets[_IMAGE_OUT_STREAM_NAME].is_empty():
|
||||
return
|
||||
segmentation_result = packet_getter.get_image_list(
|
||||
output_packets[_SEGMENTATION_OUT_STREAM_NAME])
|
||||
image = packet_getter.get_image(output_packets[_IMAGE_OUT_STREAM_NAME])
|
||||
timestamp = output_packets[_SEGMENTATION_OUT_STREAM_NAME].timestamp
|
||||
options.result_callback(segmentation_result, image,
|
||||
timestamp.value // _MICRO_SECONDS_PER_MILLISECOND)
|
||||
|
||||
task_info = _TaskInfo(
|
||||
task_graph=_TASK_GRAPH_NAME,
|
||||
input_streams=[':'.join([_IMAGE_TAG, _IMAGE_IN_STREAM_NAME])],
|
||||
output_streams=[
|
||||
':'.join([_SEGMENTATION_TAG, _SEGMENTATION_OUT_STREAM_NAME]),
|
||||
':'.join([_IMAGE_TAG, _IMAGE_OUT_STREAM_NAME])
|
||||
],
|
||||
task_options=options)
|
||||
return cls(
|
||||
task_info.generate_graph_config(
|
||||
enable_flow_limiting=options.running_mode ==
|
||||
_RunningMode.LIVE_STREAM), options.running_mode,
|
||||
packets_callback if options.result_callback else None)
|
||||
|
||||
def segment(self, image: image_module.Image) -> List[image_module.Image]:
|
||||
"""Performs the actual segmentation task on the provided MediaPipe Image.
|
||||
|
||||
Args:
|
||||
image: MediaPipe Image.
|
||||
|
||||
Returns:
|
||||
If the output_type is CATEGORY_MASK, the returned vector of images is
|
||||
per-category segmented image mask.
|
||||
If the output_type is CONFIDENCE_MASK, the returned vector of images
|
||||
contains only one confidence image mask. A segmentation result object that
|
||||
contains a list of segmentation masks as images.
|
||||
|
||||
Raises:
|
||||
ValueError: If any of the input arguments is invalid.
|
||||
RuntimeError: If image segmentation failed to run.
|
||||
"""
|
||||
output_packets = self._process_image_data(
|
||||
{_IMAGE_IN_STREAM_NAME: packet_creator.create_image(image)})
|
||||
segmentation_result = packet_getter.get_image_list(
|
||||
output_packets[_SEGMENTATION_OUT_STREAM_NAME])
|
||||
return segmentation_result
|
||||
|
||||
def segment_for_video(self, image: image_module.Image,
|
||||
timestamp_ms: int) -> List[image_module.Image]:
|
||||
"""Performs segmentation on the provided video frames.
|
||||
|
||||
Only use this method when the ImageSegmenter is created with the video
|
||||
running mode. It's required to provide the video frame's timestamp (in
|
||||
milliseconds) along with the video frame. The input timestamps should be
|
||||
monotonically increasing for adjacent calls of this method.
|
||||
|
||||
Args:
|
||||
image: MediaPipe Image.
|
||||
timestamp_ms: The timestamp of the input video frame in milliseconds.
|
||||
|
||||
Returns:
|
||||
If the output_type is CATEGORY_MASK, the returned vector of images is
|
||||
per-category segmented image mask.
|
||||
If the output_type is CONFIDENCE_MASK, the returned vector of images
|
||||
contains only one confidence image mask. A segmentation result object that
|
||||
contains a list of segmentation masks as images.
|
||||
|
||||
Raises:
|
||||
ValueError: If any of the input arguments is invalid.
|
||||
RuntimeError: If image segmentation failed to run.
|
||||
"""
|
||||
output_packets = self._process_video_data({
|
||||
_IMAGE_IN_STREAM_NAME:
|
||||
packet_creator.create_image(image).at(
|
||||
timestamp_ms * _MICRO_SECONDS_PER_MILLISECOND)
|
||||
})
|
||||
segmentation_result = packet_getter.get_image_list(
|
||||
output_packets[_SEGMENTATION_OUT_STREAM_NAME])
|
||||
return segmentation_result
|
||||
|
||||
def segment_async(self, image: image_module.Image, timestamp_ms: int) -> None:
|
||||
"""Sends live image data (an Image with a unique timestamp) to perform image segmentation.
|
||||
|
||||
Only use this method when the ImageSegmenter is created with the live stream
|
||||
running mode. The input timestamps should be monotonically increasing for
|
||||
adjacent calls of this method. This method will return immediately after the
|
||||
input image is accepted. The results will be available via the
|
||||
`result_callback` provided in the `ImageSegmenterOptions`. The
|
||||
`segment_async` method is designed to process live stream data such as
|
||||
camera input. To lower the overall latency, image segmenter may drop the
|
||||
input images if needed. In other words, it's not guaranteed to have output
|
||||
per input image.
|
||||
|
||||
The `result_callback` prvoides:
|
||||
- A segmentation result object that contains a list of segmentation masks
|
||||
as images.
|
||||
- The input image that the image segmenter runs on.
|
||||
- The input timestamp in milliseconds.
|
||||
|
||||
Args:
|
||||
image: MediaPipe Image.
|
||||
timestamp_ms: The timestamp of the input image in milliseconds.
|
||||
|
||||
Raises:
|
||||
ValueError: If the current input timestamp is smaller than what the image
|
||||
segmenter has already processed.
|
||||
"""
|
||||
self._send_live_stream_data({
|
||||
_IMAGE_IN_STREAM_NAME:
|
||||
packet_creator.create_image(image).at(
|
||||
timestamp_ms * _MICRO_SECONDS_PER_MILLISECOND)
|
||||
})
|
Loading…
Reference in New Issue
Block a user