swatimodi / portrait-segmentation-mediapipe Goto Github PK

23: Message type "mediapipe.CalculatorGraphConfig.Node" has no field named "model_path".

@SwatiModi Thanks for such a nice work. I have a question related to the training model . I am working same sort of the problem , so I am using u2net segmentation Model for my solution . But it is really slow when I integrate it with my web-app code to run in the browser. Can you suggest me any way to improve my speed or can you provide your python training and testing script , So I can use it for my problem. Thanks

Hello Swati
I tried running your code but ran into some error

/mediapipe/mediapipe/examples/android/src/java/com/google/mediapipe/apps/portraitsegmentationgpu/BUILD:35:15: Merging manifest for //mediapipe/examples/android/src/java/com/google/mediapipe/apps/portraitsegmentationgpu:portraitsegmentationgpu failed (Exit 1): ResourceProcessorBusyBox failed: error executing command bazel-out/k8-opt-exec-50AE0418/bin/external/bazel_tools/src/tools/android/java/com/google/devtools/build/android/ResourceProcessorBusyBox --tool MERGE_MANIFEST -- --manifest ... (remaining 11 argument(s) skipped)

a person here had the same issue, so i tried the solution given to him about adding converterNumBuffers paramerter into the BUILD and was then able to build the APK.

However, the built APK is still not working ( it is asking for camera permission, but the screen is black the whole time).
Since, I don't have much knowledge about android, could you also help me in debugging this.

Hi Swati, Thank you so much for this awesome post.

Based on this - Link I have been trying to run the build command, but I have been getting some errors. Could you suggest some solution?

INFO: Repository local_execution_config_python instantiated at:
C:/users/gd19/pycharmprojects/mediapipe-custom/WORKSPACE:403:14: in
C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/tensorflow/workspace2.bzl:868:19: in workspace
C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/tensorflow/workspace2.bzl:91:27: in _tf_toolchains
C:/users/gd19/_bazel_gd19/gyx2hd7f/external/tf_toolchains/toolchains/remote_config/configs.bzl:6:28: in initialize_rbe_configs
C:/users/gd19/_bazel_gd19/gyx2hd7f/external/tf_toolchains/toolchains/remote_config/rbe_config.bzl:158:27: in _tensorflow_local_config
Repository rule local_python_configure defined at:
C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/third_party/py/python_configure.bzl:279:41: in
ERROR: An error occurred during the fetch of repository 'local_execution_config_python':
Traceback (most recent call last):
File "C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/third_party/py/python_configure.bzl", line 213, column 33, in _create_local_python_repository
python_lib = _get_python_lib(repository_ctx, python_bin)
File "C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/third_party/py/python_configure.bzl", line 130, column 21, in _get_python_lib
result = execute(repository_ctx, [python_bin, "-c", cmd])
File "C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/third_party/remote_config/common.bzl", line 230, column 13, in execute
fail(
Error in fail: Repository command failed
Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases.
ERROR: C:/users/gd19/pycharmprojects/mediapipe-custom/WORKSPACE:403:14: fetching local_python_configure rule //external:local_execution_config_python: Traceback (most recent call last):
File "C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/third_party/py/python_configure.bzl", line 213, column 33, in _create_local_python_repository
python_lib = _get_python_lib(repository_ctx, python_bin)
File "C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/third_party/py/python_configure.bzl", line 130, column 21, in _get_python_lib
result = execute(repository_ctx, [python_bin, "-c", cmd])
File "C:/users/gd19/_bazel_gd19/gyx2hd7f/external/org_tensorflow/third_party/remote_config/common.bzl", line 230, column 13, in execute
fail(
Error in fail: Repository command failed
Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases.
ERROR: Analysis of target '//mediapipe/examples/desktop/portrait_segmentation:portrait_segmentation_cpu' failed; build aborted: Repository command failed
Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases.
INFO: Elapsed time: 4.871s
INFO: 0 processes.
FAILED: Build did NOT complete successfully (36 packages loaded, 11 targets configured)

Thank you so much.

I know this is outside the scope of your tutorial, but I am curious if you have any information that might help me with either creating my own or adding to their model. I have used TF ModelMaker to make a model of objects and after looking at my model and their object_detection_3d_sneakers tflite files in Netron I am assuming that the tf Model Maker file is a very basic format. I am new to ML in general so any guidance would be appreciated.