cassdlcm/mediapipe
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Project import generated by Copybara.

Browse Source 
GitOrigin-RevId: 87e46800807001e01d686fd7bcc2533714556920
This commit is contained in:
MediaPipe Team 2019-12-09 13:01:04 -08:00 committed by jqtang
parent 86b3283b2f
commit 38ee2603a7
4 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mediapipe/calculators/tflite/tflite_inference_calculator.cc
View File

@ -464,7 +464,7 @@ REGISTER_CALCULATOR(TfLiteInferenceCalculator);
// Get model name.
if (!options.model_path().empty()) {
auto model_path = options.model_path();
std::string model_path = options.model_path();
ASSIGN_OR_RETURN(model_path_, mediapipe::PathToResourceAsFile(model_path));
} else {

2
mediapipe/docs/install.md
View File

@ -380,7 +380,7 @@ To build and run iOS apps:
4. Install the needed packages.
```bash
username@DESKTOP-TMVLBJ1:~$ sudo apt-get update && sudo apt-get install -y --no-install-recommends build-essential git python zip adb openjdk-8-jdk
username@DESKTOP-TMVLBJ1:~$ sudo apt-get update && sudo apt-get install -y build-essential git python zip adb openjdk-8-jdk
```
5. Install Bazel (0.24.1 and above required).

4
mediapipe/docs/object_tracking_mobile_gpu.md
View File

@ -5,7 +5,7 @@ This doc focuses on the
that performs object detection and tracking.
Note that object detection is using TensorFlow Lite on GPU while tracking is using CPU.
For overall context on hand detection and hand tracking, please read this
For overall context on object detection and tracking, please read this
[Google Developer Blog](https://mediapipe.page.link/objecttrackingblog).
![object_tracking_android_gpu_gif](images/mobile/object_tracking_android_gpu.gif)
@ -437,7 +437,7 @@ node: {
### Renderer Subgraph
![hand_renderer_gpu_subgraph.pbtxt](images/mobile/object_tracking_renderer_gpu_subgraph.png)
![object_tracking_renderer_gpu_subgraph.pbtxt](images/mobile/object_tracking_renderer_gpu_subgraph.png)
[Source pbtxt file](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/tracking/subgraphs/renderer_gpu.pbtxt)

2
setup_opencv.sh
View File

@ -49,7 +49,7 @@ cmake .. -DCMAKE_BUILD_TYPE=RELEASE -DCMAKE_INSTALL_PREFIX=/usr/local \
-DBUILD_opencv_rgbd=OFF -DBUILD_opencv_saliency=OFF -DBUILD_opencv_shape=OFF \
-DBUILD_opencv_structured_light=OFF -DBUILD_opencv_surface_matching=OFF \
-DBUILD_opencv_world=OFF -DBUILD_opencv_xobjdetect=OFF -DBUILD_opencv_xphoto=OFF
make -j
make -j 16
sudo make install
rm -rf /tmp/build_opencv
echo "OpenCV has been built. You can find the header files and libraries in /usr/local/include/opencv4/opencv2 and /usr/local/lib"