mediapipe/docs/solutions/object_detection.md
MediaPipe Team cc6a2f7af6 Project import generated by Copybara.
GitOrigin-RevId: 73d686c40057684f8bfaca285368bf1813f9fc26
2022-03-21 12:12:39 -07:00

6.7 KiB

layout title parent nav_order
default Object Detection Solutions 9

MediaPipe Object Detection

{: .no_toc }

Table of contents {: .text-delta } 1. TOC {:toc}
---

object_detection_android_gpu.gif

Example Apps

Note: To visualize a graph, copy the graph and paste it into MediaPipe Visualizer. For more information on how to visualize its associated subgraphs, please see visualizer documentation.

Mobile

Please first see general instructions for Android and iOS on how to build MediaPipe examples.

GPU Pipeline

CPU Pipeline

This is very similar to the GPU pipeline except that at the beginning and the end of the pipeline it performs GPU-to-CPU and CPU-to-GPU image transfer respectively. As a result, the rest of graph, which shares the same configuration as the GPU pipeline, runs entirely on CPU.

Desktop

Live Camera Input

Please first see general instructions for desktop on how to build MediaPipe examples.

Video File Input

  • With a TFLite Model

    This uses the same TFLite model (see also model info) as in Live Camera Input above. The pipeline is implemented in this graph, which differs from the live-camera-input CPU-based pipeline graph simply by the additional OpenCvVideoDecoderCalculator and OpenCvVideoEncoderCalculator at the beginning and the end of the graph respectively.

    To build the application, run:

    bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 mediapipe/examples/desktop/object_detection:object_detection_tflite
    

    To run the application, replace <input video path> and <output video path> in the command below with your own paths:

    Tip: You can find a test video available in mediapipe/examples/desktop/object_detection.

    GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_tflite \
      --calculator_graph_config_file=mediapipe/graphs/object_detection/object_detection_desktop_tflite_graph.pbtxt \
      --input_side_packets=input_video_path=<input video path>,output_video_path=<output video path>
    
  • With a TensorFlow Model

    This uses the TensorFlow model ( see also model info), and the pipeline is implemented in this graph.

    Note: The following runs TensorFlow inference on CPU. If you would like to run inference on GPU (Linux only), please follow TensorFlow CUDA Support and Setup on Linux Desktop instead.

    To build the TensorFlow CPU inference example on desktop, run:

    Note: This command also builds TensorFlow targets from scratch, and it may take a long time (e.g., up to 30 mins) for the first time.

    bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 --define no_aws_support=true --linkopt=-s \
    mediapipe/examples/desktop/object_detection:object_detection_tensorflow
    

    To run the application, replace <input video path> and <output video path> in the command below with your own paths:

    Tip: You can find a test video available in mediapipe/examples/desktop/object_detection.

    GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_tflite \
      --calculator_graph_config_file=mediapipe/graphs/object_detection/object_detection_desktop_tensorflow_graph.pbtxt \
      --input_side_packets=input_video_path=<input video path>,output_video_path=<output video path>
    

Coral

Please refer to these instructions to cross-compile and run MediaPipe examples on the Coral Dev Board.

Resources