https://github.com/Rassibassi/mediapipeDemos

Real-time Python demos of google mediapipe
https://github.com/Rassibassi/mediapipeDemos

Last synced: 4 months ago
JSON representation

Real-time Python demos of google mediapipe

• Host: GitHub
• URL: https://github.com/Rassibassi/mediapipeDemos
• Owner: Rassibassi
• Created: 2021-07-15T19:57:38.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-11-17T09:04:45.000Z (over 2 years ago)
• Last Synced: 2024-08-01T13:29:03.315Z (7 months ago)
• Language: Python
• Homepage:
• Size: 33.2 KB
• Stars: 120
• Watchers: 7
• Forks: 36
• Open Issues: 11
• Metadata Files:
  • Readme: readme.MD

Awesome Lists containing this project

README

        
# Mediapipe examples

From:

https://google.github.io/mediapipe/

## Installation

```

python -m venv env

source env/bin/activate

pip install -r requirements.txt

```

For the iris example, put `iris_landmark.tflite` into `models` directory, by unpacking following zip file:

```

https://github.com/google/mediapipe/files/10012191/iris_landmark.zip

```

The facial expression example uses the trained weights from [github.com/zengqunzhao/EfficientFace](https://github.com/zengqunzhao/EfficientFace), but converted to tflite.

For the facial expression example download both models (fast and slow) into the `models` directory:

```

wget -P models https://rassibassi-mediapipedemos.s3.eu-central-1.amazonaws.com/efficient_face_model.tflite

wget -P models https://rassibassi-mediapipedemos.s3.eu-central-1.amazonaws.com/dlg_model.tflite

```

## How to run

One of the following:

```

python facial_expression.py

python face_detection.py

python face_mesh.py

python hands.py

python head_posture.py

python holistic.py

python iris.py

python objectron.py

python pose.py

python selfie_segmentation.py

```

`pose.py` and `iris.py` include the possibility to process a video file instead of the webcam input stream. Run like this:

```

python iris.py -i /path/to/some/file/i-am-a-video-file.mp4

python pose.py -i /path/to/some/file/i-am-a-video-file.mp4

```

## Numpy

See example `python pose.py` for how to extract numpy array from the mediapipe landmark objects.