Gesture-Recognition-Mask-RCNN

Implement Real-Time Gesture-Recognition and Segmentation with Mask_RCNN.

Requirements

• Ubuntu 16.04
• Python 3.5
• Tensorflow-gpu 1.8
• Keras 2.1.6
• OpenCV 3.4

Getting Started

Creating virtualenv

$ cd Gesture-Recognition-Mask-RCNN
$ virtualenv env --python=python3.5
$ source env/bin/activate

Install Dependencies

$ pip install -r requirements.txt

Download pre-trained Gesture weights (mask_rcnn_gesture_0001.h5) from the Google Drive.

Run Demo

$ python demo.py \
    --input_model=YOUR_MODEL_PATH \
    --input_video=YOUR_VIDEO_PATH