$ git clone https://github.com/WildChlamydia/MiVOLO.git
$ cd MiVOLO$ python -m venv venv
$ source venv\Scripts\activate
$ pip uninstall torch torchvision torchaudio
$ pip install torch==2.5.1 torchvision==0.20.1$ pip install -r requirements.txt
$ pip install omegaconf
Download yolov8x_person_face.pt
Download model_imdb_cross_person_4.22_99.46.pth.tar
$ python demo.py --input ma6.png --output output --detector-weights yolov8x_person_face.pt --checkpoint model_imdb_cross_person_4.22_99.46.pth.tar --device cpu
0: 384x640 1 person, 1 face, 262.4ms
Speed: 1.0ms preprocess, 262.4ms inference, 0.0ms postprocess per image at shape (1, 3, 384, 640)
faces_input: torch.Size([1, 3, 224, 224]), person_input: torch.Size([1, 3, 224, 224])
age: 30.1
gender: male [99%]
(venv)
VOB連結
ffmpeg -i "concat:VTS_01_1.VOB|VTS_01_2.VOB|VTS_01_3.VOB|VTS_01_4.VOB|VTS_01_5.VOB" -c copy output.mpg
