- Path on Srv:
s1_md0/v-fanxu/junyidu/github/action-models
- Borrows data pipeline
- Raw Path:
/s1_md0/v-fanxu/Extraction/youcook2/videos
- Extracted Img Path:
/s1_md0/v-fanxu/Extraction/youcook2/imgs
- List Path:
/s1_md0/v-fanxu/Extraction/youcook2/manifest.txt
- Epic Kitchen Verb List:
/s1_md0/v-fanxu/junyidu/github/action-models/EPIC_verb_classes.csv
- Bulk:
/s1_md0/v-fanxu/junyidu/github/action-models/predict_verb_bulk.txt
- Model download link
- Use: TSN, 8seg, Res50, RGB
- Path on Srv:
/s1_md0/v-fanxu/junyidu/download/TSN_arch=resnet50_modality=RGB_segments=8-3ecf904f.pth.tar
Decode raw video
- In dataset's root folder
python vid2img.py videos imgs
Generate manifest for video (bulk or clip)
- In the corresponding imgs folder
bash /s1_md0/v-fanxu/junyidu/github/action-models/youcook2/generate_manifest.sh
Fetch framerate for each video
- In videos folder
bash /s1_md0/v-fanxu/junyidu/github/action-models/youcook2/fetch_framerate.sh
- Kinetics
- Actions: 400
- Min Clip for an Action: ~400
- Tot Clips: 306k
- Length: 10s
- Resolution: Variable (Usually normalized to 340px)
- UCF101
- Actions: 101
- Min Clip for an Action: ~100
- Tot Clips: 13k
- Mean Length: 7.2s
- Resolution: 320x240
- Official Demo(Rand):
bash rundemo.sh
- Extract:
bash runextract.sh