NVlabs / STEP

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Training on Custom Dataset

NaeemKhan333 opened this issue · comments

Thanks for sharing such a nice work . I want to train a model using your given code . Is it necessary to make my dataset as in the "AVA-Data set Format". If it is yes then what is the way or tools can be used.What are pre-processing steps I need to do to complete the AVA Dataset Format. Is there any way which I can use to train my dataset.

I have dataset now as follow

Dataset/
├── Class-A
│ └── insp.mp4
├── Class-B
│ └── kep.mp4
└── Class-C
└── tak.mp4