search

amazon-science / long-short-term-transformer

[NeurIPS 2021 Spotlight] Official implementation of Long Short-Term Transformer for Online Action Detection
Apache License 2.0
127 stars 19 forks source link

about custom dataset #15

Closed tghim closed 2 years ago

tghim commented 2 years ago

Thank you to share your great work!

I have something to ask you.

I have my own dataset that I want to apply your LSTR to, and for this I did feature extraction for rgb and flow respectively according to this https://github.com/open-mmlab/mmaction2/tree/master/tools/data/activitynet. However, the feature results came out in pkl format. To use your dataloader, it must be in npy format. How can I get the features out in npy format like you?

xumingze0308 commented 2 years ago

You just need to convert the feature of each video from .pkl into a single .npy file. The feature should be in shape of L x C, where L is the length of the video and C is the feature dimension of each frame. You can refer the readme for details.

tghim commented 2 years ago

Thank you for your reply!