SwinTransformer / Video-Swin-Transformer

This is an official implementation for "Video Swin Transformers".
https://arxiv.org/abs/2106.13230
Apache License 2.0
1.46k stars 200 forks source link

Performance Reproducing of Swin-S #5

Closed JaminFong closed 3 years ago

JaminFong commented 3 years ago

Hi, Thanks for your great work. I'm trying to reproducing the performance of Swin-S on K-400. Using the released checkpoint for evaluation, I got an 80.11% accuracy; Evaluating the Swin-S model trained by myself, I got an 80.35% accuracy (still ~0.2% worse than the paper reported one). I wonder if anything is wrong. I doubt different validation data causes this as some videos are missing in the current K-400 dataset. My validation set contains 19,870 videos and the training set contains 239,687 videos, and how about the one you use? Thanks a lot in advance. Best.

hust-nj commented 3 years ago

Hi, thanks for your interest, we share the kinetics400 annotation here: https://github.com/SwinTransformer/storage/releases/tag/v1.0.6