Thanks for your error report and we appreciate it a lot. If you feel we have help you, give us a STAR! 😆 Checklist I have searched related issues but cannot get the expected help. The bug has not been fixed in the latest version. Describe the bug In the mmaction/utils/typing.py of mmaction2 1.x, t...

Thanks for your error report and we appreciate it a lot. If you feel we have help you, give us a STAR! 😆 Checklist I have searched related issues but cannot get the expected help. The bug has not been fixed in the latest version. Describe the bug I try to use the 1.x version in my work, but I foun...

Hi guys, Can you tell me what is the batch_size used on the fine-tuning of I3D and TimeSformer? If not, can you tell me where to find this information? The batch sizes of both models might still be default since I did not change it.

I am re-implementing grad-cam algorithms for slowfast model, following the gradcam demo provided by MMAction2 (MMAction2 GradCAM utils only). Here are my codes. %cd /content/mmaction2 %cd checkpoints !wget https://download.openmmlab.com/mmaction/recognition/slowfast/slowfast_prebn_r50_4x16x1_256e_...

Hi, I am trying to concat RGB and Flow features for activitynet using activitynet_feature_postprocessing.py for 1 single video. I reduced this pool = multiprocessing.Pool(1) from 32 to 1, as I was getting a paging error on windows. The paths are correct. But I am getting the following error. >pyt...

Thanks for your error report and we appreciate it a lot. If you feel we have help you, give us a STAR! 😆 Checklist I have searched related issues but cannot get the expected help. The bug has not been fixed in the latest version. Describe the bug A clear and concise description of what the bug is....

I downloaded the dev-1.x version of mmaction2 and the 3.x version of mmdetection, and ran demo_skeleton.py and reported Failed to import inference_detector and init_detector from mmdet.apis. These apis are required in this inference api! environment： mmcv: 2.0.0rc3 (the dev-1.x version of mmacti...

I run the code as instruments of BSN and BMN successfully, but when I run the code: python tools/test.py configs/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature.py work_dirs/bsn_400x100_20e_1x16_activitynet_feature/tem_epoch_20.pth --eval [email protected] --out work_dirs/bsn_400x100_20e_1x16_acti...

Check List I have read related issues, such as 'Worse results after train on custom classes?', but cannot get the expected help. my custom dataset and configuration I uploaded these a day before on issue Result Yesterday, I succeed to inference walking pedestrian video on SlowFast abd SlowOnly confi...

Hi! I want to use DVC for logging metrics. I found Dvcloggerhook in master branch and I need help for adaptation for 1.x branch. At this time my code looks like: from pathlib import Path from typing import Optional from mmengine.hooks import Hook from mmengine.runner import Runner from mmaction.re...