AlphAction
AlphAction copied to clipboard
MVIG-SJTU
Spatio-Temporal Action Localization System
使用CPU的时候报以下错误： Loading action model weight from ../data/models/aia_models/resnet50_4x16f_baseline.pth. Action model weight successfully loaded. Loading tracking model.. Network successfully loaded Showing tracking progress bar (in fps). Other processes are running in the...
thanks for this great work!!! but I have a question, in the backbone ,you use FrozenBatchNorm3d: > self.running_mean.zero_() > self.running_var.fill_(1) set the running_mean to zero,var to1. but why not keep...
https://github.com/MVIG-SJTU/AlphAction/blob/db19364dd2b15905ae4b70a7acd9bb9b34ccb04b/alphaction/structures/bounding_box.py#L88-L89 Hi, Thanks for your awesome work. I noticed that you use `TO_REMOVE=1` when the box mode is converted from `xywh` to `xyxy`. I am confused by this. Would you...
Hi I have managed to install the project but I get segmentation fault. My environment is: Collecting environment information... PyTorch version: 1.7.1 Is debug build: False CUDA used to build...
Thanks for your interesting work! I want to get a light model of alphaction, so i want to change the backbone from resnet50 to resnet34. But i found if i...
Traceback (most recent call last): File "train_net.py", line 245, in main() File "train_net.py", line 235, in main args.no_head) File "train_net.py", line 98, in train mem_active, File "/home/fm-pc-lt-269/Fuse/AlphAction/alphaction/engine/trainer.py", line 40, in...
I want to understand , what is difference between realtime and non-realtime inference steps... can you please help me to understand?
Can we use this only for AVA dataset or can we also use this pretrained model for a JHMDB dataset ?
Hi there, Is it feasiable to copy the pretrained models to Baidu Netdisk, since GoogleDrive is not nice to the users from mainland. Regards,
(alph) user@user-Super-Server:/mnt/745425dc-5d5b-4490-9d38-57169dcb2ab3/wxl/AlphAction-master$ python demo/demo.py --video-path "demo/input/test4.avi" --output-path "demo/123" --cfg-path "./config_files/resnet101_8x8f_denseserial.yaml" --weight-path "./data/models/aia_models/resnet101_8x8f_denseserial.pth" --common-cate Starting video demo, video path: demo/input/test4.avi /home/user/anaconda3/envs/alph/lib/python3.8/site-packages/torch/nn/modules/container.py:552: UserWarning: Setting attributes on ParameterDict is not supported. warnings.warn("Setting attributes...
