AlphAction
AlphAction copied to clipboard
MVIG-SJTU
Spatio-Temporal Action Localization System
Hello author, I am also doing this task. I would like to ask if you can provide the detection person box of UCF24 using Faster RCNN in this paper? Thanks...
Using `resnet50_4x16f_baseline.yaml` and `resnet101_8x8f_baseline.yaml`, I have the following error as `RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [2, 1024]], which...
Thanks for your excellent work and your codebase! I have a coding quesion [here](https://github.com/MVIG-SJTU/AlphAction/blob/db19364dd2b15905ae4b70a7acd9bb9b34ccb04b/alphaction/modeling/roi_heads/action_head/IA_structure.py#L267). I wonder what the significance of "-5 * math.log(10)" is. Is that an empirical optimal init...
May I know how much time requires to training the model (say 8 GPUs)? Thanks a lot!
Hi. My system has 1 GPU. I was able to run the demo code on my own video. Am I able to do training and inference with 1 GPU? What...
I was successful in converting JDE tracking model to tensorRT as the input_shapes to model is clearn (1, 3, 608, 1088). But for action model, feature extraction inputs to model...
Hi. I have cuda 10.2 and installed pytorch with cuda 10.2 but get below error: How to solve it? What is the issue? (alphaction1) s438763@hcc3:/data/Sahar5/AlphAction-master$ python -c 'from torch.utils.collect_env import...
What is the reason for this error when AlphaAction is debugged? File "/workspace/Alpha Action/alphaction/layers/roi_align_3d.py", line 7, in import alphaction._custom_cuda_ext as _C ModuleNotFoundError: No module named 'alphaction._custom_cuda_ext'
