-
I could only get around 0.3 for class accuracy with the ground truth motion sequences using the provided pre-trained model files. Here are the logs:
==================== Replication 15 ============…
-
I wanted to run the test file with the config file named "2sagcn_80e_ntu60_xsub_keypoint_3d.py", but I didn't have the dataset in the correct format because an error was raised like this `running_mean…
-
Hi,
Many thanks for sharing the code. I met trouble when execute function getfeatures() -> get_relative_coordinates.
My understanding of this function is to calculate the displacements compared to 4…
-
Hi there,
Thanks for your interesting work. Can you provide the dataset file for the NTU RGBD 60 cross view setting?
Regards,
Jinyang
-
Hi, I try to reproduce the PoseC3D with dataset NTU-RGBD
1. I downloaded the NTU-RGBD skeleton dataset via [link](https://github.com/shahroudy/NTURGB-D)
2. Then I convert the skeleton data to yo…
-
### Firstly, thank very much for your contribution. Your paper gave me a lot of inspiration.
But I still have some questions. I ran the source code again in my environment, but I can't achieve the sa…
-
I am training 2s-agcn.
Raw skeleton data are downloaded from [here](https://github.com/shahroudy/NTURGB-D).
Converted to mmaction2 format using `gen_ntu_rgbd_raw.py `.
So have two folders` xsub an…
-
我想在AI Studio平台 用AGCN去训练NTU-RGB+D数据集，后续会打算进一步处理该数据集，精简一些动作。可是下载的NTU-RGB+D数据集只有一个文件，看不到目录，请问，正确的使用AGCN 训练NTU-RGB+D的使用方式是什么呢？
-
thanks for your works!
when I run the command
mmskl configs/recognition/st_gcn_aaai18/ntu-rgbd-xview/test.yaml
I've got an error
AssertionError: Invalid device id
can you tell me how to solve …
-
Since the Top-Down approach is being used for human-pose estimation, the computational power required will increase as the number of people increase, will this model be still good enough for real-time…