jeonhobeom

This change is essential for migration to the latest pytorch. Thank you for saving my time. 😄 @nakosung

+1 Same error

@lmc2000 Use modified version in my branch https://github.com/HoBeom/mmaction2/blob/789c12d53ab830c8a7bfc01e34ae9ef777d8f775/mmaction/evaluation/metrics/acc_metric.py#L272-L300

Also I got error in RGBPoseHead in training on last batch with less then batch size. https://github.com/open-mmlab/mmaction2/blob/4d6c93474730cad2f25e51109adcf96824efc7a3/mmaction/models/heads/rgbpose_head.py#L117-L118 can be changed as follows to check the size correctly. ``` elif labels.dim()...

Thank you for your quick comments. I've tested your other screensaver, [multiclock](https://github.com/amiantos/multiclock), and it doesn't exhibit the same high CPU usage issue. This makes me wonder if the underlying codebase...

**Use `custom_2d_skeleton.py`**: Utilize the [custom_2d_skeleton.py](https://github.com/kennymckormick/pyskl/blob/main/tools/data/custom_2d_skeleton.py) script to generate a custom 2D skeleton dataset from your prepared video dataset.

The experiments were conducted in 2D coordinates, and the code isn't optimized for 3D. However, I have experience adapting it for 3D applications. By converting 25 3-dimensional keypoints into xy,...

@seekFire 3D coordinates as [[x0, y0, z0], [x1, y1, z0] ... [xn, yn, zn]] are trasnform in 2D as [[x0, y0]... [ xn, yn], [x0, z0]...[xn, zn], [y0, z0]...[yn, zn]]....

@dvskabangira The methods mentioned above are literally “tricks”. No paper has yet discussed the results of experiments by projecting 3D coordinates into 2D heatmap representation. However, I achieved high performance...

@dvskabangira The paper mentions that the projection takes place in the 2D image space and that the number of 3D keypoints matches the number of channels, thereby resulting in information...