center-group
center-group copied to clipboard
dvl-tum
Official PyTorch implementation of "The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation" (ICCV 21).
Thanks for your excellent study. The provided ckpt files are text after opening hyperlinks. Could you give me some suggestions to download pretrain models?
Sorry for bothering. I can't understand where is the [batch['pad_mask']](https://github.com/dvl-tum/center-group/blob/9e55c06bbc9c59f7eb3d86c847f9a7880c164165/centergroup/models/centergroup.py#L243) from? Is its definition from [results['pad_mask']](https://github.com/dvl-tum/center-group/blob/9e55c06bbc9c59f7eb3d86c847f9a7880c164165/centergroup/data/transforms.py#L222)? or, does it have something to do with the 'mask' in the following image?...
``` TRAINING FROM SCRATCH Use load_from_local loader NHEADS 4 NO WEIGHT SHARING!!! /anaconda3/envs/centergroup/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/ddp.py:20: LightningDeprecationWarning: The `pl.plugins.training_type.ddp.DDPPlugin` is deprecated in v1.6 and will be removed in v1.8. Use `pl.strategies.ddp.DDPStrategy` instead. rank_zero_deprecation(...
``` TRAINING FROM SCRATCH NHEADS 4 NO WEIGHT SHARING!!! /environment/miniconda3/lib/python3.7/site-packages/pytorch_lightning/plugins/training_type/ddp.py:21: LightningDeprecationWarning: The `pl.plugins.training_type.ddp.DDPPlugin` is deprecated in v1.6 and will be removed in v1.8. Use `pl.strategies.ddp.DDPStrategy` instead. "The `pl.plugins.training_type.ddp.DDPPlugin` is deprecated...
