| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| tp_h_48_256x192_enc6_d96_h192_mh1.pth | 2021-01-05 | 70.3 MB | |
| tp_r_256x192_enc4_d256_h1024_mh8.pth | 2021-01-05 | 24.1 MB | |
| tp_r_256x192_enc3_d256_h1024_mh8.pth | 2021-01-05 | 20.9 MB | |
| tp_h_48_256x192_enc4_d96_h192_mh1.pth | 2021-01-05 | 69.6 MB | |
| tp_h_32_256x192_enc4_d64_h128_mh1.pth | 2021-01-05 | 32.4 MB | |
| [COCO]_ pretrained weights on COCO dataset source code.tar.gz | 2020-12-31 | 1.9 kB | |
| [COCO]_ pretrained weights on COCO dataset source code.zip | 2020-12-31 | 2.3 kB | |
| README.md | 2020-12-31 | 377 Bytes | |
| Totals: 8 Items | 217.2 MB | 0 | |
We release the weights of TransPose-R-A3, TransPose-R-A4, TransPose-H-S, TransPose-H-A4, and TransPose-H-A6 models that have been trained on COCO train2017 dataset. They can either be stored locally in the github repo, or loadable by the function torch.hub.load_state_dict_from_url().