*** RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

okay, this is the entire error log;
(sapiens-full) sahmadzai@nextcloud:~/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose$ python3 demo/image_demo.py /home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TAS KS/sapiens/pose/INPUT/img.jpg /home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/configs/sapiens_pose/coco_wholebody/sapiens_0.3b-210e_coco_wholebody-1024x768.py /home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/sapiens_host/pose/checkpoints/sapiens_1b/sapiens_1b_goliath_best_goliath_AP_640.pth?download=true --out-file /home/ sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/OUTPUT/pose_image.jpg

/home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/albumentations/init.py:13: UserWarning: A new version of Albumentations is available: 1.4.15 (you have 1.4.14). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
check_for_updates()
/home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/torchvision/datapoints/init.py:12: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 namespa ces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://gith ub.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You ca n silence this warning by calling torchvision.disable_beta_transforms_warning().
warnings.warn(_BETA_TRANSFORMS_WARNING)
/home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/torchvision/transforms/v2/init.py:54: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 name spaces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://g ithub.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You can silence this warning by calling torchvision.disable_beta_transforms_warning().
warnings.warn(_BETA_TRANSFORMS_WARNING)
No module named 'airstore'
Warning! Make sure you are not training.
Loads checkpoint by local backend from path: /home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/sapiens_host/pose/checkpoints/sapiens_1b/sapiens_1b_goliath_best_goliat h_AP_640.pth?download=true
09/16 13:28:48 - mmengine - INFO - Resize the pos_embed shape from torch.Size([1, 3072, 1536]) to torch.Size([1, 3072, 1024]).
The model and loaded state dict do not match exactly

size mismatch for backbone.pos_embed: copying a param with shape torch.Size([1, 3119, 1536]) from checkpoint, the shape in current model is torch.Size([1, 3072, 1024]).
size mismatch for backbone.patch_embed.projection.weight: copying a param with shape torch.Size([1536, 3, 16, 16]) from checkpoint, the shape in current model is torch.Size([1024, 3, 16, 16 ]).
size mismatch for backbone.patch_embed.projection.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.0.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.0.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.0.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]).
size mismatch for backbone.layers.0.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]).
size mismatch for backbone.layers.0.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]).
size mismatch for backbone.layers.0.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.0.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.0.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.0.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]).
size mismatch for backbone.layers.0.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for backbone.layers.0.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]).
size mismatch for backbone.layers.0.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.1.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.layers.1.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.1.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.1.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.1.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.1.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.2.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.2.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.2.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.2.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.2.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.2.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.2.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.2.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.2.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.2.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.2.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.2.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.3.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.3.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.3.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.3.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.3.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.3.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.3.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.3.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.3.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.3.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.3.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.3.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.4.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.4.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.4.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.4.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.4.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.4.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.10.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.10.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.10.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.10.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.10.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.10.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.11.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.11.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.11.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.11.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.11.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.11.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.11.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.11.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.11.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.11.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.11.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.11.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.12.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.12.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.12.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.12.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.12.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.12.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.12.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.12.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.12.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.12.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.12.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.12.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.13.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.13.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.13.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.13.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.13.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.13.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.13.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.13.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.13.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.14.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.14.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.14.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.15.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.15.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.15.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.15.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.15.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.15.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.15.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.15.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.15.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.15.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.15.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.15.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.16.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.16.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.16.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.16.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.16.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.16.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.16.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.16.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.16.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.16.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.16.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.16.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.17.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.17.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.17.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.17.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.17.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.17.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.17.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.17.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.17.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.17.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.17.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.17.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.18.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.18.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.18.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.18.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.18.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.18.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.18.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.18.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.18.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.18.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.18.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.18.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.19.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.19.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.19.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.19.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.19.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.19.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.19.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.19.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.19.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.19.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.19.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.19.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.20.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.20.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.20.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.20.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.20.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.20.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.20.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.20.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.20.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.20.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.20.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.20.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.21.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.21.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.21.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.21.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.21.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.21.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.21.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.21.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.21.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.21.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.21.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.21.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.22.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.22.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.22.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.22.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.22.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.22.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.22.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.22.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.22.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.22.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]). size mismatch for backbone.layers.22.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]). size mismatch for backbone.layers.22.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.23.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.23.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.23.attn.qkv.weight: copying a param with shape torch.Size([4608, 1536]) from checkpoint, the shape in current model is torch.Size([3072, 1024]). size mismatch for backbone.layers.23.attn.qkv.bias: copying a param with shape torch.Size([4608]) from checkpoint, the shape in current model is torch.Size([3072]). size mismatch for backbone.layers.23.attn.proj.weight: copying a param with shape torch.Size([1536, 1536]) from checkpoint, the shape in current model is torch.Size([1024, 1024]). size mismatch for backbone.layers.23.attn.proj.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.23.ln2.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.23.ln2.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.layers.23.ffn.layers.0.0.weight: copying a param with shape torch.Size([6144, 1536]) from checkpoint, the shape in current model is torch.Size([4096, 1024]). size mismatch for backbone.layers.23.ffn.layers.0.0.bias: copying a param with shape torch.Size([6144]) from checkpoint, the shape in current model is torch.Size([4096]).
size mismatch for backbone.layers.23.ffn.layers.1.weight: copying a param with shape torch.Size([1536, 6144]) from checkpoint, the shape in current model is torch.Size([1024, 4096]).
size mismatch for backbone.layers.23.ffn.layers.1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for backbone.ln1.weight: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for backbone.ln1.bias: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for head.deconv_layers.0.weight: copying a param with shape torch.Size([1536, 768, 4, 4]) from checkpoint, the shape in current model is torch.Size([1024, 768, 4, 4]). size mismatch for head.final_layer.weight: copying a param with shape torch.Size([308, 768, 1, 1]) from checkpoint, the shape in current model is torch.Size([133, 768, 1, 1]). size mismatch for head.final_layer.bias: copying a param with shape torch.Size([308]) from checkpoint, the shape in current model is torch.Size([133]). unexpected key in source state_dict: backbone.layers.24.ln1.weight, backbone.layers.24.ln1.bias, backbone.layers.24.attn.qkv.weight, backbone.layers.24.attn.qkv.bias, backbone.layers.24.att n.proj.weight, backbone.layers.24.attn.proj.bias, backbone.layers.24.ln2.weight, backbone.layers.24.ln2.bias, backbone.layers.24.ffn.layers.0.0.weight, backbone.layers.24.ffn.layers.0.0.bia s, backbone.layers.24.ffn.layers.1.weight, backbone.layers.24.ffn.layers.1.bias, backbone.layers.25.ln1.weight, backbone.layers.25.ln1.bias, backbone.layers.25.attn.qkv.weight, backbone.lay ers.25.attn.qkv.bias, backbone.layers.25.attn.proj.weight, backbone.layers.25.attn.proj.bias, backbone.layers.25.ln2.weight, backbone.layers.25.ln2.bias, backbone.layers.25.ffn.layers.0.0.w eight, backbone.layers.25.ffn.layers.0.0.bias, backbone.layers.25.ffn.layers.1.weight, backbone.layers.25.ffn.layers.1.bias, backbone.layers.26.ln1.weight, backbone.layers.26.ln1.bias, back bone.layers.26.attn.qkv.weight, backbone.layers.26.attn.qkv.bias, backbone.layers.26.attn.proj.weight, backbone.layers.26.attn.proj.bias, backbone.layers.26.ln2.weight, backbone.layers.26.l n2.bias, backbone.layers.26.ffn.layers.0.0.weight, backbone.layers.26.ffn.layers.0.0.bias, backbone.layers.26.ffn.layers.1.weight, backbone.layers.26.ffn.layers.1.bias, backbone.layers.27.l n1.weight, backbone.layers.27.ln1.bias, backbone.layers.27.attn.qkv.weight, backbone.layers.27.attn.qkv.bias, backbone.layers.27.attn.proj.weight, backbone.layers.27.attn.proj.bias, backbon e.layers.27.ln2.weight, backbone.layers.27.ln2.bias, backbone.layers.27.ffn.layers.0.0.weight, backbone.layers.27.ffn.layers.0.0.bias, backbone.layers.27.ffn.layers.1.weight, backbone.layer s.27.ffn.layers.1.bias, backbone.layers.28.ln1.weight, backbone.layers.28.ln1.bias, backbone.layers.28.attn.qkv.weight, backbone.layers.28.attn.qkv.bias, backbone.layers.28.attn.proj.weight , backbone.layers.28.attn.proj.bias, backbone.layers.28.ln2.weight, backbone.layers.28.ln2.bias, backbone.layers.28.ffn.layers.0.0.weight, backbone.layers.28.ffn.layers.0.0.bias, backbone.l ayers.28.ffn.layers.1.weight, backbone.layers.28.ffn.layers.1.bias, backbone.layers.29.ln1.weight, backbone.layers.29.ln1.bias, backbone.layers.29.attn.qkv.weight, backbone.layers.29.attn.q kv.bias, backbone.layers.29.attn.proj.weight, backbone.layers.29.attn.proj.bias, backbone.layers.29.ln2.weight, backbone.layers.29.ln2.bias, backbone.layers.29.ffn.layers.0.0.weight, backbo ne.layers.29.ffn.layers.0.0.bias, backbone.layers.29.ffn.layers.1.weight, backbone.layers.29.ffn.layers.1.bias, backbone.layers.30.ln1.weight, backbone.layers.30.ln1.bias, backbone.layers.3 0.attn.qkv.weight, backbone.layers.30.attn.qkv.bias, backbone.layers.30.attn.proj.weight, backbone.layers.30.attn.proj.bias, backbone.layers.30.ln2.weight, backbone.layers.30.ln2.bias, back bone.layers.30.ffn.layers.0.0.weight, backbone.layers.30.ffn.layers.0.0.bias, backbone.layers.30.ffn.layers.1.weight, backbone.layers.30.ffn.layers.1.bias, backbone.layers.31.ln1.weight, ba ckbone.layers.31.ln1.bias, backbone.layers.31.attn.qkv.weight, backbone.layers.31.attn.qkv.bias, backbone.layers.31.attn.proj.weight, backbone.layers.31.attn.proj.bias, backbone.layers.31.l n2.weight, backbone.layers.31.ln2.bias, backbone.layers.31.ffn.layers.0.0.weight, backbone.layers.31.ffn.layers.0.0.bias, backbone.layers.31.ffn.layers.1.weight, backbone.layers.31.ffn.laye rs.1.bias, backbone.layers.32.ln1.weight, backbone.layers.32.ln1.bias, backbone.layers.32.attn.qkv.weight, backbone.layers.32.attn.qkv.bias, backbone.layers.32.attn.proj.weight, backbone.la yers.32.attn.proj.bias, backbone.layers.32.ln2.weight, backbone.layers.32.ln2.bias, backbone.layers.32.ffn.layers.0.0.weight, backbone.layers.32.ffn.layers.0.0.bias, backbone.layers.32.ffn. layers.1.weight, backbone.layers.32.ffn.layers.1.bias, backbone.layers.33.ln1.weight, backbone.layers.33.ln1.bias, backbone.layers.33.attn.qkv.weight, backbone.layers.33.attn.qkv.bias, back bone.layers.33.attn.proj.weight, backbone.layers.33.attn.proj.bias, backbone.layers.33.ln2.weight, backbone.layers.33.ln2.bias, backbone.layers.33.ffn.layers.0.0.weight, backbone.layers.33. ffn.layers.0.0.bias, backbone.layers.33.ffn.layers.1.weight, backbone.layers.33.ffn.layers.1.bias, backbone.layers.34.ln1.weight, backbone.layers.34.ln1.bias, backbone.layers.34.attn.qkv.we ight, backbone.layers.34.attn.qkv.bias, backbone.layers.34.attn.proj.weight, backbone.layers.34.attn.proj.bias, backbone.layers.34.ln2.weight, backbone.layers.34.ln2.bias, backbone.layers.3 4.ffn.layers.0.0.weight, backbone.layers.34.ffn.layers.0.0.bias, backbone.layers.34.ffn.layers.1.weight, backbone.layers.34.ffn.layers.1.bias, backbone.layers.35.ln1.weight, backbone.layers .35.ln1.bias, backbone.layers.35.attn.qkv.weight, backbone.layers.35.attn.qkv.bias, backbone.layers.35.attn.proj.weight, backbone.layers.35.attn.proj.bias, backbone.layers.35.ln2.weight, ba ckbone.layers.35.ln2.bias, backbone.layers.35.ffn.layers.0.0.weight, backbone.layers.35.ffn.layers.0.0.bias, backbone.layers.35.ffn.layers.1.weight, backbone.layers.35.ffn.layers.1.bias, ba ckbone.layers.36.ln1.weight, backbone.layers.36.ln1.bias, backbone.layers.36.attn.qkv.weight, backbone.layers.36.attn.qkv.bias, backbone.layers.36.attn.proj.weight, backbone.layers.36.attn. proj.bias, backbone.layers.36.ln2.weight, backbone.layers.36.ln2.bias, backbone.layers.36.ffn.layers.0.0.weight, backbone.layers.36.ffn.layers.0.0.bias, backbone.layers.36.ffn.layers.1.weig ht, backbone.layers.36.ffn.layers.1.bias, backbone.layers.37.ln1.weight, backbone.layers.37.ln1.bias, backbone.layers.37.attn.qkv.weight, backbone.layers.37.attn.qkv.bias, backbone.layers.3 7.attn.proj.weight, backbone.layers.37.attn.proj.bias, backbone.layers.37.ln2.weight, backbone.layers.37.ln2.bias, backbone.layers.37.ffn.layers.0.0.weight, backbone.layers.37.ffn.layers.0. 0.bias, backbone.layers.37.ffn.layers.1.weight, backbone.layers.37.ffn.layers.1.bias, backbone.layers.38.ln1.weight, backbone.layers.38.ln1.bias, backbone.layers.38.attn.qkv.weight, backbon e.layers.38.attn.qkv.bias, backbone.layers.38.attn.proj.weight, backbone.layers.38.attn.proj.bias, backbone.layers.38.ln2.weight, backbone.layers.38.ln2.bias, backbone.layers.38.ffn.layers. 0.0.weight, backbone.layers.38.ffn.layers.0.0.bias, backbone.layers.38.ffn.layers.1.weight, backbone.layers.38.ffn.layers.1.bias, backbone.layers.39.ln1.weight, backbone.layers.39.ln1.bias, backbone.layers.39.attn.qkv.weight, backbone.layers.39.attn.qkv.bias, backbone.layers.39.attn.proj.weight, backbone.layers.39.attn.proj.bias, backbone.layers.39.ln2.weight, backbone.layers .39.ln2.bias, backbone.layers.39.ffn.layers.0.0.weight, backbone.layers.39.ffn.layers.0.0.bias, backbone.layers.39.ffn.layers.1.weight, backbone.layers.39.ffn.layers.1.bias

/home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/mmengine/visualization/visualizer.py:196: UserWarning: Failed to add <class 'mmengine.visualization.vis_backend.Loca lVisBackend'>, please provide the save_dir argument.
warnings.warn(f'Failed to add {vis_backend.class}, ' /home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/mmengine/visualization/visualizer.py:196: UserWarning: Failed to add <class 'mmengine.visualization.vis_backend.Tens orboardVisBackend'>, please provide the save_dir argument.
warnings.warn(f'Failed to add {vis_backend.class}, ' ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [32,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [33,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [34,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [35,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [36,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [37,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [38,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [39,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [40,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [41,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [42,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [43,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [44,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [45,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [46,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [47,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [48,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [49,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [50,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [47,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [48,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [49,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [50,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [51,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [52,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [53,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [54,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [55,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [56,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [57,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [58,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [59,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [60,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [61,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [62,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. ../aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [10264,0,0], thread: [63,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed. Traceback (most recent call last): File "demo/image_demo.py", line 110, in main() File "demo/image_demo.py", line 90, in main batch_results = inference_topdown(model, args.img) File "/home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/mmpose/apis/inference.py", line 201, in inference_topdown results = model.test_step(batch) File "/home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 145, in test_step return self._run_forward(data, mode='predict') # type: ignore File "/home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 361, in _run_forward results = self(*data, mode=mode) File "/home/sahmadzai/miniconda3/envs/sapiens-full/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, **kwargs) File "/home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/mmpose/models/pose_estimators/base.py", line 146, in forward return self.predict(inputs, data_samples) File "/home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/mmpose/models/pose_estimators/topdown.py", line 215, in predict preds = self.head.predict(feats, data_samples, test_cfg=self.test_cfg) File "/home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/mmpose/models/heads/heatmap_heads/heatmap_head.py", line 290, in predict preds = self.decode(batch_heatmaps) File "/home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/mmpose/models/heads/base_head.py", line 74, in decode batch_output_np = to_numpy(batch_outputs, unzip=True) File "/home/sahmadzai/00_PROJECT/00_FULLBODY/SAPIENS_H_R_M_HUMAN_TASKS/sapiens/pose/mmpose/utils/tensor_utils.py", line 35, in to_numpy x.cpu() RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

facebookresearch / sapiens