This repo is great and I'm getting what looks like correct vanishing points from the TMM17 dataset thats popping up when running eval.py, but I am getting the below error whenever I run the code. Can't figure out for the life of me what the issue is, as I've installed all the correct versions of Pytorch, etc.
(CMT_Streetvision) PS C:\Users\domlimco\PycharmProjects\CMT_Streetvision\neurvps> python eval.py -d 0 C:\Users\domlimco\PycharmProjects\CMT_Streetvision\neurvps\logs\TMM17\config.yaml C:\Users\domlimco\PycharmProjects\CMT_Streetvision\neurvps\logs\TMM17\checkpoint_latest.pth.tar
✓ MSVC environment configured from: C:\Program Files (x86)\Microsoft Visual Studio\2022\BuildTools\VC\Auxiliary\Build\vcvars64.bat
<Box: {'io': {'augmentation_level': 2, 'datadir': 'data/tmm17/', 'dataset': 'TMM17', 'focal_length': 1.0, 'logdir': 'logs/', 'num_vpts': 1, 'num_workers': 4, 'resume_from': 'logs/2
00107-013044-14545f5-tmm17-bugfix-lr1e-4-long', 'tensorboard_port': 0, 'validation_debug': 0, 'validation_interval': 8000}, 'model': {'backbone': 'stacked_hourglass', 'batch_size':
8, 'conic_6x': False, 'depth': 4, 'fc_channel': 1024, 'im2col_step': 32, 'multires': [0.0051941870036646, 0.02004838034795, 0.0774278195486317, 0.299564810864565], 'num_blocks': 1
, 'num_stacks': 1, 'output_stride': 4, 'smp_multiplier': 2, 'smp_neg': 1, 'smp_pos': 1, 'smp_rnd': 3, 'upsample_scale': 1}, 'optim': {'amsgrad': True, 'lr': 0.0001, 'lr_decay_epoch': 60, 'max_epoch': 100, 'name': 'Adam', 'weight_decay': 0.0006}}>
Let's use 1 GPU(s)!
C:\Users\domlimco\PycharmProjects\CMT_Streetvision\neurvps\eval.py:142: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses
the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/
blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could
be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.ad
d_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
checkpoint = torch.load(args["<checkpoint>"])
nvalid: 275
0%| | 0/275 [00:00<?, ?it/s]C
:\Users\domlimco\AppData\Local\anaconda3\envs\CMT_Streetvision\Lib\site-packages\torch\functional.py:534: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\TensorShape.cpp:3596.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
error in deformable_im2col_cuda: (null)
0%|▌
This repo is great and I'm getting what looks like correct vanishing points from the TMM17 dataset thats popping up when running eval.py, but I am getting the below error whenever I run the code. Can't figure out for the life of me what the issue is, as I've installed all the correct versions of Pytorch, etc.