/home/ud202380282/.conda/envs/nerp/lib/python3.10/site-packages/torch/utils/data/dataloader.py:487: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 1, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
warnings.warn(_create_warning_msg(
ct_recon/pancs_4dct_phase6/slice24_img256_proj20_SIREN_512_256_8_L2_lr1e-05_encoder_gauss_scale4_size256
Creating directory: ./outputs/ct_recon/pancs_4dct_phase6/slice24_img256_proj20_SIREN_512_256_8_L2_lr1e-05_encoder_gauss_scale4_size256/images
Creating directory: ./outputs/ct_recon/pancs_4dct_phase6/slice24_img256_proj20_SIREN_512_256_8_L2_lr1e-05_encoder_gauss_scale4_size256/checkpoints
Load image: /home/ud202380282/NeRP/data/ct_data/pancs_4dct_phase6.npz
shape:torch.Size([256, 256, 1]) | min:0.000 | max:1.000 | mean:0.157 | std:0.222
cuda
/home/ud202380282/.conda/envs/nerp/lib/python3.10/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755897462/work/aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/home/ud202380282/.conda/envs/nerp/lib/python3.10/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755897462/work/aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
torch.Size([1, 256, 256, 2]) torch.Size([1, 256, 256, 1])
tensor([0.0000, 0.1571, 0.3142, 0.4712, 0.6283, 0.7854, 0.9425, 1.0996, 1.2566,
1.4137, 1.5708, 1.7279, 1.8850, 2.0420, 2.1991, 2.3562, 2.5133, 2.6704,
2.8274, 2.9845], device='cuda:0')
torch.Size([256, 256])
torch.Size([256, 256])
torch.Size([20])
torch.Size([20])
Traceback (most recent call last):
File "/home/ud202380282/NeRP/train_ct_recon.py", line 120, in
x_rot = x * torch.cos(thetas) - y * torch.sin(thetas)
RuntimeError: The size of tensor a (256) must match the size of tensor b (20) at non-singleton dimension 1H
Hi Liyue!
I try to run the code using the provided data but encounter the above problem.
It seems that torch.cos(thetas) and x can't be multiple because the dimension didn't match
/home/ud202380282/.conda/envs/nerp/lib/python3.10/site-packages/torch/utils/data/dataloader.py:487: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 1, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
warnings.warn(_create_warning_msg(
ct_recon/pancs_4dct_phase6/slice24_img256_proj20_SIREN_512_256_8_L2_lr1e-05_encoder_gauss_scale4_size256
Creating directory: ./outputs/ct_recon/pancs_4dct_phase6/slice24_img256_proj20_SIREN_512_256_8_L2_lr1e-05_encoder_gauss_scale4_size256/images
Creating directory: ./outputs/ct_recon/pancs_4dct_phase6/slice24_img256_proj20_SIREN_512_256_8_L2_lr1e-05_encoder_gauss_scale4_size256/checkpoints
Load image: /home/ud202380282/NeRP/data/ct_data/pancs_4dct_phase6.npz
shape:torch.Size([256, 256, 1]) | min:0.000 | max:1.000 | mean:0.157 | std:0.222
cuda
/home/ud202380282/.conda/envs/nerp/lib/python3.10/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755897462/work/aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/home/ud202380282/.conda/envs/nerp/lib/python3.10/site-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1646755897462/work/aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
torch.Size([1, 256, 256, 2]) torch.Size([1, 256, 256, 1])
tensor([0.0000, 0.1571, 0.3142, 0.4712, 0.6283, 0.7854, 0.9425, 1.0996, 1.2566,
1.4137, 1.5708, 1.7279, 1.8850, 2.0420, 2.1991, 2.3562, 2.5133, 2.6704,
2.8274, 2.9845], device='cuda:0')
torch.Size([256, 256])
torch.Size([256, 256])
torch.Size([20])
torch.Size([20])
Traceback (most recent call last):
File "/home/ud202380282/NeRP/train_ct_recon.py", line 120, in
x_rot = x * torch.cos(thetas) - y * torch.sin(thetas)
RuntimeError: The size of tensor a (256) must match the size of tensor b (20) at non-singleton dimension 1H
Hi Liyue!
I try to run the code using the provided data but encounter the above problem.
It seems that torch.cos(thetas) and x can't be multiple because the dimension didn't match