TypeError: type torch.cuda.FloatTensor not available. Torch not compiled with CUDA enabled.

yenchenlin / nerf-pytorch

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

MIT License

5.37k stars 1.04k forks source link

TypeError: type torch.cuda.FloatTensor not available. Torch not compiled with CUDA enabled. #48

Closed ohjarwa closed 2 years ago

ohjarwa commented 2 years ago

detail on traceback： Traceback (most recent call last): File "F:\fuxian\nerf-pytorch\run_nerf.py", line 876, in torch.set_default_tensor_type('torch.cuda.FloatTensor') File "F:\Program\Anaconda3\lib\site-packages\torch__init__.py", line 321, in set_default_tensor_type _C._set_default_tensor_type(t)

This error occurs after ' python run_nerf.py --config configs/lego.txt' How to solve it?

ohjarwa commented 2 years ago

check torch version in base environment