ValueError: Expected a torch.device with a specified index or an integer, but got:cuda

[danielchiu615]

(barf-env) C:\Users\usera\bundle-adjusting-NeRF>python3 train.py --group=test --model=barf --yaml=barf_llff --name=fern --data.scene=fern --barf_c2f=[0.1,0.5] Process ID: 21644 [train.py] (PyTorch code for training NeRF/BARF) setting configurations... loading options/base.yaml... loading options/nerf_llff.yaml... loading options/barf_llff.yaml...

• H: 480
• W: 640
• arch:
  • density_activ: softplus
  • layers_feat: [None, 256, 256, 256, 256, 256, 256, 256, 256]
  • layers_rgb: [None, 128, 3]
  • posenc:
    • L_3D: 10
    • L_view: 4
  • skip: [4]
  • tf_init: True
• barf_c2f: [0.1, 0.5]
• batch_size: None
• camera:
  • model: perspective
  • ndc: False
  • noise: None
• cpu: False
• data:
  • augment:
  • center_crop: None
  • dataset: llff
  • image_size: [480, 640]
  • num_workers: 4
  • preload: True
  • root: None
  • scene: fern
  • train_sub: None
  • val_on_test: False
  • val_ratio: 0.1
  • val_sub: None
• device: cpu
• freq:
  • ckpt: 5000
  • scalar: 200
  • val: 2000
  • vis: 1000
• gpu: 0
• group: test
• load: None
• loss_weight:
  • render: 0
  • render_fine: None
• max_epoch: None
• max_iter: 200000
• model: barf
• name: fern
• nerf:
  • density_noise_reg: None
  • depth:
    • param: inverse
    • range: [1, 0]
  • fine_sampling: False
  • rand_rays: 2048
  • sample_intvs: 128
  • sample_intvs_fine: None
  • sample_stratified: True
  • setbg_opaque: None
  • view_dep: True
• optim:
  • algo: Adam
  • lr: 0.001
  • lr_end: 0.0001
  • lr_pose: 0.003
  • lr_pose_end: 1e-05
  • sched:
    • gamma: None
    • type: ExponentialLR
  • sched_pose:
    • gamma: None
    • type: ExponentialLR
  • test_iter: 100
  • test_photo: True
  • warmup_pose: None
• output_path: output/test/fern
• output_root: output
• resume: False
• seed: 0
• tb:
  • num_images: [4, 8]
• visdom:
  • cam_depth: 0.2
  • port: 9000
  • server: localhost

• yaml: barf_llff existing options file found (identical) Traceback (most recent call last): File "C:\Users\usera\bundle-adjusting-NeRF\train.py", line 32, in main() File "C:\Users\usera\bundle-adjusting-NeRF\train.py", line 18, in main with torch.cuda.device(opt.device): File "C:\Users\usera\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\torch\cuda__init.py", line 312, in init__ self.idx = _get_device_index(device='cuda') File "C:\Users\usera\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\torch\cuda_utils.py", line 36, in _get_device_index return _torch_get_device_index(device, optional, allow_cpu) File "C:\Users\usera\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\torch_utils.py", line 731, in _get_device_index raise ValueError( ValueError: Expected a torch.device with a specified index or an integer, but got:cuda

  I first typed git clone then followed the steps and stuck here I want to try this code with custom images with camera parameters Appreciate any help!

[chenhsuanlin]

Hi @danielchiu615, the device in the config is cpu, which means your Pytorch is not correctly supporting cuda. You may want to double-check your installation, and you can verify with torch.cuda.is_available().