search

charlesq34 / pointnet

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Other
4.64k stars 1.44k forks source link

how to use cpu #315

Closed nidhinsoni closed 3 weeks ago

nidhinsoni commented 3 weeks ago

The number of training data is: 13998 The number of test data is: 2874 Traceback (most recent call last): File "D:\Python\myenv\code\pointnet2_pytorch\Pointnet_Pointnet2_pytorch\train_partseg.py", line 306, in main(args) File "D:\Python\myenv\code\pointnet2_pytorch\Pointnet_Pointnet2_pytorch\train_partseg.py", line 119, in main classifier = MODEL.get_model(num_part, normal_channel=args.normal).cuda() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Python\myenv\Lib\site-packages\torch\nn\modules\module.py", line 915, in cuda return self._apply(lambda t: t.cuda(device)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Python\myenv\Lib\site-packages\torch\nn\modules\module.py", line 779, in _apply module._apply(fn) File "D:\Python\myenv\Lib\site-packages\torch\nn\modules\module.py", line 779, in _apply module._apply(fn) File "D:\Python\myenv\Lib\site-packages\torch\nn\modules\module.py", line 779, in _apply module._apply(fn) [Previous line repeated 1 more time] File "D:\Python\myenv\Lib\site-packages\torch\nn\modules\module.py", line 804, in _apply param_applied = fn(param) ^^^^^^^^^ File "D:\Python\myenv\Lib\site-packages\torch\nn\modules\module.py", line 915, in return self._apply(lambda t: t.cuda(device)) ^^^^^^^^^^^^^^ File "D:\Python\myenv\Lib\site-packages\torch\cuda__init__.py", line 284, in _lazy_init raise AssertionError("Torch not compiled with CUDA enabled") AssertionError: Torch not compiled with CUDA enabled.

When im trying to run train_partseg, i get this error. I know that it's trying to run with CUDA but i have a computer without a graphics card, hence i want to run it using cpu. when i checked the parser, the --use_cpu argument isnt there. What can i do?