search

NVlabs / curobo

CUDA Accelerated Robot Library
https://curobo.org
Other
796 stars 125 forks source link

Error while running torch_layers_example.py #304

Closed jeonsuhyun closed 5 months ago

jeonsuhyun commented 5 months ago

I am having problem with example code 'torch_layers_example.py' My environment is Ubuntu20.04, python 3.10.14 pytorch 2.3.1 cuda 11.8 on conda.

While i was running the example code, this error occurred, and I tried to figure it out, but i couldn't.

Traceback (most recent call last): File "/home/suhyun/curobo/examples/torch_layers_example.py", line 169, in loss.backward() File "/home/suhyun/anaconda3/envs/curobo/lib/python3.10/site-packages/torch/_tensor.py", line 525, in backward torch.autograd.backward( File "/home/suhyun/anaconda3/envs/curobo/lib/python3.10/site-packages/torch/autograd/init.py", line 267, in backward _engine_run_backward( File "/home/suhyun/anaconda3/envs/curobo/lib/python3.10/site-packages/torch/autograd/graph.py", line 744, in _engine_run_backward return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass RuntimeError: Function PoseErrorBackward returned an invalid gradient at index 0 - got [512, 1, 3] but expected shape compatible with [512, 1, 1, 3]

How can i fix this error? Thanks.

balakumar-s commented 5 months ago

Thanks! This has been fixed in latest main.