search

megvii-research / Sobolev_INRs

[ECCV 2022] The official experimental code of "Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives"
MIT License
30 stars 2 forks source link

return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass #1

Open XiangFeng66 opened 2 years ago

XiangFeng66 commented 2 years ago

when I run this code ,I have this question Traceback (most recent call last): File "D:\软件\pycharm专业版\PyCharm 2022.1.3\plugins\python\helpers\pydev\pydevd.py", line 1491, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "D:\软件\pycharm专业版\PyCharm 2022.1.3\plugins\python\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "D:/科研/Soblev_INrs/Sobolev_INRs-main/Experiments/inverse_rendering/train.py", line 696, in train() File "D:/科研/Soblev_INrs/Sobolev_INRs-main/Experiments/inverse_rendering/train.py", line 613, in train der_loss = der_mse(rgb, coordinate_s, target_grad_s) File "D:\科研\Soblev_INrs\Sobolev_INRs-main\Experiments\inverse_rendering\loss.py", line 15, in der_mse pred_grad_r = diff_operators.gradient( File "D:\科研\Soblev_INrs\Sobolev_INRs-main\Experiments\inverse_rendering\diff_operators.py", line 7, in gradient grad = torch.autograd.grad(y, [x], grad_outputs=grad_outputs, create_graph=True)[0] File "D:\Anaconda\envs\fengxiangNerf\lib\site-packages\torch\autograd__init__.py", line 276, in grad return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass RuntimeError: CUDA out of memory. Tried to allocate 64.00 MiB (GPU 0; 6.00 GiB total capacity; 5.17 GiB already allocated; 0 bytes free; 5.31 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try setting maxsplit

I don't know the reason why this code have question

wtyuan96 commented 2 years ago

Sorry for the late reply. The reason for this RuntimeError is that your GPU memory is not large enough, you can try to run this code on GPU with larger memory.