search

zju3dv / clean-pvnet

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral
Apache License 2.0
402 stars 106 forks source link

testing run time error #219

Closed helloyuning closed 2 years ago

helloyuning commented 2 years ago

At first, thank for your sharing and woderful work I tried to run test cat model, but I got error as follows:

Load model: data/model/pvnet/cat/199.pth loading annotations into memory... Done (t=0.05s) creating index... index created! loading annotations into memory... Done (t=0.02s) creating index... index created! 0%| | 0/1002 [00:48<?, ?it/s] Traceback (most recent call last): File "run.py", line 276, in if name == 'main': File "run.py", line 78, in run_evaluate with torch.no_grad(): File "/home/ivclab/anaconda3/envs/pv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, kwargs) File "lib/networks/pvnet/resnet18.py", line 79, in forward x2s, x4s, x8s, x16s, x32s, xfc = self.resnet18_8s(x) File "/home/ivclab/anaconda3/envs/pv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, *kwargs) File "lib/networks/pvnet/resnet.py", line 203, in forward x2s = self.relu(x) File "/home/ivclab/anaconda3/envs/pv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(input, kwargs) File "/home/ivclab/anaconda3/envs/pv/lib/python3.7/site-packages/torch/nn/modules/activation.py", line 99, in forward return F.relu(input, inplace=self.inplace) File "/home/ivclab/anaconda3/envs/pv/lib/python3.7/site-packages/torch/nn/functional.py", line 941, in relu result = torch.relu_(input) RuntimeError: CUDA error: no kernel image is available for execution on the device

And I reinstall cuda, gcc, almost all the dependences, but It's still not working. Can you give me some advices? My environment: cuda = 9.0 gcc-5.4.0 and g++-5.4.0 python3.7

BoBoINVICTUS commented 2 years ago

Hello, I have the same problem as you, could you tell me how to solve this problem?

helloyuning commented 2 years ago

Hello, BoBoINVIDICUS. I solved this problem by changing pytorch version. GPU with compute capability 7 only support torch 10+ version, in my case, I have GPU with compute capability 8.6 is imcompatable with torch 10. So I think It is important to check the torch version supported by your GPU. Hope this can help you.

BoBoINVICTUS commented 2 years ago

Thank you very much for your reply. I will change my Pytorch version and try again. Wish you a nice day!

ShawanDeba commented 1 year ago

Thank you very much for your reply. I will change my Pytorch version and try again. Wish you a nice day!

Hey I have been facing the same problem. Torch Version:1.1.0 Cuda:1.12 NVIDIA GeForce RTX 4080