search

Huangying-Zhan / DF-VO

Depth and Flow for Visual Odometry
https://df-vo.readthedocs.io
MIT License
565 stars 117 forks source link

Got an error when running /apis/run.py #28

Open L-ED opened 3 years ago

L-ED commented 3 years ago

Hi everyone, when i running "python apis/run.py -d options/examples/default_configuration.yml" a have such error: My ubuntu, torch, cuda versions match with required.

File "apis/run.py", line 85, in vo.main() File "/workspace/DF-VO/libs/dfvo.py", line 373, in main self.deep_model_inference() File "/workspace/DF-VO/libs/dfvo.py", line 326, in deep_model_inference forward_backward=self.cfg.deep_flow.forward_backward) File "/workspace/DF-VO/libs/deep_models/deep_models.py", line 173, in forward_flow dataset=self.cfg.dataset) File "/workspace/DF-VO/libs/deep_models/flow/lite_flow_net/lite_flow.py", line 119, in inference_flow combined_flow_data = self.inference_no_grad(input_img1, input_img2) File "/workspace/DF-VO/envs/dfvo/lib/python3.6/site-packages/torch/autograd/grad_mode.py", line 43, in decorate_no_grad return func(*args, kwargs) File "/workspace/DF-VO/libs/deep_models/flow/deep_flow.py", line 169, in inference_no_grad return self.inference(img1, img2) File "/workspace/DF-VO/libs/deep_models/flow/lite_flow_net/lite_flow.py", line 77, in inference output = self.model(resized_img_list) File "/workspace/DF-VO/envs/dfvo/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, *kwargs) File "/workspace/DF-VO/libs/deep_models/flow/lite_flow_net/lite_flow_net.py", line 318, in forward tensorFlow = self.moduleRegularization[intLevel](tensorFirst[intLevel], tensorSecond[intLevel], tensorFeaturesFirst[intLevel], tensorFeaturesSecond[intLevel], tensorFlow) File "/workspace/DF-VO/envs/dfvo/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(input, kwargs) File "/workspace/DF-VO/libs/deep_models/flow/lite_flow_net/lite_flow_net.py", line 255, in forward tensorDist = self.moduleDist(self.moduleMain(torch.cat([ tensorDifference, tensorFlow - tensorFlow.view(tensorFlow.size(0), 2, -1).mean(2, True).view(tensorFlow.size(0), 2, 1, 1), self.moduleFeat(tensorFeaturesFirst) ], 1))) File "/workspace/DF-VO/envs/dfvo/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, *kwargs) File "/workspace/DF-VO/envs/dfvo/lib/python3.6/site-packages/torch/nn/modules/container.py", line 92, in forward input = module(input) File "/workspace/DF-VO/envs/dfvo/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(input, **kwargs) File "/workspace/DF-VO/envs/dfvo/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 338, in forward self.padding, self.dilation, self.groups) RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM

wenbinuser commented 3 years ago

i also faced this problem. Have you solved it yet?

arkinrc commented 2 years ago

same issue is here. @Huangying-Zhan any solution?

Thanks Regards arkin

arkinrc commented 2 years ago

its because of different version of Cuda as i think. Latest Nvidia GPU model doesnt support cuda9.0 and got this issue.

iamykkkk commented 2 years ago

I also met this problem, it is because the size of the pictures in kitti_odom is 1226*370, but in options/examples/default_configuration.yml ,the size of pictures is not the same number. I changed the text and it can run.

image: height: 370 # image height width: 1226 # image width ext: png # image file extension for data loading

LinkWithMe commented 1 year ago

I also met this problem, it is because the size of the pictures in kitti_odom is 1226*370, but in options/examples/default_configuration.yml ,the size of pictures is not the same number. I changed the text and it can run.

image: height: 370 # image height width: 1226 # image width ext: png # image file extension for data loading

Amazing and thanks!!!!!!!!!!!!!!!!!