RuntimeError: CUDA error: no kernel image is available for execution on the device

[eunseon02]

(CenterPose) root@eunseon-ASUS:~/CenterPose/src# python demo.py --demo /root/CenterPose/images/CenterPose/chair/00000.png --arch dlav1_34 --load_model ../models/CenterPose/chair_v1_140.pth 
/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/sklearn/utils/linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.
  FutureWarning)
Fix size testing.
training chunk_sizes: [1]
The output will be saved to  /root/CenterPose/src/lib/../../exp/object_pose/default
heads {'hm': 1, 'wh': 2, 'hps': 16, 'reg': 2, 'hm_hp': 8, 'hp_offset': 2, 'scale': 3}
Creating model...
Downloading: "http://dl.yf.io/dla/models/imagenet/dla34-ba72cf86.pth" to /root/.cache/torch/checkpoints/dla34-ba72cf86.pth
100%|################################################| 63228658/63228658 [00:39<00:00, 1594112.61it/s]
loaded ../models/CenterPose/chair_v1_140.pth, epoch 140
  THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=383 error=8 : invalid device function
Traceback (most recent call last):
  File "demo.py", line 156, in <module>
    demo(opt, meta)
  File "demo.py", line 83, in demo
    ret = detector.run(image_name, meta_inp=meta)
  File "/root/CenterPose/src/lib/detectors/base_detector.py", line 474, in run
    images, self.pre_images, pre_hms, pre_hm_hp, pre_inds, return_time=True)
  File "/root/CenterPose/src/lib/detectors/object_pose.py", line 135, in process
    output = self.model(images, pre_images, pre_hms, pre_hm_hp)[-1]
  File "/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/CenterPose/src/lib/models/networks/pose_dla_dcn.py", line 528, in forward
    x = self.base(x)
  File "/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/CenterPose/src/lib/models/networks/pose_dla_dcn.py", line 312, in forward
    x = self.base_layer(x)
  File "/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/torch/nn/modules/container.py", line 92, in forward
    input = module(input)
  File "/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/torch/nn/modules/activation.py", line 99, in forward
    return F.relu(input, inplace=self.inplace)
  File "/root/anaconda3/envs/CenterPose/lib/python3.6/site-packages/torch/nn/functional.py", line 941, in relu
    result = torch.relu_(input)

i using cuda 10.0, torch==1.11.0, torchvision==0.12.0

[loubron23]

I have the same problem. Have you solved it yet?

[eunseon02]

I have the same problem. Have you solved it yet?

not yet, Have you solved it?

[loubron23]

I have the same problem. Have you solved it yet?

not yet, Have you solved it?

yes, recently I've solved this problem. for me, it is because my gpu is rtx4070 and cuda is 11.6, which does not match the current torch1.1.0. Later, I used torch1.13.0 and the corresponding torchvision, and the code can run normally.