不知道什么原因希望协助解决

[johndialys]

Traceback (most recent call last):
File "demo.py", line 16, in
model = create_model(opt)
File "/viton/Global-Flow-Local-Attention/model/init.py", line 32, in create_model
instance = model(opt)
File "/viton/Global-Flow-Local-Attention/model/pose_model.py", line 64, in init
norm='instance', activation='LeakyReLU', extractor_kz=opt.kernel_size)
File "/viton/Global-Flow-Local-Attention/model/networks/init.py", line 37, in define_g
return create_network(netG_cls, opt, **parameter_dic)
File "/viton/Global-Flow-Local-Attention/model/networks/init.py", line 28, in create_network
net.init_weights(opt.init_type)
File "/viton/Global-Flow-Local-Attention/model/networks/base_network.py", line 55, in init_weights
self.apply(init_func)
File "/root/anaconda3/envs/gflab/lib/python3.6/site-packages/torch/nn/modules/module.py", line 242, in apply
module.apply(fn)
File "/root/anaconda3/envs/gflab/lib/python3.6/site-packages/torch/nn/modules/module.py", line 242, in apply
module.apply(fn)
File "/root/anaconda3/envs/gflab/lib/python3.6/site-packages/torch/nn/modules/module.py", line 242, in apply
module.apply(fn)
[Previous line repeated 1 more time]
File "/root/anaconda3/envs/gflab/lib/python3.6/site-packages/torch/nn/modules/module.py", line 243, in apply
fn(self)
File "/viton/Global-Flow-Local-Attention/model/networks/base_network.py", line 47, in init_func
init.orthogonal_(m.weight.data, gain=gain)
File "/root/anaconda3/envs/gflab/lib/python3.6/site-packages/torch/nn/init.py", line 356, in orthogonal_
q, r = torch.qr(flattened)
RuntimeError: cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/generic/THCTensorMathPairwise.cu:225

[zhangle9012]

CUDA version may not match torch version
see in https://pytorch.org/get-started/previous-versions/

[matrixlibing]

I have the same problem.
My machine environment is as follows:
CUDA Driver Version > CUDA Toolkit == Pytorch needed.

`(gfla) [gfla@k8s-master gfla]$ conda list | grep cuda
cuda90 1.0 h6433d27_0 pytorch
pytorch 1.0.0 py3.7_cuda9.0.176_cudnn7.4.1_1 pytorch

(gfla) [gfla@k8s-master gfla]$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2017 NVIDIA Corporation
Built on Fri_Sep__1_21:08:03_CDT_2017
Cuda compilation tools, release 9.0, V9.0.176

(gfla) [gfla@k8s-master gfla]$ nvidia-smi
Thu Dec 22 15:26:05 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.67 Driver Version: 418.67 CUDA Version: 10.1 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Tesla T4 Off | 00000000:3B:00.0 Off | 0 |
| N/A 45C P0 29W / 70W | 11535MiB / 15079MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 1 Tesla T4 Off | 00000000:AF:00.0 Off | 0 |
| N/A 43C P0 29W / 70W | 12174MiB / 15079MiB | 0% Default |
+-------------------------------+----------------------+----------------------+`