CUDNN_STATUS_NOT_SUPPORTED

[mykeehu]

I trained a model. When I try to generate an image with the command below under Windows, I get an error. CUDA 12.1 is installed.

python src/inference_unpaired.py --model_path "output/woman256/checkpoints/model_10001.pkl" --input_image "data/woman256/test_A/2023-03-24 12.33.47 3065512818812758378_249162050.png" --prompt "picture of a woman" --direction "a2b" --output_dir "outputs" --image_prep "no_resize"

and error:

I:\img2img-turbo\venvi2i\lib\site-packages\torch\nn\modules\conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ..\aten\src\ATen\native\cudnn\Conv_v8.cpp:919.)
  return F.conv2d(input, weight, bias, self.stride,
I:\img2img-turbo\venvi2i\lib\site-packages\diffusers\models\attention_processor.py:1259: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
  hidden_states = F.scaled_dot_product_attention(