Error : CUDNN failure 4

[neoxedneox]

After clicking on live, the following error appears :

Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'cudnn_conv_algo_search': 'EXHAUSTIVE', 'device_id': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'has_user_compute_stream': '0', 'gpu_external_alloc': '0', 'enable_cuda_graph': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0'}, 'CPUExecutionProvider': {}}
find model: C:\Users\NeoX/.insightface\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'cudnn_conv_algo_search': 'EXHAUSTIVE', 'device_id': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'has_user_compute_stream': '0', 'gpu_external_alloc': '0', 'enable_cuda_graph': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0'}, 'CPUExecutionProvider': {}}
find model: C:\Users\NeoX/.insightface\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'cudnn_conv_algo_search': 'EXHAUSTIVE', 'device_id': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'has_user_compute_stream': '0', 'gpu_external_alloc': '0', 'enable_cuda_graph': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0'}, 'CPUExecutionProvider': {}}
find model: C:\Users\NeoX/.insightface\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'cudnn_conv_algo_search': 'EXHAUSTIVE', 'device_id': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'has_user_compute_stream': '0', 'gpu_external_alloc': '0', 'enable_cuda_graph': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0'}, 'CPUExecutionProvider': {}}
find model: C:\Users\NeoX/.insightface\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CUDAExecutionProvider': {'cudnn_conv_algo_search': 'EXHAUSTIVE', 'device_id': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'has_user_compute_stream': '0', 'gpu_external_alloc': '0', 'enable_cuda_graph': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0'}, 'CPUExecutionProvider': {}}
find model: C:\Users\NeoX/.insightface\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (640, 640)
2024-11-18 03:15:04.8553061 [E:onnxruntime:Default, cuda_call.cc:116 onnxruntime::CudaCall] CUDNN failure 4: CUDNN_STATUS_INTERNAL_ERROR ; GPU=0 ; hostname=DESKTOP-TG7I910 ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\nn\conv.cc ; line=335 ; expr=cudnnFindConvolutionForwardAlgorithmEx( GetCudnnHandle(context), s_.x_tensor, s_.x_data, s_.w_desc, s_.w_data, s_.conv_desc, s_.y_tensor, s_.y_data, 1, &algo_count, &perf, algo_search_workspace.get(), max_ws_size);
2024-11-18 03:15:04.8688189 [E:onnxruntime:, sequential_executor.cc:514 onnxruntime::ExecuteKernel] Non-zero status code returned while running FusedConv node. Name:'Conv_0' Status Message: CUDNN failure 4: CUDNN_STATUS_INTERNAL_ERROR ; GPU=0 ; hostname=DESKTOP-TG7I910 ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\nn\conv.cc ; line=335 ; expr=cudnnFindConvolutionForwardAlgorithmEx( GetCudnnHandle(context), s_.x_tensor, s_.x_data, s_.w_desc, s_.w_data, s_.conv_desc, s_.y_tensor, s_.y_data, 1, &algo_count, &perf, algo_search_workspace.get(), max_ws_size);
2024-11-18 03:15:04.8836061 [E:onnxruntime:Default, cuda_call.cc:116 onnxruntime::CudaCall] CUDA failure 700: an illegal memory access was encountered ; GPU=0 ; hostname=DESKTOP-TG7I910 ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_execution_provider.cc ; line=395 ; expr=cudaStreamSynchronize(static_cast<cudaStream_t>(stream_));
Exception in Tkinter callback
Traceback (most recent call last):
  File "C:\Users\NeoX\AppData\Local\Programs\Python\Python311\Lib\tkinter\__init__.py", line 1948, in __call__
    return self.func(*args)
           ^^^^^^^^^^^^^^^^
  File "G:\Deep-Live-Cam-main\env\Lib\site-packages\customtkinter\windows\widgets\ctk_button.py", line 554, in _clicked
    self._command()
  File "G:\Deep-Live-Cam-main\modules\ui.py", line 336, in <lambda>
    command=lambda: webcam_preview(
                    ^^^^^^^^^^^^^^^
  File "G:\Deep-Live-Cam-main\modules\ui.py", line 750, in webcam_preview
    create_webcam_preview(camera_index)
  File "G:\Deep-Live-Cam-main\modules\ui.py", line 809, in create_webcam_preview
    source_image = get_one_face(cv2.imread(modules.globals.source_path))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "G:\Deep-Live-Cam-main\modules\face_analyser.py", line 28, in get_one_face
    face = get_face_analyser().get(frame)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "G:\Deep-Live-Cam-main\env\Lib\site-packages\insightface\app\face_analysis.py", line 59, in get
    bboxes, kpss = self.det_model.detect(img,
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "G:\Deep-Live-Cam-main\env\Lib\site-packages\insightface\model_zoo\retinaface.py", line 224, in detect
    scores_list, bboxes_list, kpss_list = self.forward(det_img, self.det_thresh)
                                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "G:\Deep-Live-Cam-main\env\Lib\site-packages\insightface\model_zoo\retinaface.py", line 152, in forward
    net_outs = self.session.run(self.output_names, {self.input_name : blob})
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "G:\Deep-Live-Cam-main\env\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running FusedConv node. Name:'Conv_0' Status Message: CUDNN failure 4: CUDNN_STATUS_INTERNAL_ERROR ; GPU=0 ; hostname=DESKTOP-TG7I910 ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\nn\conv.cc ; line=335 ; expr=cudnnFindConvolutionForwardAlgorithmEx( GetCudnnHandle(context), s_.x_tensor, s_.x_data, s_.w_desc, s_.w_data, s_.conv_desc, s_.y_tensor, s_.y_data, 1, &algo_count, &perf, algo_search_workspace.get(), max_ws_size);

GPU : Gigabyte GTX 1060 6GB