Open Persite007 opened 10 months ago
Update: After update all, no error at startup but now DWPreprocessor crash with the test workflow file.
Error occurred when executing DWPreprocessor:
Unknown C++ exception from OpenCV code
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py", line 58, in estimate_pose
out = common_annotator_call(cb, image, include_hand=detect_hand, include_face=detect_face, include_body=detect_body, image_and_json=True, resolution=resolution)
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\utils.py", line 46, in common_annotator_call
np_result = model(np_image, output_type="np", detect_resolution=detect_resolution, **kwargs)
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py", line 54, in cb
result = model(image, **kwargs)
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\__init__.py", line 189, in __call__
poses = self.detect_poses(detected_map)
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\__init__.py", line 176, in detect_poses
keypoints_info = self.dw_pose_estimation(oriImg.copy())
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\wholebody.py", line 55, in __call__
det_result = inference_detector(self.session_det, oriImg)
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux\dwpose\cv_ox_det.py", line 107, in inference_detector
output = session.forward(outNames)
Hi, did you upadte your intel graghic card driver for CPU? Besides I think you can remove onnxruntime-directml
and onnxruntime-openvino
and just use gpu CudaExecutionProvider
.
I added in requirements.txt onnxruntime-gpu onnxruntime-directml onnxruntime-openvino Like you explain in an other post. Good :) now onnxruntime is working on CPUs and Gpu but still an error with openvino. How to fix it?