roop1.2带显卡整合版报错，求支援

hepburner · 发表于 2023-7-24 00:01:08

使用CPU运行没有问题。

但使用显卡运行，就报错
错误为:

set det-size: (640, 640)
2023-07-23 23:59:41.0317699 [Ennxruntime:, sequential_executor.cc:514 onnxruntime::ExecuteKernel] Non-zero status code returned while running Resize node. Name:'Resize_124' Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device
Exception in Tkinter callback
Traceback (most recent call last):
  File "F:\ai\roop1.2\python3\lib\tkinter\__init__.py", line 1921, in __call__
return self.func(*args)
  File "F:\ai\roop1.2\python3\lib\site-packages\customtkinter\windows\widgets\ctk_button.py", line 554, in _clicked
self._command()
  File "F:\ai\roop1.2\roop\ui.py", line 103, in <lambda>
start_button = ctk.CTkButton(root, text='Start', cursor='hand2', command=lambda: select_output_path(start))
  File "F:\ai\roop1.2\roop\ui.py", line 199, in select_output_path
start()
  File "F:\ai\roop1.2\roop\core.py", line 133, in start
if not frame_processor.pre_start():
  File "F:\ai\roop1.2\roop\processors\frame\face_swapper.py", line 45, in pre_start
elif not get_one_face(cv2.imread(roop.globals.source_path)):
  File "F:\ai\roop1.2\roop\face_analyser.py", line 30, in get_one_face
faces = get_many_faces(frame)
  File "F:\ai\roop1.2\roop\face_analyser.py", line 41, in get_many_faces
return get_face_analyser().get(frame)
  File "F:\ai\roop1.2\python3\lib\site-packages\insightface\app\face_analysis.py", line 59, in get
bboxes, kpss = self.det_model.detect(img,
  File "F:\ai\roop1.2\python3\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 "F:\ai\roop1.2\python3\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 "F:\ai\roop1.2\python3\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 217, 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 Resize node. Name:'Resize_124' Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device

hepburner · 发表于 2023-7-24 00:33:31

是因为我设置高了，爆显存？

人工智障 · 发表于 2023-7-26 23:10:06

显卡型号？报错时跑的模型是哪个？参数设置是啥？

hepburner · 发表于 2023-7-27 20:02:09

本帖最后由 hepburner 于 2023-7-27 20:20 编辑

人工智障发表于 2023-7-26 23:10
显卡型号？报错时跑的模型是哪个？参数设置是啥？

问题已解决：
官方已经给出答案：换显卡
Runtime errors during processing

A Non zero status code... or Cannot allocate memory... during processing results in lost frames and indicate that your GPU is out of VRAM or just overwhelmed - you need to lower the --execution-threads to 1 and increase it slowly.

Non zero status code...