关于roop报错

q8791184q

星级打分

• 1
• 2
• 3
• 4
• 5

平均分:NAN  参与人数:0  我的评分:未评

大哥们谁能帮我看下，使用ROOP进行换脸+高清修复的时候，图片一张一张换没事，一旦批量换，第一张没问题，第二张开始就出现以下错误，实在没搞懂







WARNING:tensorflow:AutoGraph is not available in this environment: functions lack code information. This is typical of some environments like the interactive Python shell. See https://github.com/tensorflow/te ... cess-to-source-code for more information.
生成过程比较慢，有时候加载模型会比较慢，耐心等待
源图片：C:/Users/Administrator/Desktop/data_src/1.jpg，目标视频/图片：C:/Users/Administrator/Desktop/data_dst/11.jpg
namespace(source_path='C:/Users/Administrator/Desktop/data_src/1.jpg', target_path='C:/Users/Administrator/Desktop/data_dst/11.jpg', output_path='./Swap_Out\\1.jpg16905700421_HD.png', frame_processor=['face_swapper', 'face_enhancer'], keep_fps=True, skip_audio=False, keep_frames=False, many_faces=True, max_memory=16, execution_provider=['cuda'], execution_threads=4, reference_face_position=0, reference_frame_number=0, similar_face_distance=1000, temp_frame_format='png', temp_frame_quality=0, output_video_encoder='libx264', output_video_quality=35)
dsdsdsd namespace(source_path='C:/Users/Administrator/Desktop/data_src/1.jpg', target_path='C:/Users/Administrator/Desktop/data_dst/11.jpg', output_path='./Swap_Out\\1.jpg16905700421_HD.png', frame_processor=['face_swapper', 'face_enhancer'], keep_fps=True, skip_audio=False, keep_frames=False, many_faces=True, max_memory=16, execution_provider=['cuda'], execution_threads=4, reference_face_position=0, reference_frame_number=0, similar_face_distance=1000, temp_frame_format='png', temp_frame_quality=0, output_video_encoder='libx264', output_video_quality=35)
Progressing... ROOP.FACE-SWAPPER
Progressing... ROOP.FACE-ENHANCER
Processing to image succeed!
源图片：C:/Users/Administrator/Desktop/data_src/1.jpg，目标视频/图片：C:/Users/Administrator/Desktop/data_dst/12.jpg
namespace(source_path='C:/Users/Administrator/Desktop/data_src/1.jpg', target_path='C:/Users/Administrator/Desktop/data_dst/12.jpg', output_path='./Swap_Out\\1.jpg16905700602_HD.png', frame_processor=['face_swapper', 'face_enhancer'], keep_fps=True, skip_audio=False, keep_frames=False, many_faces=True, max_memory=16, execution_provider=['cuda'], execution_threads=4, reference_face_position=0, reference_frame_number=0, similar_face_distance=1000, temp_frame_format='png', temp_frame_quality=0, output_video_encoder='libx264', output_video_quality=35)
dsdsdsd namespace(source_path='C:/Users/Administrator/Desktop/data_src/1.jpg', target_path='C:/Users/Administrator/Desktop/data_dst/12.jpg', output_path='./Swap_Out\\1.jpg16905700602_HD.png', frame_processor=['face_swapper', 'face_enhancer'], keep_fps=True, skip_audio=False, keep_frames=False, many_faces=True, max_memory=16, execution_provider=['cuda'], execution_threads=4, reference_face_position=0, reference_frame_number=0, similar_face_distance=1000, temp_frame_format='png', temp_frame_quality=0, output_video_encoder='libx264', output_video_quality=35)
Progressing... ROOP.FACE-SWAPPER
*** 捕获到异常 <class 'onnxruntime.capi.onnxruntime_pybind11_state.Fail'> [ONNXRuntimeError] : 1 : FAIL : D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUDNN failure 1: CUDNN_STATUS_NOT_INITIALIZED ; GPU=0 ; hostname=WIN-OG8ET4KIQOP ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_stream_handle.cc ; line=52 ; expr=cudnnCreate(&cudnn_handle_);


Error in sys.excepthook:
Traceback (most recent call last):
  File "roop_face_main_V17_20230728.py", line 447, in handleException
AttributeError: 'traceback' object has no attribute 'print_tb'

Original exception was:
Traceback (most recent call last):
  File "roop_face_main_V17_20230728.py", line 123, in run
  File "roop\core.py", line 242, in run
    start()
  File "roop\core.py", line 173, in start
    frame_processor.process_image(roop.globals.source_path, roop.globals.output_path, roop.globals.output_path)
  File "F:\ROOP\roop\processors\frame\face_swapper.py", line 91, in process_image
    result = process_frame(source_face, reference_face, target_frame)
  File "F:\ROOP\roop\processors\frame\face_swapper.py", line 68, in process_frame
    temp_frame = swap_face(source_face, target_face, temp_frame)
  File "F:\ROOP\roop\processors\frame\face_swapper.py", line 60, in swap_face
    return get_face_swapper().get(temp_frame, target_face, source_face, paste_back=True)
  File "insightface\model_zoo\inswapper.py", line 53, in get
    pred = self.session.run(self.output_names, {self.input_names[0]: blob, self.input_names[1]: latent})[0]
  File "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 : D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUDNN failure 1: CUDNN_STATUS_NOT_INITIALIZED ; GPU=0 ; hostname=WIN-OG8ET4KIQOP ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_stream_handle.cc ; line=52 ; expr=cudnnCreate(&cudnn_handle_);

hepburn

把线程改小试试。
如果不是整合版，大概率是cuda和cudnn的设置出了问题。
实在不行，去b站问问。

国际狄拉克

显卡驱动是最新的吗，不是的话更新一下