py-faster-rcnn 훈련의 흔한 오류

2267 단어 faster-r-cnn

py-faster-rcnn 훈련의 흔한 오류


py-faster-rcnn을 훈련할 때 다음과 같은 오류가 자주 발생합니다.
  • TypeError: ‘numpy.float64’ object cannot be interpreted as an index
  • Check failed: error == cudaSuccess (4 vs. 0) unspecified launch failure
  • AttributeError: ‘module’ object has no attribute ‘text_format’

  • TypeError: ‘numpy.float64’ object cannot be interpreted as an index


    .해결 방법 sudo pip install -U numpy==1.11.0`

    Check failed: error == cudaSuccess (4 vs. 0) unspecified launch failure

  • 해결 방법
  • ①cudnn 설치:

  •             cp caffe/inlude/caffe/layers/cudnn_* caffe-fast-rcnn/include/caffe/layers/
                cp caffe/src/caffe/layers/cudnn_* caffe-fast-rcnn/src/caffe/layers/
                cp caffe/include/caffe/util/cudnn.hpp caffe-fast-rcnn/include/caffe/util/
    
                cd caffe-fast-rcnn
                make clean
                make -j8
                make pycaffe
     - ②   py-faster-rcnn/lib/fast_rcnn/config.py: BATCH_SIZE , 64,32,16,8....
    
            # Minibatch size (number of regions of interest [ROIs])
            __C.TRAIN.BATCH_SIZE = 128

    AttributeError: ‘module’ object has no attribute ‘text_format’

  • py-faster-rcnn/lib/fast_에서rcnn/train.py에 추가:import google.protobuf.text_format
  • 좋은 웹페이지 즐겨찾기