环境:

  • requirements:
  1. Keras==2.2.4
  2. numpy==1.16.4
  3. opencv-python==3.4.2.16
  4. tensorboard==1.13.1
  5. tensorflow==1.14.0rc0
  6. tensorflow-estimator==1.14.0rc0
  7. scikit-image==0.15.0

问题:ValueError: Shape must be rank 1 but is rank 0 for ‘bn_conv1/Reshape_4’ (op: ‘Reshape’) with input shapes: [1,1,1,64], [].

修改文件:tensorflow_backend.py

File:tensorflow_backend.py

方法:把这些行中的(-1)改成中括号[-1].

Method: replace (-1) in these lines with brackets [-1].

Faster-RCNN:Target detection model in Keras

I hope I can help you,If you have any questions, please  comment on this blog or send me a private message. I will reply in my free time. 

相关文章:

  • 2021-07-09
  • 2021-09-02
  • 2021-05-26
  • 2022-01-16
  • 2021-06-04
  • 2021-07-22
  • 2022-12-23
猜你喜欢
  • 2022-01-23
  • 2021-09-19
  • 2022-02-08
  • 2021-06-11
  • 2021-09-13
  • 2022-01-07
  • 2021-04-30
相关资源
相似解决方案