frcnn ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1_4/Reshape_4' (op: 'Reshape') with

在调用faster RCnn 时shared_layers = nn.nn_base(img_input, trainable=True) ，报错：

InvalidArgumentError: Shape must be rank 1 but is rank 0 for 'bn_conv1_1/Reshape_4' (op: 'Reshape') with input shapes: [1,1,1,64], [].

经过查阅，发现是BatchNormalization的问题，如下代码也会类似报错

from keras.layers import BatchNormalization, Input

 x = Input(shape=(1, 2, 2)) 

BatchNormalization(axis=1)(x)   

报错：InvalidArgumentError: Shape must be rank 1 but is rank 0 for 'batch_normalization_1/cond/Reshape_4' (op: 'Reshape') with input shapes: [1,1,1,1], [].

在CPU版的keras 2.2.0上没有问题，在gup版本的keras有问题。因此将keras 降低版本为2.1.6：

 pip3 uninstall keras

 pip3 install keras==2.1.6  -i http://pypi.douban.com/simple --trusted-host pypi.douban.com

不在报错