The BatchNorm layer convertion to caffe model from tensorflow

1. caffe must set the batchnorm scale as 1, which is as follows.
   net.params[‘bn1’][2].data[…] = 1
2. Mean value is [0,0,0,0…,0] and variance is [1,1,1,1,…,1]
3. The gamma and beta value are from tensorflow model

net.params['bn1'][0].data[...] = mean
net.params['bn1'][1].data[...] = variance
net.params['bn1'][2].data[...] = 1
net.params['bn1_scale'][0].data[...] = gamma
net.params['bn1_scale'][1].data[...] = beta