caffe python接口 图片预处理 transformer 类 学习笔记

1:调用该接口,  传入字典 参数  
 eg: transformer=caffe.io.Transformer({'data': net.blobs['data'].data.shape})

2: self.set_transpose(self,in_,order)    用于将输入图片通道进行重排，将RGB格式转换为BGR 
in_ 字典的key值
order: 图像通道重排的顺序
eg:transformer.set_transpose('data', (2,0,1))

3：self.set_channel_swap(self, in_, order)
用于将输入图片通道进行重排，将RGB格式转换为BGR 
in_ 字典的key值
order: 图像通道重排的顺序

class Transformer:
    """
    Transform input for feeding into a Net.

    Note: this is mostly for illustrative purposes and it is likely better
    to define your own input preprocessing routine for your needs.

    Parameters
    ----------
    net : a Net for which the input should be prepared
    """
    def __init__(self, inputs):    #inputs :输入字典 eg:{'data': net.blobs['data'].data.shape}
        self.inputs = inputs
        self.transpose = {}
        self.channel_swap = {}
        self.raw_scale = {}
        self.mean = {}
        self.input_scale = {}

    def __check_input(self, in_):          # in_: 字典的key值
        if in_ not in self.inputs:
            raise Exception('{}