Cacher is the code snippet organizer for pro developers

image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg')
transformed_image = transformer.preprocess('data', image)
plt.imshow(image)
  
  
import numpy as np
import skimage.io
from scipy.ndimage import zoom
from skimage.transform import resize
    def preprocess(self, in_, data):
        """
        Format input for Caffe:
        - convert to single
        - resize to input dimensions (preserving number of channels)
        - transpose dimensions to K x H x W
        - reorder channels (for instance color to BGR)
        - scale raw input (e.g. from [0, 1] to [0, 255] for ImageNet models)
        - subtract mean
        - scale feature

        Parameters
        ----------
        in_ : name of input blob to preprocess for
        data : (H' x W' x K) ndarray

        Returns
        -------
        caffe_in : (K x H x W) ndarray for input to a Net
        """
        self.__check_input(in_)
        caffe_in = data.astype(np.float32, copy=False)
        transpose = self.transpose.get(in_)
        channel_swap = self.channel_swap.get(in_)
        raw_scale = self.raw_scale.get(in_)
        mean = self.mean.get(in_)
        input_scale = self.input_scale.get(in_)
        in_dims = self.inputs[in_][2:]
        if caffe_in.shape[:2] != in_dims:
            caffe_in = resize_image(caffe_in, in_dims)
        if transpose is not None:
            caffe_in = caffe_in.transpose(transpose)
        if channel_swap is not None:
            caffe_in = caffe_in[channel_swap, :, :]
        if raw_scale is not None:
            caffe_in *= raw_scale
        if mean is not None:
            caffe_in -= mean
        if input_scale is not None:
            caffe_in *= input_scale
        return caffe_in

    def deprocess(self, in_, data):
        """
        Invert Caffe formatting; see preprocess().
        """
        self.__check_input(in_)
        decaf_in = data.copy().squeeze()
        transpose = self.transpose.get(in_)
        channel_swap = self.channel_swap.get(in_)
        raw_scale = self.raw_scale.get(in_)
        mean = self.mean.get(in_)
        input_scale = self.input_scale.get(in_)
        if input_scale is not None:
            decaf_in /= input_scale
        if mean is not None:
            decaf_in += mean
        if raw_scale is not None:
            decaf_in /= raw_scale
        if channel_swap is not None:
            decaf_in = decaf_in[np.argsort(channel_swap), :, :]
        if transpose is not None:
            decaf_in = decaf_in.transpose(np.argsort(transpose))
        return decaf_in

## Pre-processing

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):
        self.inputs = inputs
        self.transpose = {}
        self.channel_swap = {}
        self.raw_scale = {}
        self.mean = {}
        self.input_scale = {}

    def __check_input(self, in_):
        if in_ not in self.inputs:
            raise Exception('{} is not one of the net inputs: {}'.format(
                in_, self.inputs))

    def preprocess(self, in_, data):
        """
        Format input for Caffe:
        - convert to single
        - resize to input dimensions (preserving number of channels)
        - transpose dimensions to K x H x W
        - reorder channels (for instance color to BGR)
        - scale raw input (e.g. from [0, 1] to [0, 255] for ImageNet models)
        - subtract mean
        - scale feature

        Parameters
        ----------
        in_ : name of input blob to preprocess for
        data : (H' x W' x K) ndarray

        Returns
        -------
        caffe_in : (K x H x W) ndarray for input to a Net
        """
        pass

    def deprocess(self, in_, data):
        """
        Invert Caffe formatting; see preprocess().
        """
        pass

    def set_transpose(self, in_, order):
        """
        Set the input channel order for e.g. RGB to BGR conversion
        as needed for the reference ImageNet model.

        Parameters
        ----------
        in_ : which input to assign this channel order
        order : the order to transpose the dimensions
        """
        self.__check_input(in_)
        if len(order) != len(self.inputs[in_]) - 1:
            raise Exception('Transpose order needs to have the same number of '
                            'dimensions as the input.')
        self.transpose[in_] = order

    def set_channel_swap(self, in_, order):
        """
        Set the input channel order for e.g. RGB to BGR conversion
        as needed for the reference ImageNet model.
        N.B. this assumes the channels are the first dimension AFTER transpose.

        Parameters
        ----------
        in_ : which input to assign this channel order
        order : the order to take the channels.
            (2,1,0) maps RGB to BGR for example.
        """
        self.__check_input(in_)
        if len(order) != self.inputs[in_][1]:
            raise Exception('Channel swap needs to have the same number of '
                            'dimensions as the input channels.')
        self.channel_swap[in_] = order

    def set_raw_scale(self, in_, scale):
        """
        Set the scale of raw features s.t. the input blob = input * scale.
        While Python represents images in [0, 1], certain Caffe models
        like CaffeNet and AlexNet represent images in [0, 255] so the raw_scale
        of these models must be 255.

        Parameters
        ----------
        in_ : which input to assign this scale factor
        scale : scale coefficient
        """
        self.__check_input(in_)
        self.raw_scale[in_] = scale

    def set_mean(self, in_, mean):
        """
        Set the mean to subtract for centering the data.

        Parameters
        ----------
        in_ : which input to assign this mean.
        mean : mean ndarray (input dimensional or broadcastable)
        """
        self.__check_input(in_)
        ms = mean.shape
        if mean.ndim == 1:
            # broadcast channels
            if ms[0] != self.inputs[in_][1]:
                raise ValueError('Mean channels incompatible with input.')
            mean = mean[:, np.newaxis, np.newaxis]
        else:
            # elementwise mean
            if len(ms) == 2:
                ms = (1,) + ms
            if len(ms) != 3:
                raise ValueError('Mean shape invalid')
            if ms != self.inputs[in_][1:]:
                raise ValueError('Mean shape incompatible with input shape.')
        self.mean[in_] = mean

    def set_input_scale(self, in_, scale):
        """
        Set the scale of preprocessed inputs s.t. the blob = blob * scale.
        N.B. input_scale is done AFTER mean subtraction and other preprocessing
        while raw_scale is done BEFORE.

        Parameters
        ----------
        in_ : which input to assign this scale factor
        scale : scale coefficient
        """
        self.__check_input(in_)
        self.input_scale[in_] = scale

# load the mean ImageNet image (as distributed with Caffe) for subtraction
mu = np.load(caffe_root + 'python/caffe/imagenet/ilsvrc_2012_mean.npy')
mu = mu.mean(1).mean(1)  # average over pixels to obtain the mean (BGR) pixel values
print 'mean-subtracted values:', zip('BGR', mu)

# create transformer for the input called 'data'
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})

transformer.set_transpose('data', (2,0,1))  # move image channels to outermost dimension
transformer.set_mean('data', mu)            # subtract the dataset-mean value in each channel
transformer.set_raw_scale('data', 255)      # rescale from [0, 1] to [0, 255]
transformer.set_channel_swap('data', (2,1,0))  # swap channels from RGB to BGR