caffe中大多数层用C++写成。 但是对于自己数据的输入要写对应的输入层,比如你要去图像中的一部分,不能用LMDB,或者你的label 需要特殊的标记。 这时候就需要用python 写一个输入层。

 

如在fcn 的voc_layers.py 中 有两个类:

VOCSegDataLayer

SBDDSegDataLayer  

分别包含:setup,reshape,forward, backward, load_image, load_label. 不需要backward 没有参数更新。

import caffe

import numpy as np
from PIL import Image

import random

class VOCSegDataLayer(caffe.Layer):
    """
    Load (input image, label image) pairs from PASCAL VOC
    one-at-a-time while reshaping the net to preserve dimensions.

    Use this to feed data to a fully convolutional network.
    """

    def setup(self, bottom, top):
        """
        Setup data layer according to parameters:

        - voc_dir: path to PASCAL VOC year dir
        - split: train / val / test
        - mean: tuple of mean values to subtract
        - randomize: load in random order (default: True)
        - seed: seed for randomization (default: None / current time)

        for PASCAL VOC semantic segmentation.

        example

        params = dict(voc_dir="/path/to/PASCAL/VOC2011",
            mean=(104.00698793, 116.66876762, 122.67891434),
            split="val")
        """
        # config
        params = eval(self.param_str)
        self.voc_dir = params['voc_dir']
        self.split = params['split']
        self.mean = np.array(params['mean'])
        self.random = params.get('randomize', True)
        self.seed = params.get('seed', None)

        # two tops: data and label
        if len(top) != 2:
            raise Exception("Need to define two tops: data and label.")
        # data layers have no bottoms
        if len(bottom) != 0:
            raise Exception("Do not define a bottom.")

        # load indices for images and labels
        split_f  = '{}/ImageSets/Segmentation/{}.txt'.format(self.voc_dir,
                self.split)
        self.indices = open(split_f, 'r').read().splitlines()
        self.idx = 0

        # make eval deterministic
        if 'train' not in self.split:
            self.random = False

        # randomization: seed and pick
        if self.random:
            random.seed(self.seed)
            self.idx = random.randint(0, len(self.indices)-1)


    def reshape(self, bottom, top):
        # load image + label image pair
        self.data = self.load_image(self.indices[self.idx])
        self.label = self.load_label(self.indices[self.idx])
        # reshape tops to fit (leading 1 is for batch dimension)
        top[0].reshape(1, *self.data.shape)
        top[1].reshape(1, *self.label.shape)


    def forward(self, bottom, top):
        # assign output
        top[0].data[...] = self.data
        top[1].data[...] = self.label

        # pick next input
        if self.random:
            self.idx = random.randint(0, len(self.indices)-1)
        else:
            self.idx += 1
            if self.idx == len(self.indices):
                self.idx = 0


    def backward(self, top, propagate_down, bottom):
        pass


    def load_image(self, idx):
        """
        Load input image and preprocess for Caffe:
        - cast to float
        - switch channels RGB -> BGR
        - subtract mean
        - transpose to channel x height x width order
        """
        im = Image.open('{}/JPEGImages/{}.jpg'.format(self.voc_dir, idx))
        in_ = np.array(im, dtype=np.float32)
        in_ = in_[:,:,::-1]
        in_ -= self.mean
        in_ = in_.transpose((2,0,1))
        return in_


    def load_label(self, idx):
        """
        Load label image as 1 x height x width integer array of label indices.
        The leading singleton dimension is required by the loss.
        """
        im = Image.open('{}/SegmentationClass/{}.png'.format(self.voc_dir, idx))
        label = np.array(im, dtype=np.uint8)
        label = label[np.newaxis, ...]
        return label


class SBDDSegDataLayer(caffe.Layer):
    """
    Load (input image, label image) pairs from the SBDD extended labeling
    of PASCAL VOC for semantic segmentation
    one-at-a-time while reshaping the net to preserve dimensions.

    Use this to feed data to a fully convolutional network.
    """

    def setup(self, bottom, top):
        """
        Setup data layer according to parameters:

        - sbdd_dir: path to SBDD `dataset` dir
        - split: train / seg11valid
        - mean: tuple of mean values to subtract
        - randomize: load in random order (default: True)
        - seed: seed for randomization (default: None / current time)

        for SBDD semantic segmentation.

        N.B.segv11alid is the set of segval11 that does not intersect with SBDD.
        Find it here: https://gist.github.com/shelhamer/edb330760338892d511e.

        example

        params = dict(sbdd_dir="/path/to/SBDD/dataset",
            mean=(104.00698793, 116.66876762, 122.67891434),
            split="valid")
        """
        # config
        params = eval(self.param_str)
        self.sbdd_dir = params['sbdd_dir']
        self.split = params['split']
        self.mean = np.array(params['mean'])
        self.random = params.get('randomize', True)
        self.seed = params.get('seed', None)

        # two tops: data and label
        if len(top) != 2:
            raise Exception("Need to define two tops: data and label.")
        # data layers have no bottoms
        if len(bottom) != 0:
            raise Exception("Do not define a bottom.")

        # load indices for images and labels
        split_f  = '{}/{}.txt'.format(self.sbdd_dir,
                self.split)
        self.indices = open(split_f, 'r').read().splitlines()
        self.idx = 0

        # make eval deterministic
        if 'train' not in self.split:
            self.random = False

        # randomization: seed and pick
        if self.random:
            random.seed(self.seed)
            self.idx = random.randint(0, len(self.indices)-1)


    def reshape(self, bottom, top):
        # load image + label image pair
        self.data = self.load_image(self.indices[self.idx])
        self.label = self.load_label(self.indices[self.idx])
        # reshape tops to fit (leading 1 is for batch dimension)
        top[0].reshape(1, *self.data.shape)
        top[1].reshape(1, *self.label.shape)


    def forward(self, bottom, top):
        # assign output
        top[0].data[...] = self.data
        top[1].data[...] = self.label

        # pick next input
        if self.random:
            self.idx = random.randint(0, len(self.indices)-1)
        else:
            self.idx += 1
            if self.idx == len(self.indices):
                self.idx = 0


    def backward(self, top, propagate_down, bottom):
        pass


    def load_image(self, idx):
        """
        Load input image and preprocess for Caffe:
        - cast to float
        - switch channels RGB -> BGR
        - subtract mean
        - transpose to channel x height x width order
        """
        im = Image.open('{}/img/{}.jpg'.format(self.sbdd_dir, idx))
        in_ = np.array(im, dtype=np.float32)
        in_ = in_[:,:,::-1]
        in_ -= self.mean
        in_ = in_.transpose((2,0,1))
        return in_


    def load_label(self, idx):
        """
        Load label image as 1 x height x width integer array of label indices.
        The leading singleton dimension is required by the loss.
        """
        import scipy.io
        mat = scipy.io.loadmat('{}/cls/{}.mat'.format(self.sbdd_dir, idx))
        label = mat['GTcls'][0]['Segmentation'][0].astype(np.uint8)
        label = label[np.newaxis, ...]
        return label

  

对于 最终的loss 层:

在prototxt 中定义的layer:

layer {
  type: 'Python'  #python 
  name: 'loss'     # loss 层
  top: 'loss'
  bottom: 'ipx'
  bottom: 'ipy'
  python_param {
   
    module: 'pyloss'          # 写在pyloss 文件中
   
    layer: 'EuclideanLossLayer'    # 对应此类的名字
  }
  # set loss weight so Caffe knows this is a loss layer
  loss_weight: 1
}

  

loss 层的实现 :

import caffe
import numpy as np


class EuclideanLossLayer(caffe.Layer):
    """
    Compute the Euclidean Loss in the same manner as the C++ EuclideanLossLayer
    to demonstrate the class interface for developing layers in Python.
    """

    def setup(self, bottom, top):# top是最后的loss, bottom 中有两个值,一个网络的输出, 一个是label。
        # check input pair
        if len(bottom) != 2:
            raise Exception("Need two inputs to compute distance.")

    def reshape(self, bottom, top):
        # check input dimensions match
        if bottom[0].count != bottom[1].count:
            raise Exception("Inputs must have the same dimension.")
        # difference is shape of inputs
        self.diff = np.zeros_like(bottom[0].data, dtype=np.float32)
        # loss output is scalar
        top[0].reshape(1)

    def forward(self, bottom, top):
        self.diff[...] = bottom[0].data - bottom[1].data
        top[0].data[...] = np.sum(self.diff**2) / bottom[0].num / 2.

    def backward(self, top, propagate_down, bottom):
        for i in range(2):
            if not propagate_down[i]:
                continue
            if i == 0:
                sign = 1
            else:
                sign = -1
            bottom[i].diff[...] = sign * self.diff / bottom[i].num