"""
An implementation of stochastic max-pooling, based onStochastic Pooling for Regularization of Deep Convolutional Neural Networks
Matthew D. Zeiler, Rob Fergus, ICLR 2013
"""__authors__ = "Mehdi Mirza"
__copyright__ = "Copyright 2010-2012, Universite de Montreal"
__credits__ = ["Mehdi Mirza", "Ian Goodfellow"]
__license__ = "3-clause BSD"
__maintainer__ = "Mehdi Mirza"
__email__ = "mirzamom@iro"import numpy
import theano
from theano import tensor
from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
from theano.gof.op import get_debug_valuesdef stochastic_max_pool_bc01(bc01, pool_shape, pool_stride, image_shape, rng = None):"""Stochastic max pooling for training as defined in:Stochastic Pooling for Regularization of Deep Convolutional Neural NetworksMatthew D. Zeiler, Rob Fergusbc01: minibatch in format (batch size, channels, rows, cols),IMPORTANT: All values should be poitiviepool_shape: shape of the pool region (rows, cols)pool_stride: strides between pooling regions (row stride, col stride)image_shape: avoid doing some of the arithmetic in theanorng: theano random stream"""r, c = image_shapepr, pc = pool_shapers, cs = pool_stridebatch = bc01.shape[0] #总共batch的个数channel = bc01.shape[1] #通道个数if rng is None:rng = RandomStreams(2022)# Compute index in pooled space of last needed pool# (needed = each input pixel must appear in at least one pool)def last_pool(im_shp, p_shp, p_strd):rval = int(numpy.ceil(float(im_shp - p_shp) / p_strd))assert p_strd * rval + p_shp >= im_shpassert p_strd * (rval - 1) + p_shp < im_shpreturn rval #表示pool过程中需要移动的次数return T.dot(x, self._W)# Compute starting row of the last poollast_pool_r = last_pool(image_shape[0] ,pool_shape[0], pool_stride[0]) * pool_stride[0] #最后一个pool的起始位置# Compute number of rows needed in image for all indexes to work outrequired_r = last_pool_r + pr #满足上面pool条件时所需要image的高度
last_pool_c = last_pool(image_shape[1] ,pool_shape[1], pool_stride[1]) * pool_stride[1]required_c = last_pool_c + pc# final result shaperes_r = int(numpy.floor(last_pool_r/rs)) + 1 #最后pool完成时图片的shaperes_c = int(numpy.floor(last_pool_c/cs)) + 1for bc01v in get_debug_values(bc01):assert not numpy.any(numpy.isinf(bc01v))assert bc01v.shape[2] == image_shape[0]assert bc01v.shape[3] == image_shape[1]# padding,如果不能整除移动，需要对原始图片进行扩充padded = tensor.alloc(0.0, batch, channel, required_r, required_c)name = bc01.nameif name is None:name = 'anon_bc01'bc01 = tensor.set_subtensor(padded[:,:, 0:r, 0:c], bc01)bc01.name = 'zero_padded_' + name# unravelingwindow = tensor.alloc(0.0, batch, channel, res_r, res_c, pr, pc)window.name = 'unravlled_winodows_' + namefor row_within_pool in xrange(pool_shape[0]):row_stop = last_pool_r + row_within_pool + 1for col_within_pool in xrange(pool_shape[1]):col_stop = last_pool_c + col_within_pool + 1win_cell = bc01[:,:,row_within_pool:row_stop:rs, col_within_pool:col_stop:cs]window  =  tensor.set_subtensor(window[:,:,:,:, row_within_pool, col_within_pool], win_cell) #windows中装的是所有的pooling数据块# find the normnorm = window.sum(axis = [4, 5]) #求和当分母用 norm = tensor.switch(tensor.eq(norm, 0.0), 1.0, norm) #如果norm为0,则将norm赋值为1norm = window / norm.dimshuffle(0, 1, 2, 3, 'x', 'x') #除以norm得到每个位置的概率# get probprob = rng.multinomial(pvals = norm.reshape((batch * channel * res_r * res_c, pr * pc)), dtype='float32') #multinomial()函数能够按照pvals产生多个多项式分布,元素值为0或1# selectres = (window * prob.reshape((batch, channel, res_r, res_c,  pr, pc))).max(axis=5).max(axis=4) #window和后面的矩阵相乘是点乘，即对应元素相乘，numpy矩阵符号res.name = 'pooled_' + namereturn tensor.cast(res, theano.config.floatX)def weighted_max_pool_bc01(bc01, pool_shape, pool_stride, image_shape, rng = None):"""This implements test time probability weighted pooling defined in:Stochastic Pooling for Regularization of Deep Convolutional Neural NetworksMatthew D. Zeiler, Rob Fergusbc01: minibatch in format (batch size, channels, rows, cols),IMPORTANT: All values should be poitiviepool_shape: shape of the pool region (rows, cols)pool_stride: strides between pooling regions (row stride, col stride)image_shape: avoid doing some of the arithmetic in theano"""r, c = image_shapepr, pc = pool_shapers, cs = pool_stridebatch = bc01.shape[0]channel = bc01.shape[1]if rng is None: rng = RandomStreams(2022) # Compute index in pooled space of last needed pool # (needed = each input pixel must appear in at least one pool)def last_pool(im_shp, p_shp, p_strd):rval = int(numpy.ceil(float(im_shp - p_shp) / p_strd))assert p_strd * rval + p_shp >= im_shpassert p_strd * (rval - 1) + p_shp < im_shpreturn rval# Compute starting row of the last poollast_pool_r = last_pool(image_shape[0] ,pool_shape[0], pool_stride[0]) * pool_stride[0]# Compute number of rows needed in image for all indexes to work outrequired_r = last_pool_r + prlast_pool_c = last_pool(image_shape[1] ,pool_shape[1], pool_stride[1]) * pool_stride[1]required_c = last_pool_c + pc# final result shaperes_r = int(numpy.floor(last_pool_r/rs)) + 1res_c = int(numpy.floor(last_pool_c/cs)) + 1for bc01v in get_debug_values(bc01):assert not numpy.any(numpy.isinf(bc01v))assert bc01v.shape[2] == image_shape[0]assert bc01v.shape[3] == image_shape[1]# paddingpadded = tensor.alloc(0.0, batch, channel, required_r, required_c)name = bc01.nameif name is None:name = 'anon_bc01'bc01 = tensor.set_subtensor(padded[:,:, 0:r, 0:c], bc01)bc01.name = 'zero_padded_' + name# unravelingwindow = tensor.alloc(0.0, batch, channel, res_r, res_c, pr, pc)window.name = 'unravlled_winodows_' + namefor row_within_pool in xrange(pool_shape[0]):row_stop = last_pool_r + row_within_pool + 1for col_within_pool in xrange(pool_shape[1]):col_stop = last_pool_c + col_within_pool + 1win_cell = bc01[:,:,row_within_pool:row_stop:rs, col_within_pool:col_stop:cs]window  =  tensor.set_subtensor(window[:,:,:,:, row_within_pool, col_within_pool], win_cell)# find the normnorm = window.sum(axis = [4, 5])norm = tensor.switch(tensor.eq(norm, 0.0), 1.0, norm)norm = window / norm.dimshuffle(0, 1, 2, 3, 'x', 'x')# averageres = (window * norm).sum(axis=[4,5]) #前面的代码几乎和前向传播代码一样，这里只需加权求和即可res.name = 'pooled_' + namereturn res.reshape((batch, channel, res_r, res_c))