faster rcnn源码理解（二）之AnchorTargetLayer（网络中的rpn_data）

faster用python版本的https://github.com/rbgirshick/py-faster-rcnn

AnchorTargetLayer源码在https://github.com/rbgirshick/py-faster-rcnn/blob/master/lib/rpn/anchor_target_layer.py

源码粘贴：

# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick and Sean Bell
# --------------------------------------------------------
import os
import caffe
import yaml
from fast_rcnn.config import cfg
import numpy as np
import numpy.random as npr
from generate_anchors import generate_anchors
from utils.cython_bbox import bbox_overlaps
from fast_rcnn.bbox_transform import bbox_transform
DEBUG = False
class AnchorTargetLayer(caffe.Layer):
"""
Assign anchors to ground-truth targets. Produces anchor classification
labels and bounding-box regression targets.
"""
def setup(self, bottom, top):
layer_params = yaml.load(self.param_str_)
anchor_scales = layer_params.get('scales', (8, 16, 32))
self._anchors = generate_anchors(scales=np.array(anchor_scales))#九个anchor的w h x_cstr y_cstr，对原始的wh做横向纵向变化，并放大缩小得到九个
self._num_anchors = self._anchors.shape[0]<span style="font-family: Arial, Helvetica, sans-serif;">#anchor的个数</span>
self._feat_stride = layer_params['feat_stride']#网络中参数16
if DEBUG:
print 'anchors:'
print self._anchors
print 'anchor shapes:'
print np.hstack((
self._anchors[:, 2::4] - self._anchors[:, 0::4],
self._anchors[:, 3::4] - self._anchors[:, 1::4],
))
self._counts = cfg.EPS
self._sums = np.zeros((1, 4))
self._squared_sums = np.zeros((1, 4))
self._fg_sum = 0
self._bg_sum = 0
self._count = 0
# allow boxes to sit over the edge by a small amount
self._allowed_border = layer_params.get('allowed_border', 0)
#bottom 长度为4；bottom[0],map；bottom[1],boxes,labels;bottom[2],im_fo;bottom[3],图片数据
height, width = bottom[0].data.shape[-2:]
if DEBUG:
print 'AnchorTargetLayer: height', height, 'width', width
A = self._num_anchors#anchor的个数
# labels
top[0].reshape(1, 1, A * height, width)
# bbox_targets
top[1].reshape(1, A * 4, height, width)
# bbox_inside_weights
top[2].reshape(1, A * 4, height, width)
# bbox_outside_weights
top[3].reshape(1, A * 4, height, width)
def forward(self, bottom, top):
# Algorithm:
#
# for each (H, W) location i
#
generate 9 anchor boxes centered on cell i
#
apply predicted bbox deltas at cell i to each of the 9 anchors
# filter out-of-image anchors
# measure GT overlap
assert bottom[0].data.shape[0] == 1, 
'Only single item batches are supported'
# map of shape (..., H, W)
height, width = bottom[0].data.shape[-2:]
# GT boxes (x1, y1, x2, y2, label)
gt_boxes = bottom[1].data#gt_boxes:长度不定
# im_info
im_info = bottom[2].data[0, :]
if DEBUG:
print ''
print 'im_size: ({}, {})'.format(im_info[0], im_info[1])
print 'scale: {}'.format(im_info[2])
print 'height, width: ({}, {})'.format(height, width)
print 'rpn: gt_boxes.shape', gt_boxes.shape
print 'rpn: gt_boxes', gt_boxes
# 1. Generate proposals from bbox deltas and shifted anchors
shift_x = np.arange(0, width) * self._feat_stride
shift_y = np.arange(0, height) * self._feat_stride
shift_x, shift_y = np.meshgrid(shift_x, shift_y)
shifts = np.vstack((shift_x.ravel(), shift_y.ravel(),
shift_x.ravel(), shift_y.ravel())).transpose()
# add A anchors (1, A, 4) to
# cell K shifts (K, 1, 4) to get
# shift anchors (K, A, 4)
# reshape to (K*A, 4) shifted anchors
A = self._num_anchors
K = shifts.shape[0]
all_anchors = (self._anchors.reshape((1, A, 4)) +
shifts.reshape((1, K, 4)).transpose((1, 0, 2)))
all_anchors = all_anchors.reshape((K * A, 4))
total_anchors = int(K * A)#K*A，所有anchors个数，包括越界的
#K: width*height
#A: 9
# only keep anchors inside the image
inds_inside = np.where(
(all_anchors[:, 0] >= -self._allowed_border) &
(all_anchors[:, 1] >= -self._allowed_border) &
(all_anchors[:, 2] < im_info[1] + self._allowed_border) &
# width
(all_anchors[:, 3] < im_info[0] + self._allowed_border)
# height
)[0]#没有过界的anchors索引
if DEBUG:
print 'total_anchors', total_anchors
print 'inds_inside', len(inds_inside)
# keep only inside anchors
anchors = all_anchors[inds_inside, :]#没有过界的anchors
if DEBUG:
print 'anchors.shape', anchors.shape
# label: 1 is positive, 0 is negative, -1 is dont care
labels = np.empty((len(inds_inside), ), dtype=np.float32)
labels.fill(-1)
# overlaps between the anchors and the gt boxes
# overlaps (ex, gt)
overlaps = bbox_overlaps(
np.ascontiguousarray(anchors, dtype=np.float),
np.ascontiguousarray(gt_boxes, dtype=np.float))
argmax_overlaps = overlaps.argmax(axis=1)#overlaps每行最大值索引
max_overlaps = overlaps[np.arange(len(inds_inside)), argmax_overlaps]
gt_argmax_overlaps = overlaps.argmax(axis=0)
gt_max_overlaps = overlaps[gt_argmax_overlaps,
np.arange(overlaps.shape[1])]
gt_argmax_overlaps = np.where(overlaps == gt_max_overlaps)[0]
if not cfg.TRAIN.RPN_CLOBBER_POSITIVES:
# assign bg labels first so that positive labels can clobber them
labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0
# fg label: for each gt, anchor with highest overlap
labels[gt_argmax_overlaps] = 1
# fg label: above threshold IOU
labels[max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1
if cfg.TRAIN.RPN_CLOBBER_POSITIVES:
# assign bg labels last so that negative labels can clobber positives
labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0
# subsample positive labels if we have too many
num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCHSIZE)
fg_inds = np.where(labels == 1)[0]
if len(fg_inds) > num_fg:
disable_inds = npr.choice(
fg_inds, size=(len(fg_inds) - num_fg), replace=False)
labels[disable_inds] = -1
# subsample negative labels if we have too many
num_bg = cfg.TRAIN.RPN_BATCHSIZE - np.sum(labels == 1)
bg_inds = np.where(labels == 0)[0]
if len(bg_inds) > num_bg:
disable_inds = npr.choice(
bg_inds, size=(len(bg_inds) - num_bg), replace=False)
labels[disable_inds] = -1
#print "was %s inds, disabling %s, now %s inds" % (
#len(bg_inds), len(disable_inds), np.sum(labels == 0))
bbox_targets = np.zeros((len(inds_inside), 4), dtype=np.float32)
bbox_targets = _compute_targets(anchors, gt_boxes[argmax_overlaps, :])
bbox_inside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32)
bbox_inside_weights[labels == 1, :] = np.array(cfg.TRAIN.RPN_BBOX_INSIDE_WEIGHTS)
bbox_outside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32)
if cfg.TRAIN.RPN_POSITIVE_WEIGHT < 0:
# uniform weighting of examples (given non-uniform sampling)
num_examples = np.sum(labels >= 0)
positive_weights = np.ones((1, 4)) * 1.0 / num_examples
negative_weights = np.ones((1, 4)) * 1.0 / num_examples
else:
assert ((cfg.TRAIN.RPN_POSITIVE_WEIGHT > 0) &
(cfg.TRAIN.RPN_POSITIVE_WEIGHT < 1))
positive_weights = (cfg.TRAIN.RPN_POSITIVE_WEIGHT /
np.sum(labels == 1))
negative_weights = ((1.0 - cfg.TRAIN.RPN_POSITIVE_WEIGHT) /
np.sum(labels == 0))
bbox_outside_weights[labels == 1, :] = positive_weights
bbox_outside_weights[labels == 0, :] = negative_weights
if DEBUG:
self._sums += bbox_targets[labels == 1, :].sum(axis=0)
self._squared_sums += (bbox_targets[labels == 1, :] ** 2).sum(axis=0)
self._counts += np.sum(labels == 1)
means = self._sums / self._counts
stds = np.sqrt(self._squared_sums / self._counts - means ** 2)
print 'means:'
print means
print 'stdevs:'
print stds
# map up to original set of anchors
labels = _unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = _unmap(bbox_targets, total_anchors, inds_inside, fill=0)
bbox_inside_weights = _unmap(bbox_inside_weights, total_anchors, inds_inside, fill=0)
bbox_outside_weights = _unmap(bbox_outside_weights, total_anchors, inds_inside, fill=0)
if DEBUG:
print 'rpn: max max_overlap', np.max(max_overlaps)
print 'rpn: num_positive', np.sum(labels == 1)
print 'rpn: num_negative', np.sum(labels == 0)
self._fg_sum += np.sum(labels == 1)
self._bg_sum += np.sum(labels == 0)
self._count += 1
print 'rpn: num_positive avg', self._fg_sum / self._count
print 'rpn: num_negative avg', self._bg_sum / self._count
# labels
labels = labels.reshape((1, height, width, A)).transpose(0, 3, 1, 2)
labels = labels.reshape((1, 1, A * height, width))
top[0].reshape(*labels.shape)
top[0].data[...] = labels
# bbox_targets
bbox_targets = bbox_targets 
.reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)
top[1].reshape(*bbox_targets.shape)
top[1].data[...] = bbox_targets
# bbox_inside_weights
bbox_inside_weights = bbox_inside_weights 
.reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)
assert bbox_inside_weights.shape[2] == height
assert bbox_inside_weights.shape[3] == width
top[2].reshape(*bbox_inside_weights.shape)
top[2].data[...] = bbox_inside_weights
# bbox_outside_weights
bbox_outside_weights = bbox_outside_weights 
.reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)
assert bbox_outside_weights.shape[2] == height
assert bbox_outside_weights.shape[3] == width
top[3].reshape(*bbox_outside_weights.shape)
top[3].data[...] = bbox_outside_weights
def backward(self, top, propagate_down, bottom):
"""This layer does not propagate gradients."""
pass
def reshape(self, bottom, top):
"""Reshaping happens during the call to forward."""
pass
def _unmap(data, count, inds, fill=0):
""" Unmap a subset of item (data) back to the original set of items (of
size count) """
if len(data.shape) == 1:
ret = np.empty((count, ), dtype=np.float32)
ret.fill(fill)
ret[inds] = data
else:
ret = np.empty((count, ) + data.shape[1:], dtype=np.float32)
ret.fill(fill)
ret[inds, :] = data
return ret
def _compute_targets(ex_rois, gt_rois):
"""Compute bounding-box regression targets for an image."""
assert ex_rois.shape[0] == gt_rois.shape[0]
assert ex_rois.shape[1] == 4
assert gt_rois.shape[1] == 5
return bbox_transform(ex_rois, gt_rois[:, :4]).astype(np.float32, copy=False)

总结笔记：
rpn-data是AnchorTargetLayer
bottom 长度为4；bottom[0],map；bottom[1],boxes,labels;bottom[2],im_fo;bottom[3],图片数据
self._feat_stride:网络中参数16
self._anchors：九个anchor的w h x_cstr y_cstr，对原始的wh做横向纵向变化，并放大缩小得到九个
self._num_anchors：anchor的个数


inds_inside：没有过界的anchors索引
anchors：没有过界的anchors
argmax_overlaps：overlaps每行最大值索引
total_anchors： K*A，所有anchors个数，包括越界的
K: width*height
A: 9


gt_boxes:长度不定


bbox_overlaps： 返回:
overlaps: (len(inds_inside)* len(gt_boxes))


论文笔记：我们分配正标签给两类anchor：（i）与某个ground truth（GT）包围盒有最高的IoU（Intersection-over-Union，交集并集之比）重叠的anchor（也许不到0.7），（ii）与任意GT包围盒有大于0.7的IoU交叠的anchor。
labels:0,bg; 1,fg; -1, on care,(len(inds_inside));over_laps列最大值对应行坐标=1； over_laps行最大值 > 0.7,行=1； over_laps行最大值 < 0.3，行=0
正样本数量由他们控制：cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCHSIZE（128），小于等于
负样本数量。。。。。：cfg.TRAIN.RPN_BATCHSIZE - np.sum(labels == 1)
cfg.TRAIN.RPN_BATCHSIZE:  256，最终输出proposal数量控制


多的proposal被随机搞成-1了。。。。。。随机


bbox_inside_weights： label等于1的行，它的值等于cfg.TRAIN.RPN_BBOX_INSIDE_WEIGHTS（1.0）；其他等于0;(len(inds_inside), 4)；相当于损失函数中的pi*


cfg.TRAIN.RPN_POSITIVE_WEIGHT:  -1.0


bbox_outside_weights：fg,bg=np.ones((1, 4)) * 1.0 / sum(fg+bg)，其他为0;(len(inds_inside), 4)


_unmap： 建立一个total_anchors*第一个参数列的数组；全用fill填充；再把inds_inside对应的行用第一个参数对应的行填充 

最后

以上就是端庄歌曲为你收集整理的faster rcnn源码理解（二）之AnchorTargetLayer（网络中的rpn_data）的全部内容，希望文章能够帮你解决faster rcnn源码理解（二）之AnchorTargetLayer（网络中的rpn_data）所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。