ProposalLayer源碼解析

ProposalLayer源碼解析

標籤（空格分隔）： faster-rcnn 物體檢測 源碼

---

# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick and Sean Bell
# --------------------------------------------------------

import caffe
import numpy as np
import yaml
from fast_rcnn.config import cfg
from generate_anchors import generate_anchors
from fast_rcnn.bbox_transform import bbox_transform_inv, clip_boxes
from fast_rcnn.nms_wrapper import nms

DEBUG = False

'''
ProposalLayer是由python寫的一個層
ProposalLayer有兩個輸入
bottom[0]：是每一個anchor是否是前景的概率，大小爲：(batch_size,2*k,w,h)
bottom[1]: 每個anchor的座標偏移量，大小爲：(batch_size,4*k,w,h)

ProposalLayer的輸出是一個二維矩陣
top[0]:(num_rois,5)
每一行代表（batch_ind,start_w,start_h,end_w,end_h）
'''
class ProposalLayer(caffe.Layer):
    """
    Outputs object detection proposals by applying estimated bounding-box
    transformations to a set of regular boxes (called "anchors").
    """
'setup這個函數從配置文件中讀取配置信息，包括共享卷積層最後一層的feature map 相對於原始圖像的縮放比例'
'以及anchor的寬高比和基準尺寸之類的'

    def setup(self, bottom, top):
        # parse the layer parameter string, which must be valid YAML
        layer_params = yaml.load(self.param_str_)

        self._feat_stride = layer_params['feat_stride']
        anchor_scales = layer_params.get('scales', (8, 16, 32))
        self._anchors = generate_anchors(scales=np.array(anchor_scales))
        self._num_anchors = self._anchors.shape[0]。#feature map上的每一點產生的anchor數

        if DEBUG:
            print 'feat_stride: {}'.format(self._feat_stride)
            print 'anchors:'
            print self._anchors

        # rois blob: holds R regions of interest, each is a 5-tuple
        # (n, x1, y1, x2, y2) specifying an image batch index n and a
        # rectangle (x1, y1, x2, y2)
        top[0].reshape(1, 5)

        # scores blob: holds scores for R regions of interest
        if len(top) > 1:
            top[1].reshape(1, 1, 1, 1)

    def forward(self, bottom, top):
        # Algorithm:
        #
        # for each (H, W) location i
        #   generate A anchor boxes centered on cell i
        #   apply predicted bbox deltas at cell i to each of the A anchors
        # clip predicted boxes to image
        # remove predicted boxes with either height or width < threshold
        # sort all (proposal, score) pairs by score from highest to lowest
        # take top pre_nms_topN proposals before NMS
        # apply NMS with threshold 0.7 to remaining proposals
        # take after_nms_topN proposals after NMS
        # return the top proposals (-> RoIs top, scores top)

        assert bottom[0].data.shape[0] == 1, \
            'Only single item batches are supported'
        '''
        從配置文件中讀取相關的配置參數

        cfg_key：當前是測試階段還是訓練階段；
        pre_nms_topN: 在NMS處理之前，分數在前面的rois
        post_nms_topN: 在NMS處理之後，分數在前面的rois
        nms_thresh: NMS的閾值
        min_size: rois最小的尺寸

        '''
        cfg_key = str(self.phase) # either 'TRAIN' or 'TEST'
        pre_nms_topN  = cfg[cfg_key].RPN_PRE_NMS_TOP_N
        post_nms_topN = cfg[cfg_key].RPN_POST_NMS_TOP_N
        nms_thresh    = cfg[cfg_key].RPN_NMS_THRESH
        min_size      = cfg[cfg_key].RPN_MIN_SIZE

        # the first set of _num_anchors channels are bg probs
        # the second set are the fg probs, which we want
        scores = bottom[0].data[:, self._num_anchors:, :, :] #選取前num_anchors個feature map
        bbox_deltas = bottom[1].data               #bottom[1]相對於默認的座標的偏移量
        im_info = bottom[2].data[0, :]            #原圖像的相關信息，長寬之類的

        if DEBUG:
            print 'im_size: ({}, {})'.format(im_info[0], im_info[1])
            print 'scale: {}'.format(im_info[2])

        # 1. Generate proposals from bbox deltas and shifted anchors
        height, width = scores.shape[-2:]

        if DEBUG:
            print 'score map size: {}'.format(scores.shape)

        # Enumerate all shifts
        '將feature map上的點對應到原圖像上'
        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()#shifts的大小爲是一個二維舉證（w*h,4）

        # Enumerate all shifted anchors:
        #
        # 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]
        anchors = self._anchors.reshape((1, A, 4)) + \
                  shifts.reshape((1, K, 4)).transpose((1, 0, 2))
        anchors = anchors.reshape((K * A, 4))#生成默認的anchor的座標

        # Transpose and reshape predicted bbox transformations to get them
        # into the same order as the anchors:
        #
        # bbox deltas will be (1, 4 * A, H, W) format
        # transpose to (1, H, W, 4 * A)
        # reshape to (1 * H * W * A, 4) where rows are ordered by (h, w, a)
        # in slowest to fastest order
        bbox_deltas = bbox_deltas.transpose((0, 2, 3, 1)).reshape((-1, 4))#生成anchor座標的偏移量，anchor的個數爲A(w*h)*K

        # Same story for the scores:
        #
        # scores are (1, A, H, W) format
        # transpose to (1, H, W, A)
        # reshape to (1 * H * W * A, 1) where rows are ordered by (h, w, a)
        scores = scores.transpose((0, 2, 3, 1)).reshape((-1, 1))#獲取每一個anchor的分數

        # Convert anchors into proposals via bbox transformations
        proposals = bbox_transform_inv(anchors, bbox_deltas)#進行座標偏移，經過這一步之後anchor邊成了proposal

        # 2. clip predicted boxes to image
        proposals = clip_boxes(proposals, im_info[:2])#然後 將proposal限制在原圖像範圍之內

        # 3. remove predicted boxes with either height or width < threshold
        # (NOTE: convert min_size to input image scale stored in im_info[2])
        keep = _filter_boxes(proposals, min_size * im_info[2])#最小尺寸的限制
        proposals = proposals[keep, :]
        scores = scores[keep]

        # 4. sort all (proposal, score) pairs by score from highest to lowest
        # 5. take top pre_nms_topN (e.g. 6000)
        order = scores.ravel().argsort()[::-1]#對分數進行排序，
        if pre_nms_topN > 0:
            order = order[:pre_nms_topN]
        proposals = proposals[order, :]#在nms之前取pre_nms_topN個proposal
        scores = scores[order]

        # 6. apply nms (e.g. threshold = 0.7)
        # 7. take after_nms_topN (e.g. 300)
        # 8. return the top proposals (-> RoIs top)
        keep = nms(np.hstack((proposals, scores)), nms_thresh)#進行NMS
        if post_nms_topN > 0:
            keep = keep[:post_nms_topN]
        proposals = proposals[keep, :]#取NMS之後的post_nms_topN
        scores = scores[keep]#獲取對應分數

        # Output rois blob
        # Our RPN implementation only supports a single input image, so all
        # batch inds are 0
        batch_inds = np.zeros((proposals.shape[0], 1), dtype=np.float32)#獲取batch_size的索引，將proposal對應到batch_size的那一張圖片
        blob = np.hstack((batch_inds, proposals.astype(np.float32, copy=False)))
        top[0].reshape(*(blob.shape))
        top[0].data[...] = blob

        # [Optional] output scores blob
        if len(top) > 1:
            top[1].reshape(*(scores.shape))
            top[1].data[...] = scores

    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 _filter_boxes(boxes, min_size):
    """Remove all boxes with any side smaller than min_size."""
    ws = boxes[:, 2] - boxes[:, 0] + 1
    hs = boxes[:, 3] - boxes[:, 1] + 1
    keep = np.where((ws >= min_size) & (hs >= min_size))[0]
    return keep