Faster RCNN演算法訓練程式碼解析（3）
阿新 • • 發佈：2018-11-07
四個層的forward函式分析：
RoIDataLayer：讀資料，隨機打亂等
AnchorTargetLayer：輸出所有anchors（這裡分析這個）
ProposalLayer：用產生的anchors平移整圖，裁剪出界、移除低於閾值的的anchors，排序後使用nms，返回頂部排名的anchors
ProposalTargetLayer：將proposals分配給gt物體。得出proposal的分類標籤和box的迴歸目標。
緊接著之前的部落格，我們繼續來看faster rcnn中的AnchorTargetLayer層：
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)) self._num_anchors = self._anchors.shape[0] self._feat_stride = layer_params['feat_stride'] 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) height, width = bottom[0].data.shape[-2:] if DEBUG: print 'AnchorTargetLayer: height', height, 'width', width A = self._num_anchors # 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)
首先說一下這一層的目的是輸出在特徵圖上所有點的anchors（經過二分類和迴歸）；
（1）輸入blob：bottom[0]儲存特徵圖資訊，bottom[1]儲存gt框座標,bottom[2]儲存im_info資訊；
（2）輸出blob：top[0]儲存anchors的label值（fg是1,bg是0,-1類不關心）,top[1]儲存的是生成的anchors的迴歸偏移量，即論文中的tx,ty,tw,th四個量（所以說整個faster rcnn總共兩次bbox迴歸，第一次在RPN中，第二次在fast rcnn中），top[2]和top[3]分別儲存的是bbox_inside_weights和bbox_outside_weights。
好的，先進入層的setup函式：該函式通過解析父類對自己的一些引數進行初始化，同時定義該層的輸入輸出blob;
該函式中要注意的是generate_anchors()函式，它的作用是產生對應與特徵圖上最左上角那個點的九種anchor（尺寸對應與輸入影象），這9個anchor在後面被用來產生所有影象上的anchors，進入generate_anchors（）函式。前面部落格做過分析了，不再累述。
接著向下看該層的前向傳播函式forward函式：
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:] ##bottom[0]特徵圖資訊，bottom[1]gt座標，bottom[3]為im_info # GT boxes (x1, y1, x2, y2, label) gt_boxes = bottom[1].data # 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 ##對映原圖的偏移量 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))) ##左上角anchor進行偏移覆蓋全圖 all_anchors = all_anchors.reshape((K * A, 4)) total_anchors = int(K * A) # only keep anchors inside the image ，保留位置在影象內的anchors 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] if DEBUG: print 'total_anchors', total_anchors print 'inds_inside', len(inds_inside) # keep only inside anchors anchors = all_anchors[inds_inside, :] if DEBUG: print 'anchors.shape', anchors.shape
########################################################################################################################
##這裡的shift_x和shift_y分別對應x和y軸上的偏移量，用在之前說過的用generate_anchors（）函式生成的最左上角的anchors上，
##對其進行偏移，從而獲得所有影象上的anchors；all_anchors用來儲存所有這些anchors，total_anchors用來儲存這些anchors的數量K×A,其中，
##K是輸入影象的num,A是一幅影象上anchor的num；之後作者還對這些anchors進行了篩選，超出影象邊界的anchors都將其丟棄～繼續：
##########################################################################################################################
# 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)) ##n*k,重疊率 argmax_overlaps = overlaps.argmax(axis=1) 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 #################################################################################################################
##這一部分主要就是獲得這些anchors和對應gt的最大重疊率的情況，以及正樣本的劃分標準：a.對於每一個gt，重疊率最大的那個anchor為fg；
##b,對於每一個gt，最大重疊率大於0.7的為fg；
#################################################################################################################
# subsample positive labels if we have too many 正樣本太多就取樣 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
##這裡則是通過_unmap()函式實現將之前在所有影象上產生的anchors都賦上label、bbox_targets、bbox_inside_weights、bbox_outside_weights屬性
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
這一部分是生成bbox_targets、bbox_inside_weights、bbox_inside_weights；其中對於bbox_targets，它這裡是呼叫了_compute_targets()函式，見：
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)
在該函式又接著呼叫了bbox_transform函式，見：
def bbox_transform(ex_rois, gt_rois): ex_widths = ex_rois[:, 2] - ex_rois[:, 0] + 1.0 ex_heights = ex_rois[:, 3] - ex_rois[:, 1] + 1.0 ex_ctr_x = ex_rois[:, 0] + 0.5 * ex_widths ex_ctr_y = ex_rois[:, 1] + 0.5 * ex_heights gt_widths = gt_rois[:, 2] - gt_rois[:, 0] + 1.0 gt_heights = gt_rois[:, 3] - gt_rois[:, 1] + 1.0 gt_ctr_x = gt_rois[:, 0] + 0.5 * gt_widths gt_ctr_y = gt_rois[:, 1] + 0.5 * gt_heights targets_dx = (gt_ctr_x - ex_ctr_x) / ex_widths targets_dy = (gt_ctr_y - ex_ctr_y) / ex_heights targets_dw = np.log(gt_widths / ex_widths) targets_dh = np.log(gt_heights / ex_heights) targets = np.vstack( (targets_dx, targets_dy, targets_dw, targets_dh)).transpose() return targets
從而得到了論文中所需要的四個偏移量tx,ty,tw,th四個量；
而對於後兩個bbox_inside_weights和bbox_outside_weights，函式中定義的是bbox_inside_weights初始化為n×4的0陣列，然後其中正樣本的座標的權值均為1；而bbox_outside_weights同樣的初始化，其中正樣本和負樣本都被賦值1/num(anchors的數量)。