1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350
|
import os 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 import pdb
DEBUG = False
def anchor_target_layer(rpn_cls_score, gt_boxes, im_info, data, _feat_stride=[16, ], anchor_scales=[4, 8, 16, 32]): """ Assign anchors to ground-truth targets. Produces anchor classification labels and bounding-box regression targets. """
_anchors = generate_anchors(scales=np.array(anchor_scales)) _num_anchors = _anchors.shape[0]
if DEBUG: print 'anchors:' print _anchors print 'anchor shapes:' print np.hstack(( _anchors[:, 2::4] - _anchors[:, 0::4], _anchors[:, 3::4] - _anchors[:, 1::4], )) _counts = cfg.EPS _sums = np.zeros((1, 4)) _squared_sums = np.zeros((1, 4)) _fg_sum = 0 _bg_sum = 0 _count = 0
_allowed_border = 0
im_info = im_info[0]
assert rpn_cls_score.shape[0] == 1, \ 'Only single item batches are supported'
height, width = rpn_cls_score.shape[1:3]
if DEBUG: print 'AnchorTargetLayer: height', height, 'width', width 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
shift_x = np.arange(0, width) * _feat_stride shift_y = np.arange(0, height) * _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() A = _num_anchors K = shifts.shape[0] all_anchors = (_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)
inds_inside = np.where( (all_anchors[:, 0] >= -_allowed_border) & (all_anchors[:, 1] >= -_allowed_border) & (all_anchors[:, 2] < im_info[1] + _allowed_border) & (all_anchors[:, 3] < im_info[0] + _allowed_border) )[0]
if DEBUG: print 'total_anchors', total_anchors print 'inds_inside', len(inds_inside)
anchors = all_anchors[inds_inside, :] if DEBUG: print 'anchors.shape', anchors.shape
labels = np.empty((len(inds_inside),), dtype=np.float32) labels.fill(-1)
overlaps = bbox_overlaps( np.ascontiguousarray(anchors, dtype=np.float), np.ascontiguousarray(gt_boxes, dtype=np.float))
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: labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0
labels[gt_argmax_overlaps] = 1
labels[max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1
if cfg.TRAIN.RPN_CLOBBER_POSITIVES: labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0
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
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
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:
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: _sums += bbox_targets[labels == 1, :].sum(axis=0) _squared_sums += (bbox_targets[labels == 1, :] ** 2).sum(axis=0) _counts += np.sum(labels == 1) means = _sums / _counts stds = np.sqrt(_squared_sums / _counts - means ** 2) print 'means:' print means print 'stdevs:' print stds
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) _fg_sum += np.sum(labels == 1) _bg_sum += np.sum(labels == 0) _count += 1 print 'rpn: num_positive avg', _fg_sum / _count print 'rpn: num_negative avg', _bg_sum / _count
labels = labels.reshape((1, height, width, A)).transpose(0, 3, 1, 2) labels = labels.reshape((1, 1, A * height, width)) rpn_labels = labels
bbox_targets = bbox_targets.reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)
rpn_bbox_targets = bbox_targets bbox_inside_weights = bbox_inside_weights.reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)
rpn_bbox_inside_weights = bbox_inside_weights
bbox_outside_weights = bbox_outside_weights.reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2)
rpn_bbox_outside_weights = bbox_outside_weights
return rpn_labels, rpn_bbox_targets, rpn_bbox_inside_weights, rpn_bbox_outside_weights
def _unmap(data, count, inds, fill=0): """ Unmap a subset of item (data) back to the original set of items (of size count) 在之前的处理过程中,我们一直在处理存在于图片边界内部的anchors,还有相当多的anchors在图片边界外部或者在图片边界上。 而这一部分我们直接忽略掉了,现在利用这个函数将他们也进行简单处理,赋予他们所需要的label和weights信息。 :param data: 该参数有两种形式,一个是图片内部anchors的labels,另一个是图片内部anchors的RPN回归目标以及权重等信息。 labels是一个一维数组,其他的都是shape为[N, 4]形状的二维数组。 :param count:原始anchors的数目,这里包括图片边缘内部的,也包括存在于图片边缘上的和外部的。 :param inds: 存在于图片边缘内部的anchors在原始anchors序列中的索引,也是一个一维数组。 :param fill: 默认填充的数值,在图片边缘上的和外部的anchors没有经过前面的计算过程,这些参数只用fill提供的值默认填充。 :return: 补完之后的信息,这里的信息是所有anchors的信息,包括图片内部的,边界上的和边界外的、 """
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. :param ex_rois: 待处理的rois,一般是一系列anchors :param gt_rois: ground truth boxes, 与每一个ex_rois(anchor)一一对应,每一行都是与当前ex_roi(anchor)其拥有最大IOU的gt box。 :return: """
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)
|