def __call__(self, x, im_info): h, n = self.trunk(x), x.data.shape[0] rpn_cls_score = self.rpn_cls_score(h) c, hh, ww = rpn_cls_score.data.shape[1:] rpn_bbox_pred = self.rpn_bbox_pred(h) rpn_cls_score = F.reshape(rpn_cls_score, (n, 2, -1)) # RoI Proposal rpn_cls_prob = F.softmax(rpn_cls_score) rpn_cls_prob_reshape = F.reshape(rpn_cls_prob, (n, c, hh, ww)) rois = self.proposal_layer( rpn_cls_prob_reshape, rpn_bbox_pred, im_info, self.train) if self.gpu >= 0: rois = to_gpu(rois, device=self.gpu) im_info = to_gpu(im_info, device=self.gpu) with chainer.cuda.Device(self.gpu): boxes = rois[:, 1:5] / im_info[0][2] else: boxes = rois[:, 1:5] / im_info[0][2] rois = chainer.Variable(rois, volatile=not self.train) # RCNN pool5 = roi_pooling_2d(self.trunk.feature, rois, 7, 7, 0.0625) fc6 = F.relu(self.fc6(pool5)) fc7 = F.relu(self.fc7(fc6)) self.scores = F.softmax(self.cls_score(fc7)) box_deltas = self.bbox_pred(fc7).data pred_boxes = bbox_transform_inv(boxes, box_deltas, self.gpu) self.pred_boxes = clip_boxes(pred_boxes, im_info[0][:2], self.gpu) if self.train: # loss_cls = F.softmax_cross_entropy(cls_score, labels) # huber loss with delta=1 means SmoothL1Loss return None else: return self.scores, self.pred_boxes
def __call__(self, x, im_info): h, n = self.trunk(x), x.data.shape[0] rpn_cls_score = self.rpn_cls_score(h) c, hh, ww = rpn_cls_score.data.shape[1:] rpn_bbox_pred = self.rpn_bbox_pred(h) rpn_cls_score = F.reshape(rpn_cls_score, (n, 2, -1)) # RoI Proposal rpn_cls_prob = F.softmax(rpn_cls_score) rpn_cls_prob_reshape = F.reshape(rpn_cls_prob, (n, c, hh, ww)) rois = self.proposal_layer(rpn_cls_prob_reshape, rpn_bbox_pred, im_info, self.train) if self.gpu >= 0: rois = to_gpu(rois, device=self.gpu) im_info = to_gpu(im_info, device=self.gpu) with chainer.cuda.Device(self.gpu): boxes = rois[:, 1:5] / im_info[0][2] else: boxes = rois[:, 1:5] / im_info[0][2] rois = chainer.Variable(rois, volatile=not self.train) # RCNN pool5 = roi_pooling_2d(self.trunk.feature, rois, 7, 7, 0.0625) fc6 = F.relu(self.fc6(pool5)) fc7 = F.relu(self.fc7(fc6)) self.scores = F.softmax(self.cls_score(fc7)) box_deltas = self.bbox_pred(fc7).data pred_boxes = bbox_transform_inv(boxes, box_deltas, self.gpu) self.pred_boxes = clip_boxes(pred_boxes, im_info[0][:2], self.gpu) if self.train: # loss_cls = F.softmax_cross_entropy(cls_score, labels) # huber loss with delta=1 means SmoothL1Loss return None else: return self.scores, self.pred_boxes
def __call__(self, x, im_info, gt_boxes=None): h = self.trunk(x) if isinstance(im_info, chainer.cuda.cupy.ndarray): im_info = chainer.cuda.cupy.asnumpy(im_info) if self.train: im_info = im_info.data gt_boxes = gt_boxes.data if isinstance(gt_boxes, chainer.cuda.cupy.ndarray): im_info = chainer.cuda.cupy.asnumpy(im_info) gt_boxes = chainer.cuda.cupy.asnumpy(gt_boxes) rpn_cls_loss, rpn_loss_bbox, rois = self.RPN( h, im_info, self.gpu, gt_boxes) else: rois = self.RPN(h, im_info, self.gpu, gt_boxes) if self.train: rois, labels, bbox_targets, bbox_inside_weights, \ bbox_outside_weights = self.proposal_target_layer( rois, gt_boxes) # Convert rois if self.gpu >= 0: rois = to_gpu(rois, device=self.gpu) im_info = to_gpu(im_info, device=self.gpu) with chainer.cuda.Device(self.gpu): boxes = rois[:, 1:5] / im_info[0][2] else: boxes = rois[:, 1:5] / im_info[0][2] # RCNN pool5 = roi_pooling_2d( self.trunk.feature, rois, 7, 7, self.spatial_scale) fc6 = F.dropout(F.relu(self.fc6(pool5)), train=self.train) fc7 = F.dropout(F.relu(self.fc7(fc6)), train=self.train) # Per class probability cls_score = self.cls_score(fc7) cls_prob = F.softmax(cls_score) # BBox predictions bbox_pred = self.bbox_pred(fc7) box_deltas = bbox_pred.data if self.train: if self.gpu >= 0: tg = lambda x: to_gpu(x, device=self.gpu) labels = tg(labels) bbox_targets = tg(bbox_targets) bbox_inside_weights = tg(bbox_inside_weights) bbox_outside_weights = tg(bbox_outside_weights) loss_cls = F.softmax_cross_entropy(cls_score, labels) labels = Variable(labels, volatile='off') bbox_targets = Variable(bbox_targets, volatile='off') loss_bbox = smooth_l1_loss( bbox_pred, bbox_targets, bbox_inside_weights, bbox_outside_weights, self.sigma) reporter.report({'rpn_loss_cls': rpn_cls_loss, 'rpn_loss_bbox': rpn_loss_bbox, 'loss_bbox': loss_bbox, 'loss_cls': loss_cls}, self) return rpn_cls_loss, rpn_loss_bbox, loss_bbox, loss_cls else: pred_boxes = bbox_transform_inv(boxes, box_deltas, self.gpu) pred_boxes = clip_boxes(pred_boxes, im_info[0][:2], self.gpu) return cls_prob, pred_boxes
def __call__(self, x, im_info, gt_boxes=None): h = self.trunk(x) if chainer.cuda.available \ and isinstance(im_info, chainer.cuda.cupy.ndarray): im_info = chainer.cuda.cupy.asnumpy(im_info) if self.train: im_info = im_info.data gt_boxes = gt_boxes.data if isinstance(gt_boxes, chainer.cuda.cupy.ndarray): im_info = chainer.cuda.cupy.asnumpy(im_info) gt_boxes = chainer.cuda.cupy.asnumpy(gt_boxes) rpn_cls_loss, rpn_loss_bbox, rois = self.RPN( h, im_info, self.gpu, gt_boxes) else: rois = self.RPN(h, im_info, self.gpu, gt_boxes) if self.train: rois, labels, bbox_targets, bbox_inside_weights, \ bbox_outside_weights = self.proposal_target_layer( rois, gt_boxes) # Convert rois if self.gpu >= 0: rois = to_gpu(rois, device=self.gpu) im_info = to_gpu(im_info, device=self.gpu) with chainer.cuda.Device(self.gpu): boxes = rois[:, 1:5] / im_info[0][2] else: boxes = rois[:, 1:5] / im_info[0][2] # RCNN pool5 = roi_pooling_2d(self.trunk.feature, rois, 7, 7, self.spatial_scale) fc6 = F.dropout(F.relu(self.fc6(pool5)), train=self.train) fc7 = F.dropout(F.relu(self.fc7(fc6)), train=self.train) # Per class probability cls_score = self.cls_score(fc7) cls_prob = F.softmax(cls_score) # BBox predictions bbox_pred = self.bbox_pred(fc7) box_deltas = bbox_pred.data if self.train: if self.gpu >= 0: tg = lambda x: to_gpu(x, device=self.gpu) labels = tg(labels) bbox_targets = tg(bbox_targets) bbox_inside_weights = tg(bbox_inside_weights) bbox_outside_weights = tg(bbox_outside_weights) loss_cls = F.softmax_cross_entropy(cls_score, labels) labels = Variable(labels, volatile='auto') bbox_targets = Variable(bbox_targets, volatile='auto') loss_bbox = smooth_l1_loss(bbox_pred, bbox_targets, bbox_inside_weights, bbox_outside_weights, self.sigma) reporter.report( { 'rpn_loss_cls': rpn_cls_loss, 'rpn_loss_bbox': rpn_loss_bbox, 'loss_bbox': loss_bbox, 'loss_cls': loss_cls }, self) return rpn_cls_loss, rpn_loss_bbox, loss_bbox, loss_cls else: pred_boxes = bbox_transform_inv(boxes, box_deltas, self.gpu) pred_boxes = clip_boxes(pred_boxes, im_info[0][:2], self.gpu) return cls_prob, pred_boxes