def forward(self, feat, proposals, img_shape):
batch_size = proposals.shape[0]
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = torch.cat([rois_pad, proposals], dim=1)
# rcnn
bbox_results = self._bbox_forward(feat, rois)
cls_score = bbox_results['cls_score']
bbox_pred = bbox_results['bbox_pred']
bbox_head_outputs = self.bbox_head.get_bboxes(rois, cls_score,
bbox_pred, img_shape,
batch_size,
num_proposals,
self.test_cfg)
num_detections, det_boxes, det_scores, det_classes = bbox_head_outputs
result = [num_detections, det_boxes, det_scores, det_classes]
if self.enable_mask:
# mask roi input
num_mask_proposals = det_boxes.size(1)
rois_pad = mm2trt_util.arange_by_input(det_boxes, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_mask_proposals).view(-1, 1)
mask_proposals = det_boxes.view(-1, 4)
mask_rois = torch.cat([rois_pad, mask_proposals], dim=1)
mask_results = self._mask_forward(feat, mask_rois)
mask_pred = mask_results['mask_pred']
mc, mh, mw = mask_pred.shape[1:]
mask_pred = mask_pred.reshape(batch_size, -1, mc, mh, mw).sigmoid()
if not self.module.mask_head.class_agnostic:
det_index = det_classes.unsqueeze(-1).long()
det_index = det_index + 1
mask_pad = mask_pred[:, :, 0:1, ...] * 0
mask_pred = torch.cat([mask_pad, mask_pred], dim=2)
mask_pred = mm2trt_util.gather_topk(mask_pred,
dim=2,
index=det_index)
mask_pred = mask_pred.squeeze(2)
result += [mask_pred]
return result
def forward(self, feat, proposals):
batch_size = proposals.shape[0]
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = torch.cat([rois_pad, proposals], dim=1)
roi_feats = self.bbox_roi_extractor(
feat[:len(self.bbox_roi_extractor.featmap_strides)], rois)
if self.shared_head is not None:
roi_feats = self.shared_head(roi_feats)
# rcnn
cls_score, bbox_pred = self.bbox_head(roi_feats)
if isinstance(cls_score, list):
cls_score = sum(cls_score) / float(len(cls_score))
scores = F.softmax(cls_score, dim=1)
bboxes = delta2bbox(proposals, bbox_pred,
self.bbox_head.bbox_coder.means,
self.bbox_head.bbox_coder.stds)
scores = scores.view(batch_size, num_proposals, -1)
bboxes = bboxes.view(batch_size, num_proposals, -1, 4)
num_bboxes = bboxes.shape[1]
bboxes_ext = bboxes[:, :, 0:1, :] * 0
bboxes = torch.cat([bboxes, bboxes_ext], 2)
num_detections, det_boxes, det_scores, det_classes = self.rcnn_nms(
scores, bboxes, num_bboxes, self.test_cfg.max_per_img)
return num_detections, det_boxes, det_scores, det_classes
def bbox2roi(proposals):
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = torch.cat([rois_pad, proposals], dim=1)
return rois
def forward(self, feat, proposals, img_shape):
batch_size = proposals.shape[0]
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = torch.cat([rois_pad, proposals], dim=1)
# rcnn
bbox_results = self._bbox_forward(feat, rois)
cls_score = bbox_results['cls_score']
bbox_pred = bbox_results['bbox_pred']
bbox_head_outputs = self.bbox_head.get_bboxes(rois, cls_score,
bbox_pred, img_shape,
batch_size,
num_proposals,
self.test_cfg)
num_detections, det_boxes, det_scores, det_classes = bbox_head_outputs
grid_rois = bbox2roi(det_boxes)
grid_feats = self.grid_roi_extractor(
feat[:len(self.grid_roi_extractor.featmap_strides)], grid_rois)
grid_pred = self.grid_head(grid_feats)
det_scores, det_boxes = self.grid_head.get_bboxes(
det_scores.view(-1), det_boxes.view(-1, 4), grid_pred['fused'],
img_shape)
det_scores = det_scores.view(batch_size, -1)
det_boxes = det_boxes.view(batch_size, -1, 4)
return num_detections, det_boxes, det_scores, det_classes
def forward(self, feat ,proposals, img_shape):
ms_scores = []
batch_size = proposals.shape[0]
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = proposals
for i in range(self.num_stages):
bbox_results = self._bbox_forward(i, feat, torch.cat([rois_pad, rois], dim=1))
ms_scores.append(bbox_results['cls_score'])
bbox_pred = bbox_results['bbox_pred']
if i < self.num_stages - 1:
bbox_label = bbox_results['cls_score'].argmax(dim=1)
rois = self.bbox_head[i].regress_by_class(rois, bbox_label, bbox_pred, img_shape)
rois = torch.cat([rois_pad, rois], dim=1)
### bbox_head.get_boxes
cls_score = bbox_results['cls_score']
bbox_pred = bbox_results['bbox_pred']
num_detections, det_boxes, det_scores, det_classes = self.bbox_head[-1].get_bboxes(
rois,
cls_score,
bbox_pred,
img_shape,
batch_size,
num_proposals,
self.test_cfg
)
return num_detections, det_boxes, det_scores, det_classes
def forward(self, feat, proposals, img_shape):
batch_size = proposals.shape[0]
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = torch.cat([rois_pad, proposals], dim=1)
bbox_results = self._bbox_forward(feat, rois)
cls_score = bbox_results['cls_score']
bbox_pred = bbox_results['bbox_pred']
num_detections, det_boxes, det_scores, det_classes = self.bbox_head.get_bboxes(
rois, cls_score, bbox_pred, img_shape, batch_size, num_proposals,
self.test_cfg)
return num_detections, det_boxes, det_scores, det_classes
def forward(self, feat, proposals):
ms_scores = []
batch_size = proposals.shape[0]
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = proposals
for i in range(self.num_stages):
bbox_results = self._bbox_forward(
i, feat, torch.cat([rois_pad, rois], dim=1))
ms_scores.append(bbox_results['cls_score'])
bbox_pred = bbox_results['bbox_pred']
if i < self.num_stages - 1:
bbox_label = bbox_results['cls_score'].argmax(dim=1)
rois = self.regress_by_class(i, rois, bbox_label, bbox_pred)
### bbox_head.get_boxes
cls_score = sum(ms_scores) / self.num_stages
if isinstance(cls_score, list):
cls_score = sum(cls_score) / float(len(cls_score))
scores = F.softmax(cls_score, dim=1)
bbox_head = self.bbox_head[-1]
bboxes = delta2bbox(rois, bbox_pred, bbox_head.bbox_coder.means,
bbox_head.bbox_coder.stds)
scores = scores.view(batch_size, num_proposals, -1)
bboxes = bboxes.view(batch_size, num_proposals, -1, 4)
bboxes = bboxes.repeat(1, 1, bbox_head.num_classes, 1)
bboxes_ext = bboxes[:, :, 0:1, :] * 0
bboxes = torch.cat([bboxes, bboxes_ext], 2)
num_bboxes = bboxes.shape[1]
num_detections, det_boxes, det_scores, det_classes = self.rcnn_nms(
scores, bboxes, num_bboxes, self.test_cfg.max_per_img)
return num_detections, det_boxes, det_scores, det_classes
def forward(self, feat, proposals, img_shape):
ms_scores = []
batch_size = proposals.shape[0]
num_proposals = proposals.shape[1]
rois_pad = mm2trt_util.arange_by_input(proposals, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_proposals).view(-1, 1)
proposals = proposals.view(-1, 4)
rois = proposals
if self.module.with_semantic:
_, semantic_feat = self.semantic_head(feat)
else:
semantic_feat = None
for i in range(self.num_stages):
bbox_results = self._bbox_forward(
i,
feat,
torch.cat([rois_pad, rois], dim=1),
semantic_feat=semantic_feat)
ms_scores.append(bbox_results['cls_score'])
bbox_pred = bbox_results['bbox_pred']
if i < self.num_stages - 1:
bbox_label = bbox_results['cls_score'].argmax(dim=1)
rois = self.bbox_head[i].regress_by_class(
rois, bbox_label, bbox_pred, img_shape)
rois = torch.cat([rois_pad, rois], dim=1)
# bbox_head.get_boxes
cls_score = bbox_results['cls_score']
bbox_pred = bbox_results['bbox_pred']
num_detections, det_boxes, det_scores, det_classes = self.bbox_head[
-1].get_bboxes(rois, cls_score, bbox_pred, img_shape, batch_size,
num_proposals, self.test_cfg)
result = [num_detections, det_boxes, det_scores, det_classes]
if self.enable_mask:
# mask roi input
num_mask_proposals = det_boxes.size(1)
rois_pad = mm2trt_util.arange_by_input(det_boxes, 0).unsqueeze(1)
rois_pad = rois_pad.repeat(1, num_mask_proposals).view(-1, 1)
mask_proposals = det_boxes.view(-1, 4)
mask_rois = torch.cat([rois_pad, mask_proposals], dim=1)
mask_roi_extractor = self.mask_roi_extractor[-1]
mask_feats = mask_roi_extractor(
feat[:mask_roi_extractor.num_inputs], mask_rois)
if self.module.with_semantic and ('mask'
in self.module.semantic_fusion):
mask_semantic_feat = self.semantic_roi_extractor(
[semantic_feat], mask_rois)
mask_feats += mask_semantic_feat
last_feat = None
aug_masks = []
for i in range(self.num_stages):
mask_head = self.mask_head[i]
if self.module.mask_info_flow:
mask_pred, last_feat = mask_head(mask_feats, last_feat)
else:
mask_pred = mask_head(mask_feats)
mask_pred = mask_pred.sigmoid()
aug_masks.append(mask_pred)
mask_pred = merge_aug_masks(aug_masks, self.test_cfg)
mc, mh, mw = mask_pred.shape[1:]
mask_pred = mask_pred.reshape(batch_size, -1, mc, mh, mw)
if not self.module.mask_head[-1].class_agnostic:
det_index = det_classes.unsqueeze(-1).long()
det_index = det_index + 1
mask_pad = mask_pred[:, :, 0:1, ...] * 0
mask_pred = torch.cat([mask_pad, mask_pred], dim=2)
mask_pred = mm2trt_util.gather_topk(
mask_pred, dim=2, index=det_index)
mask_pred = mask_pred.squeeze(2)
result += [mask_pred]
return result
