Python mmdet.core.multiclass_nms() Examples
The following are 30
code examples of mmdet.core.multiclass_nms().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
mmdet.core
, or try the search function
.
.
Example #1
| Source File: bbox_head.py From AerialDetection with Apache License 2.0 | 5 votes |
|
def get_det_bboxes(self,
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None):
if isinstance(cls_score, list):
cls_score = sum(cls_score) / float(len(cls_score))
scores = F.softmax(cls_score, dim=1) if cls_score is not None else None
if bbox_pred is not None:
bboxes = delta2bbox(rois[:, 1:], bbox_pred, self.target_means,
self.target_stds, img_shape)
else:
bboxes = rois[:, 1:]
# TODO: add clip here
if rescale:
bboxes /= scale_factor
if cfg is None:
return bboxes, scores
else:
det_bboxes, det_labels = multiclass_nms(bboxes, scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #2
| Source File: reppoints_detector.py From Cascade-RPN with Apache License 2.0 | 5 votes |
|
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Example #3
| Source File: reppoints_detector.py From RepPoints with MIT License | 5 votes |
|
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
# TODO more flexible
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Example #4
| Source File: bbox_head.py From mmdetection_with_SENet154 with Apache License 2.0 | 5 votes |
|
def get_det_bboxes(self,
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None):
if isinstance(cls_score, list):
cls_score = sum(cls_score) / float(len(cls_score))
scores = F.softmax(cls_score, dim=1) if cls_score is not None else None
if bbox_pred is not None:
bboxes = delta2bbox(rois[:, 1:], bbox_pred, self.target_means,
self.target_stds, img_shape)
else:
bboxes = rois[:, 1:]
# TODO: add clip here
if rescale:
bboxes /= scale_factor
if cfg is None:
return bboxes, scores
else:
det_bboxes, det_labels = multiclass_nms(bboxes, scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #5
| Source File: reppoints_detector.py From ttfnet with Apache License 2.0 | 5 votes |
|
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Example #6
| Source File: reppoints_detector.py From IoU-Uniform-R-CNN with Apache License 2.0 | 5 votes |
|
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Example #7
| Source File: reppoints_detector.py From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 | 5 votes |
|
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Example #8
| Source File: reppoints_detector.py From kaggle-kuzushiji-recognition with MIT License | 5 votes |
|
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Example #9
| Source File: reppoints_detector.py From RDSNet with Apache License 2.0 | 5 votes |
|
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Example #10
| Source File: fovea_head.py From ttfnet with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
featmap_sizes,
point_list,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(point_list)
det_bboxes = []
det_scores = []
for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) \
in zip(cls_scores, bbox_preds, featmap_sizes, self.strides,
self.base_edge_list, point_list):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
nms_pre = cfg.get('nms_pre', -1)
if (nms_pre > 0) and (scores.shape[0] > nms_pre):
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
y = y[topk_inds]
x = x[topk_inds]
x1 = (stride * x - base_len * bbox_pred[:, 0]).\
clamp(min=0, max=img_shape[1] - 1)
y1 = (stride * y - base_len * bbox_pred[:, 1]).\
clamp(min=0, max=img_shape[0] - 1)
x2 = (stride * x + base_len * bbox_pred[:, 2]).\
clamp(min=0, max=img_shape[1] - 1)
y2 = (stride * y + base_len * bbox_pred[:, 3]).\
clamp(min=0, max=img_shape[0] - 1)
bboxes = torch.stack([x1, y1, x2, y2], -1)
det_bboxes.append(bboxes)
det_scores.append(scores)
det_bboxes = torch.cat(det_bboxes)
if rescale:
det_bboxes /= det_bboxes.new_tensor(scale_factor)
det_scores = torch.cat(det_scores)
padding = det_scores.new_zeros(det_scores.shape[0], 1)
det_scores = torch.cat([padding, det_scores], dim=1)
det_bboxes, det_labels = multiclass_nms(det_bboxes, det_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #11
| Source File: fcos_head.py From Cascade-RPN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #12
| Source File: fcos_head.py From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #13
| Source File: fcos_head.py From CenterNet with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #14
| Source File: fcos_plus_head.py From CenterNet with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #15
| Source File: fcos_head.py From Libra_R-CNN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #16
| Source File: fcos_head.py From ttfnet with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #17
| Source File: fcos_head.py From AugFPN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #18
| Source File: fcos_head.py From AugFPN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single_auxiliary(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes
Example #19
| Source File: retina_head.py From AugFPN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single_auxiliary(self,
cls_scores,
bbox_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, anchors in zip(cls_scores, bbox_preds,
mlvl_anchors):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
cls_score = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
max_scores, _ = scores[:, 1:].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = delta2bbox(anchors, bbox_pred, self.target_means,
self.target_stds, img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes, mlvl_scores, cfg.score_thr, cfg.nms, cfg.max_per_img)
return det_bboxes
Example #20
| Source File: fovea_head.py From Cascade-RPN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
featmap_sizes,
point_list,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(point_list)
det_bboxes = []
det_scores = []
for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) \
in zip(cls_scores, bbox_preds, featmap_sizes, self.strides,
self.base_edge_list, point_list):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
nms_pre = cfg.get('nms_pre', -1)
if (nms_pre > 0) and (scores.shape[0] > nms_pre):
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
y = y[topk_inds]
x = x[topk_inds]
x1 = (stride * x - base_len * bbox_pred[:, 0]).\
clamp(min=0, max=img_shape[1] - 1)
y1 = (stride * y - base_len * bbox_pred[:, 1]).\
clamp(min=0, max=img_shape[0] - 1)
x2 = (stride * x + base_len * bbox_pred[:, 2]).\
clamp(min=0, max=img_shape[1] - 1)
y2 = (stride * y + base_len * bbox_pred[:, 3]).\
clamp(min=0, max=img_shape[0] - 1)
bboxes = torch.stack([x1, y1, x2, y2], -1)
det_bboxes.append(bboxes)
det_scores.append(scores)
det_bboxes = torch.cat(det_bboxes)
if rescale:
det_bboxes /= det_bboxes.new_tensor(scale_factor)
det_scores = torch.cat(det_scores)
padding = det_scores.new_zeros(det_scores.shape[0], 1)
det_scores = torch.cat([padding, det_scores], dim=1)
det_bboxes, det_labels = multiclass_nms(det_bboxes, det_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #21
| Source File: fcos_head.py From FoveaBox with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #22
| Source File: fovea_head.py From FoveaBox with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
featmap_sizes,
point_list,
img_shape,
scale_factor,
cfg,
rescale=False, debug=False):
assert len(cls_scores) == len(bbox_preds) == len(point_list)
det_bboxes = []
det_scores = []
for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) in zip(
cls_scores, bbox_preds, featmap_sizes, self.strides, self.base_edge_list, point_list):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
y = y[topk_inds]
x = x[topk_inds]
x1 = (stride * x - base_len * bbox_pred[:, 0]).clamp(min=0, max=img_shape[1] - 1)
y1 = (stride * y - base_len * bbox_pred[:, 1]).clamp(min=0, max=img_shape[0] - 1)
x2 = (stride * x + base_len * bbox_pred[:, 2]).clamp(min=0, max=img_shape[1] - 1)
y2 = (stride * y + base_len * bbox_pred[:, 3]).clamp(min=0, max=img_shape[0] - 1)
bboxes = torch.stack([x1, y1, x2, y2], -1)
det_bboxes.append(bboxes)
det_scores.append(scores)
det_bboxes = torch.cat(det_bboxes)
if rescale:
det_bboxes /= det_bboxes.new_tensor(scale_factor)
det_scores = torch.cat(det_scores)
padding = det_scores.new_zeros(det_scores.shape[0], 1)
det_scores = torch.cat([padding, det_scores], dim=1)
if debug:
det_bboxes, det_labels = multiclass_nms(
det_bboxes,
det_scores,
cfg['score_thr'],
cfg['nms'],
cfg['max_per_img'])
else:
det_bboxes, det_labels = multiclass_nms(
det_bboxes,
det_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #23
| Source File: fovea_head.py From mmdetection with Apache License 2.0 | 4 votes |
|
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
featmap_sizes,
point_list,
img_shape,
scale_factor,
cfg,
rescale=False):
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_scores) == len(bbox_preds) == len(point_list)
det_bboxes = []
det_scores = []
for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) \
in zip(cls_scores, bbox_preds, featmap_sizes, self.strides,
self.base_edge_list, point_list):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
nms_pre = cfg.get('nms_pre', -1)
if (nms_pre > 0) and (scores.shape[0] > nms_pre):
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
y = y[topk_inds]
x = x[topk_inds]
x1 = (stride * x - base_len * bbox_pred[:, 0]).\
clamp(min=0, max=img_shape[1] - 1)
y1 = (stride * y - base_len * bbox_pred[:, 1]).\
clamp(min=0, max=img_shape[0] - 1)
x2 = (stride * x + base_len * bbox_pred[:, 2]).\
clamp(min=0, max=img_shape[1] - 1)
y2 = (stride * y + base_len * bbox_pred[:, 3]).\
clamp(min=0, max=img_shape[0] - 1)
bboxes = torch.stack([x1, y1, x2, y2], -1)
det_bboxes.append(bboxes)
det_scores.append(scores)
det_bboxes = torch.cat(det_bboxes)
if rescale:
det_bboxes /= det_bboxes.new_tensor(scale_factor)
det_scores = torch.cat(det_scores)
padding = det_scores.new_zeros(det_scores.shape[0], 1)
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
det_scores = torch.cat([det_scores, padding], dim=1)
det_bboxes, det_labels = multiclass_nms(det_bboxes, det_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #24
| Source File: fcos_head.py From IoU-Uniform-R-CNN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #25
| Source File: fovea_head.py From IoU-Uniform-R-CNN with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
featmap_sizes,
point_list,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(point_list)
det_bboxes = []
det_scores = []
for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) \
in zip(cls_scores, bbox_preds, featmap_sizes, self.strides,
self.base_edge_list, point_list):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
nms_pre = cfg.get('nms_pre', -1)
if (nms_pre > 0) and (scores.shape[0] > nms_pre):
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
y = y[topk_inds]
x = x[topk_inds]
x1 = (stride * x - base_len * bbox_pred[:, 0]).\
clamp(min=0, max=img_shape[1] - 1)
y1 = (stride * y - base_len * bbox_pred[:, 1]).\
clamp(min=0, max=img_shape[0] - 1)
x2 = (stride * x + base_len * bbox_pred[:, 2]).\
clamp(min=0, max=img_shape[1] - 1)
y2 = (stride * y + base_len * bbox_pred[:, 3]).\
clamp(min=0, max=img_shape[0] - 1)
bboxes = torch.stack([x1, y1, x2, y2], -1)
det_bboxes.append(bboxes)
det_scores.append(scores)
det_bboxes = torch.cat(det_bboxes)
if rescale:
det_bboxes /= det_bboxes.new_tensor(scale_factor)
det_scores = torch.cat(det_scores)
padding = det_scores.new_zeros(det_scores.shape[0], 1)
det_scores = torch.cat([padding, det_scores], dim=1)
det_bboxes, det_labels = multiclass_nms(det_bboxes, det_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #26
| Source File: fcos_head.py From RDSNet with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #27
| Source File: fcos_head.py From kaggle-kuzushiji-recognition with MIT License | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #28
| Source File: fovea_head.py From kaggle-kuzushiji-recognition with MIT License | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
featmap_sizes,
point_list,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(point_list)
det_bboxes = []
det_scores = []
for cls_score, bbox_pred, featmap_size, stride, base_len, (y, x) \
in zip(cls_scores, bbox_preds, featmap_sizes, self.strides,
self.base_edge_list, point_list):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4).exp()
nms_pre = cfg.get('nms_pre', -1)
if (nms_pre > 0) and (scores.shape[0] > nms_pre):
max_scores, _ = scores.max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
y = y[topk_inds]
x = x[topk_inds]
x1 = (stride * x - base_len * bbox_pred[:, 0]).\
clamp(min=0, max=img_shape[1] - 1)
y1 = (stride * y - base_len * bbox_pred[:, 1]).\
clamp(min=0, max=img_shape[0] - 1)
x2 = (stride * x + base_len * bbox_pred[:, 2]).\
clamp(min=0, max=img_shape[1] - 1)
y2 = (stride * y + base_len * bbox_pred[:, 3]).\
clamp(min=0, max=img_shape[0] - 1)
bboxes = torch.stack([x1, y1, x2, y2], -1)
det_bboxes.append(bboxes)
det_scores.append(scores)
det_bboxes = torch.cat(det_bboxes)
if rescale:
det_bboxes /= det_bboxes.new_tensor(scale_factor)
det_scores = torch.cat(det_scores)
padding = det_scores.new_zeros(det_scores.shape[0], 1)
det_scores = torch.cat([padding, det_scores], dim=1)
det_bboxes, det_labels = multiclass_nms(det_bboxes, det_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
Example #29
| Source File: fcos_head.py From PolarMask with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
Example #30
| Source File: fcos_head.py From mmdetection-annotated with Apache License 2.0 | 4 votes |
|
def get_bboxes_single(self,
cls_scores,
bbox_preds,
centernesses,
mlvl_points,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points)
mlvl_bboxes = []
mlvl_scores = []
mlvl_centerness = []
for cls_score, bbox_pred, centerness, points in zip(
cls_scores, bbox_preds, centernesses, mlvl_points):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
scores = cls_score.permute(1, 2, 0).reshape(
-1, self.cls_out_channels).sigmoid()
centerness = centerness.permute(1, 2, 0).reshape(-1).sigmoid()
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
max_scores, _ = (scores * centerness[:, None]).max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
points = points[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
centerness = centerness[topk_inds]
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_centerness.append(centerness)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
mlvl_centerness = torch.cat(mlvl_centerness)
det_bboxes, det_labels = multiclass_nms(
mlvl_bboxes,
mlvl_scores,
cfg.score_thr,
cfg.nms,
cfg.max_per_img,
score_factors=mlvl_centerness)
return det_bboxes, det_labels
