How to use the mmdet.datasets.utils.to_tensor function in mmdet
To help you get started, we’ve selected a few mmdet examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
musket-ml / segmentation_training_pipeline / segmentation_pipeline / mmdetection.py View on Github 
def prepare_single(img, scale, flip, proposal=None):
_img, img_shape, pad_shape, scale_factor = self.img_transform(
img, scale, flip, keep_ratio=self.resize_keep_ratio)
_img = to_tensor(_img)
_img_meta = dict(
ori_shape=(img_info['height'], img_info['width'], 3),
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
if proposal is not None:
if proposal.shape[1] == 5:
score = proposal[:, 4, None]
proposal = proposal[:, :4]
else:
score = None
_proposal = self.bbox_transform(proposal, img_shape,
scale_factor, flip)
_proposal = np.hstack(
[_proposal, score]) if score is not None else _proposaldef prepare_single(img, scale, flip, proposal=None):
_img, img_shape, pad_shape, scale_factor = self.img_transform(
img, scale, flip)
_img = to_tensor(_img)
_img_meta = dict(
ori_shape=(img_info['height'], img_info['width'], 3),
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
if proposal is not None:
if proposal.shape[1] == 5:
score = proposal[:, 4, None]
proposal = proposal[:, :4]
else:
score = None
_proposal = self.bbox_transform(proposal, img_shape,
scale_factor, flip)
_proposal = np.hstack(
[_proposal, score]) if score is not None else _proposalimg_meta = dict(
ori_shape=ori_shape,
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
data = dict(
img=DC(to_tensor(img), stack=True),
img_meta=DC(img_meta, cpu_only=True),
gt_bboxes=DC(to_tensor(gt_bboxes)))
if self.with_label:
data['gt_labels'] = DC(to_tensor(gt_labels))
if self.with_crowd:
data['gt_bboxes_ignore'] = DC(to_tensor(gt_bboxes_ignore))
if self.with_mask:
data['gt_masks'] = DC(gt_masks, cpu_only=True)
#--------------------offline ray label generation-----------------------------
self.center_sample = True
self.use_mask_center = True
self.radius = 1.5
self.strides = [8, 16, 32, 64, 128]
self.regress_ranges=((-1, 64), (64, 128), (128, 256), (256, 512),(512, INF))
featmap_sizes = self.get_featmap_size(pad_shape)
self.featmap_sizes = featmap_sizes
num_levels = len(self.strides)
all_level_points = self.get_points(featmap_sizes)
self.num_points_per_level = [i.size()[0] for i in all_level_points]ori_shape=(img_info['height'], img_info['width'], 3),
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
if proposal is not None:
if proposal.shape[1] == 5:
score = proposal[:, 4, None]
proposal = proposal[:, :4]
else:
score = None
_proposal = self.bbox_transform(proposal, img_shape,
scale_factor, flip)
_proposal = np.hstack(
[_proposal, score]) if score is not None else _proposal
_proposal = to_tensor(_proposal)
else:
_proposal = None
return _img, _img_meta, _proposalgt_bboxes_ignore = self.bbox_transform(gt_bboxes_ignore, img_shape,
scale_factor, flip)
if self.with_mask:
gt_masks = self.mask_transform(ann['masks'], pad_shape,
scale_factor, flip)
ori_shape = (img_info['height'], img_info['width'], 3)
img_meta = dict(
ori_shape=ori_shape,
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
data = dict(
img=DC(to_tensor(img), stack=True),
img_meta=DC(img_meta, cpu_only=True),
gt_bboxes=DC(to_tensor(gt_bboxes)))
if self.with_label:
data['gt_labels'] = DC(to_tensor(gt_labels))
if self.with_crowd:
data['gt_bboxes_ignore'] = DC(to_tensor(gt_bboxes_ignore))
if self.with_mask:
data['gt_masks'] = DC(gt_masks, cpu_only=True)
#--------------------offline ray label generation-----------------------------
self.center_sample = True
self.use_mask_center = True
self.radius = 1.5ori_shape=(img_info['height'], img_info['width'], 3),
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
if proposal is not None:
if proposal.shape[1] == 5:
score = proposal[:, 4, None]
proposal = proposal[:, :4]
else:
score = None
_proposal = self.bbox_transform(proposal, img_shape,
scale_factor, flip)
_proposal = np.hstack(
[_proposal, score]) if score is not None else _proposal
_proposal = to_tensor(_proposal)
else:
_proposal = None
return _img, _img_meta, _proposalif self.with_mask:
gt_masks = self.mask_transform(ann['masks'], pad_shape,
scale_factor, flip)
ori_shape = (img_info['height'], img_info['width'], 3)
img_meta = dict(
ori_shape=ori_shape,
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
data = dict(
img=DC(to_tensor(img), stack=True),
img_meta=DC(img_meta, cpu_only=True),
gt_bboxes=DC(to_tensor(gt_bboxes)))
if self.with_label:
data['gt_labels'] = DC(to_tensor(gt_labels))
if self.with_crowd:
data['gt_bboxes_ignore'] = DC(to_tensor(gt_bboxes_ignore))
if self.with_mask:
data['gt_masks'] = DC(gt_masks, cpu_only=True)
#--------------------offline ray label generation-----------------------------
self.center_sample = True
self.use_mask_center = True
self.radius = 1.5
self.strides = [8, 16, 32, 64, 128]
self.regress_ranges=((-1, 64), (64, 128), (128, 256), (256, 512),(512, INF))ori_shape = (img_info['height'], img_info['width'], 3)
img_meta = dict(
ori_shape=ori_shape,
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
data = dict(
img=DC(to_tensor(img), stack=True),
img_meta=DC(img_meta, cpu_only=True),
gt_bboxes=DC(to_tensor(gt_bboxes)))
if self.proposals is not None:
data['proposals'] = DC(to_tensor(proposals))
if self.with_label:
data['gt_labels'] = DC(to_tensor(gt_labels))
if self.with_crowd:
data['gt_bboxes_ignore'] = DC(to_tensor(gt_bboxes_ignore))
if self.with_mask:
data['gt_masks'] = DC(gt_masks, cpu_only=True)
return datagt_bboxes_ignore = self.bbox_transform(gt_bboxes_ignore, img_shape,
scale_factor, flip)
if self.with_mask:
gt_masks = self.mask_transform(ann['masks'], pad_shape,
scale_factor, flip)
ori_shape = (img_info['height'], img_info['width'], 3)
img_meta = dict(
ori_shape=ori_shape,
img_shape=img_shape,
pad_shape=pad_shape,
scale_factor=scale_factor,
flip=flip)
data = dict(
img=DC(to_tensor(img), stack=True),
img_meta=DC(img_meta, cpu_only=True),
gt_bboxes=DC(to_tensor(gt_bboxes)))
if self.proposals is not None:
data['proposals'] = DC(to_tensor(proposals))
if self.with_label:
data['gt_labels'] = DC(to_tensor(gt_labels))
if self.with_crowd:
data['gt_bboxes_ignore'] = DC(to_tensor(gt_bboxes_ignore))
if self.with_mask:
data['gt_masks'] = DC(gt_masks, cpu_only=True)
return data
Popular mmdet functions
- mmdet.core.bbox2roi
- mmdet.core.delta2bbox
- mmdet.core.force_fp32
- mmdet.core.multi_apply
- mmdet.core.multiclass_nms
- mmdet.datasets.build_dataloader
- mmdet.datasets.utils.to_tensor
- mmdet.models.build_detector
- mmdet.models.builder
- mmdet.models.builder.build_head
- mmdet.models.builder.build_loss
- mmdet.models.registry.DETECTORS
- mmdet.models.registry.DETECTORS.register_module
- mmdet.models.registry.HEADS
- mmdet.models.registry.HEADS.register_module
- mmdet.models.utils.build_conv_layer
- mmdet.models.utils.build_norm_layer
- mmdet.models.utils.ConvModule
- mmdet.ops.build_conv_layer
- mmdet.utils.build_from_cfg