def __call__(self, results):
if self.file_client is None:
self.file_client = mmcv.FileClient(**self.file_client_args)
if results['img_prefix'] is not None:
filename = osp.join(results['img_prefix'],
results['img_info']['filename'])
else:
filename = results['img_info']['filename']
# img_bytes = self.file_client.get(filename)
# img = mmcv.imfrombytes(img_bytes, flag=self.color_type)
img = mmcv_custom.imread(filename, flag=self.color_type)
if self.to_float32:
img = img.astype(np.float32)
results['filename'] = filename
results['img'] = img
results['img_shape'] = img.shape
results['ori_shape'] = img.shape
num_channels = 1 if len(img.shape) < 3 else img.shape[2]
results['img_norm_cfg'] = dict(mean=np.zeros(num_channels,
dtype=np.float32),
std=np.ones(num_channels,
dtype=np.float32),
to_rgb=False)
return results
def show_result(img,
result,
class_names,
score_thr=0.3,
wait_time=0,
show=True,
out_file=None):
"""Visualize the detection results on the image.
Args:
img (str or np.ndarray): Image filename or loaded image.
result (tuple[list] or list): The detection result, can be either
(bbox, segm) or just bbox.
class_names (list[str] or tuple[str]): A list of class names.
score_thr (float): The threshold to visualize the bboxes and masks.
wait_time (int): Value of waitKey param.
show (bool, optional): Whether to show the image with opencv or not.
out_file (str, optional): If specified, the visualization result will
be written to the out file instead of shown in a window.
Returns:
np.ndarray or None: If neither `show` nor `out_file` is specified, the
visualized image is returned, otherwise None is returned.
"""
assert isinstance(class_names, (tuple, list))
img = mmcv_custom.imread(img)
img = img.copy()
if isinstance(result, tuple):
bbox_result, segm_result = result
else:
bbox_result, segm_result = result, None
bboxes = np.vstack(bbox_result)
# draw segmentation masks
if segm_result is not None:
segms = mmcv.concat_list(segm_result)
inds = np.where(bboxes[:, -1] > score_thr)[0]
for i in inds:
color_mask = np.random.randint(0, 256, (1, 3), dtype=np.uint8)
mask = maskUtils.decode(segms[i]).astype(np.bool)
img[mask] = img[mask] * 0.5 + color_mask * 0.5
# draw bounding boxes
labels = [
np.full(bbox.shape[0], i, dtype=np.int32)
for i, bbox in enumerate(bbox_result)
]
labels = np.concatenate(labels)
mmcv.imshow_det_bboxes(img,
bboxes,
labels,
class_names=class_names,
score_thr=score_thr,
show=show,
wait_time=wait_time,
out_file=out_file)
if not (show or out_file):
return img
def __call__(self, results):
filename = osp.join(results['img_prefix'],
results['img_info']['filename'])
img = mmcv_custom.imread(filename)
if self.to_float32:
img = img.astype(np.float32)
results['filename'] = filename
results['img'] = img
results['img_shape'] = img.shape
results['ori_shape'] = img.shape
return results
def prepare_test_img(self, idx):
"""Prepare an image for testing (multi-scale and flipping)"""
img_info = self.img_infos[idx]
img = mmcv_custom.imread(
osp.join(self.img_prefix, img_info['filename']))
# corruption
if self.corruption is not None:
img = corrupt(img,
severity=self.corruption_severity,
corruption_name=self.corruption)
# load proposals if necessary
if self.proposals is not None:
proposal = self.proposals[idx][:self.num_max_proposals]
if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
raise AssertionError(
'proposals should have shapes (n, 4) or (n, 5), '
'but found {}'.format(proposal.shape))
else:
proposal = None
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 _proposal
_proposal = to_tensor(_proposal)
else:
_proposal = None
return _img, _img_meta, _proposal
imgs = []
img_metas = []
proposals = []
for scale in self.img_scales:
_img, _img_meta, _proposal = prepare_single(
img, scale, False, proposal)
imgs.append(_img)
img_metas.append(DC(_img_meta, cpu_only=True))
proposals.append(_proposal)
if self.flip_ratio > 0:
_img, _img_meta, _proposal = prepare_single(
img, scale, True, proposal)
imgs.append(_img)
img_metas.append(DC(_img_meta, cpu_only=True))
proposals.append(_proposal)
data = dict(img=imgs, img_meta=img_metas)
if self.proposals is not None:
data['proposals'] = proposals
return data
def prepare_train_img(self, idx):
img_info = self.img_infos[idx]
# load image
img = mmcv_custom.imread(
osp.join(self.img_prefix, img_info['filename']))
# corruption
if self.corruption is not None:
img = corrupt(img,
severity=self.corruption_severity,
corruption_name=self.corruption)
# load proposals if necessary
if self.proposals is not None:
proposals = self.proposals[idx][:self.num_max_proposals]
# TODO: Handle empty proposals properly. Currently images with
# no proposals are just ignored, but they can be used for
# training in concept.
if len(proposals) == 0:
return None
if not (proposals.shape[1] == 4 or proposals.shape[1] == 5):
raise AssertionError(
'proposals should have shapes (n, 4) or (n, 5), '
'but found {}'.format(proposals.shape))
if proposals.shape[1] == 5:
scores = proposals[:, 4, None]
proposals = proposals[:, :4]
else:
scores = None
ann = self.get_ann_info(idx)
gt_bboxes = ann['bboxes']
gt_labels = ann['labels']
if self.with_crowd:
gt_bboxes_ignore = ann['bboxes_ignore']
# skip the image if there is no valid gt bbox
if len(gt_bboxes) == 0 and self.skip_img_without_anno:
warnings.warn('Skip the image "%s" that has no valid gt bbox' %
osp.join(self.img_prefix, img_info['filename']))
return None
# extra augmentation
if self.extra_aug is not None:
img, gt_bboxes, gt_labels = self.extra_aug(img, gt_bboxes,
gt_labels)
# apply transforms
flip = True if np.random.rand() < self.flip_ratio else False
# randomly sample a scale
img_scale = random_scale(self.img_scales, self.multiscale_mode)
img, img_shape, pad_shape, scale_factor = self.img_transform(
img, img_scale, flip, keep_ratio=self.resize_keep_ratio)
img = img.copy()
if self.with_seg:
gt_seg = mmcv.imread(osp.join(
self.seg_prefix, img_info['filename'].replace('jpg', 'png')),
flag='unchanged')
gt_seg = self.seg_transform(gt_seg.squeeze(), img_scale, flip)
gt_seg = mmcv.imrescale(gt_seg,
self.seg_scale_factor,
interpolation='nearest')
gt_seg = gt_seg[None, ...]
if self.proposals is not None:
proposals = self.bbox_transform(proposals, img_shape, scale_factor,
flip)
proposals = np.hstack([proposals, scores
]) if scores is not None else proposals
gt_bboxes = self.bbox_transform(gt_bboxes, img_shape, scale_factor,
flip)
if self.with_crowd:
gt_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)
if self.with_seg:
data['gt_semantic_seg'] = DC(to_tensor(gt_seg), stack=True)
return data
def _load_semantic_seg(self, results):
results['gt_semantic_seg'] = mmcv_custom.imread(
osp.join(results['seg_prefix'], results['ann_info']['seg_map']),
flag='unchanged').squeeze()
return results
def prepare_test_img(self, idx):
"""Prepare an image for testing (multi-scale and flipping)"""
img_info = self.img_infos[idx]
img = mmcv_custom.imread(
osp.join(self.img_prefix, img_info['filename']))
if self.proposals is not None:
proposal = self.proposals[idx][:self.num_max_proposals]
if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
raise AssertionError(
'proposals should have shapes (n, 4) or (n, 5), '
'but found {}'.format(proposal.shape))
else:
proposal = None
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(
id=img_info['id'],
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, _proposal
imgs = []
img_metas = []
proposals = []
for scale in self.img_scales:
_img, _img_meta, _proposal = prepare_single(
img, scale, False, proposal)
imgs.append(_img)
img_metas.append(DC(_img_meta, cpu_only=True))
proposals.append(_proposal)
if self.flip_ratio > 0:
_img, _img_meta, _proposal = prepare_single(
img, scale, True, proposal)
imgs.append(_img)
img_metas.append(DC(_img_meta, cpu_only=True))
proposals.append(_proposal)
data = dict(img=imgs, img_meta=img_metas)
if self.proposals is not None:
data['proposals'] = proposals
if self.with_label:
ann = self.get_ann_info(idx)
gt_bboxes = ann['bboxes']
gt_bboxes = self.bbox_transform(gt_bboxes,
img_metas[0].data['img_shape'],
img_metas[0].data['scale_factor'],
False)
data['gt_bboxes'] = DC(to_tensor(gt_bboxes))
if self.with_hardmask:
data['hardmask'] = dict()
_stage = [3, 4, 6, 3]
for idx_stage, item in enumerate(_stage):
for idx_block in range(item):
key = 'Res{}_Block{}'.format(idx_stage + 1, idx_block + 1)
_mask_c1 = mmcv_custom.imread(
osp.join(self.hardmask_prefix, '{}_{}_c1.png'.format(img_info['id'], key)), 'grayscale'
)
_mask_c1 = to_tensor(_mask_c1).\
unsqueeze(0).\
unsqueeze(0).\
float() / 255.
data['hardmask'][key + '_c1'] = DC(_mask_c1)
_mask_c23 = mmcv_custom.imread(
osp.join(self.hardmask_prefix, '{}_{}_c23.png'.format(img_info['id'], key)), 'grayscale'
)
_mask_c23 = to_tensor(_mask_c23). \
unsqueeze(0). \
unsqueeze(0). \
float() / 255.
data['hardmask'][key + '_c23'] = DC(_mask_c23)
return data
def prepare_train_img(self, idx):
img_info = self.img_infos[idx]
# load image
img = mmcv_custom.imread(
osp.join(self.img_prefix, img_info['filename']))
# load proposals if necessary
if self.proposals is not None:
proposals = self.proposals[idx][:self.num_max_proposals]
# TODO: Handle empty proposals properly. Currently images with
# no proposals are just ignored, but they can be used for
# training in concept.
if len(proposals) == 0:
return None
if not (proposals.shape[1] == 4 or proposals.shape[1] == 5):
raise AssertionError(
'proposals should have shapes (n, 4) or (n, 5), '
'but found {}'.format(proposals.shape))
if proposals.shape[1] == 5:
scores = proposals[:, 4, None]
proposals = proposals[:, :4]
else:
scores = None
ann = self.get_ann_info(idx)
gt_bboxes = ann['bboxes']
gt_labels = ann['labels']
if self.with_crowd:
gt_bboxes_ignore = ann['bboxes_ignore']
# skip the image if there is no valid gt bbox
if len(gt_bboxes) == 0:
return None
# extra augmentation
if self.extra_aug is not None:
img, gt_bboxes, gt_labels = self.extra_aug(img, gt_bboxes,
gt_labels)
# apply transforms
flip = True if np.random.rand() < self.flip_ratio else False
# randomly sample a scale
img_scale = random_scale(self.img_scales, self.multiscale_mode)
img, img_shape, pad_shape, scale_factor = self.img_transform(
img, img_scale, flip, keep_ratio=self.resize_keep_ratio)
img = img.copy()
if self.with_seg:
gt_seg = mmcv.imread(
osp.join(self.seg_prefix,
img_info['file_name'].replace('jpg', 'png')),
flag='unchanged')
gt_seg = self.seg_transform(gt_seg.squeeze(), img_scale, flip)
gt_seg = mmcv.imrescale(
gt_seg, self.seg_scale_factor, interpolation='nearest')
gt_seg = gt_seg[None, ...]
if self.proposals is not None:
proposals = self.bbox_transform(proposals, img_shape, scale_factor,
flip)
proposals = np.hstack([proposals, scores
]) if scores is not None else proposals
gt_bboxes = self.bbox_transform(gt_bboxes, img_shape, scale_factor,
flip)
if self.with_crowd:
gt_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)
# <Update 2019.9.21> Add Id to Img-Meta.
img_meta = dict(
id=img_info['id'],
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)
if self.with_seg:
data['gt_semantic_seg'] = DC(to_tensor(gt_seg), stack=True)
if self.with_hardmask:
data['hardmask'] = dict()
_stage = [3, 4, 6, 3]
for idx_stage, item in enumerate(_stage):
for idx_block in range(item):
key = 'Res{}_Block{}'.format(idx_stage + 1, idx_block + 1)
_mask_c1 = mmcv_custom.imread(
osp.join(self.hardmask_prefix, '{}_{}_c1.png'.format(img_info['id'], key)), 'grayscale'
)
_mask_c1 = to_tensor(_mask_c1).\
unsqueeze(0).\
unsqueeze(0).\
float() / 255.
data['hardmask'][key + '_c1'] = DC(_mask_c1)
_mask_c23 = mmcv_custom.imread(
osp.join(self.hardmask_prefix, '{}_{}_c23.png'.format(img_info['id'], key)), 'grayscale'
)
_mask_c23 = to_tensor(_mask_c23). \
unsqueeze(0). \
unsqueeze(0). \
float() / 255.
data['hardmask'][key + '_c23'] = DC(_mask_c23)
return data