def main():
args = parse_args()
cfg = retrieve_data_cfg(args.config, args.skip_type, args.cfg_options)
dataset = build_dataset(cfg.data.train)
progress_bar = mmcv.ProgressBar(len(dataset))
for item in dataset:
filename = os.path.join(args.output_dir,
Path(item['filename']).name
) if args.output_dir is not None else None
gt_masks = item.get('gt_masks', None)
if gt_masks is not None:
gt_masks = mask2ndarray(gt_masks)
imshow_det_bboxes(item['img'],
item['gt_bboxes'],
item['gt_labels'],
gt_masks,
class_names=dataset.CLASSES,
show=not args.not_show,
wait_time=args.show_interval,
out_file=filename,
bbox_color=(255, 102, 61),
text_color=(255, 102, 61))
progress_bar.update()
def __call__(self, results):
img = results['img']
orig_type = img.dtype
anns = self._load_anns(results)
if np.random.choice([0, 1], p=[1 - self.aug_ratio, self.aug_ratio]):
try:
import instaboost.InstaBoost as instaboost
except ImportError:
raise ImportError('Please run "pip install instaboostfast" '
'to install instaboostfast first.')
print(anns)
print(img.shape)
anns, img = instaboost.get_new_data(anns,
img.astype(np.uint8),
self.cfg,
background=None)
results = self._parse_anns(results, anns, img.astype(orig_type))
## 可视化确认结果无误
filename = results['img_info']['file_name']
import cv2
from mmdet.core.visualization import imshow_det_bboxes
img_out = results['img'].copy()
imshow_det_bboxes(
img_out,
results['gt_bboxes'],
results['gt_labels'],
class_names=underwater_classes(),
show=False,
out_file='/home/featurize/work/underwater-object-detection/boost/'
+ filename)
return results
def main():
args = parse_args()
cfg = retrieve_data_cfg(args.config, args.skip_type, args.cfg_options)
if 'gt_semantic_seg' in cfg.train_pipeline[-1]['keys']:
cfg.data.train.pipeline = [
p for p in cfg.data.train.pipeline if p['type'] != 'SegRescale'
]
dataset = build_dataset(cfg.data.train)
progress_bar = mmcv.ProgressBar(len(dataset))
for item in dataset:
filename = os.path.join(args.output_dir,
Path(item['filename']).name
) if args.output_dir is not None else None
gt_bboxes = item['gt_bboxes']
gt_labels = item['gt_labels']
gt_masks = item.get('gt_masks', None)
if gt_masks is not None:
gt_masks = mask2ndarray(gt_masks)
gt_seg = item.get('gt_semantic_seg', None)
if gt_seg is not None:
pad_value = 255 # the padding value of gt_seg
sem_labels = np.unique(gt_seg)
all_labels = np.concatenate((gt_labels, sem_labels), axis=0)
all_labels, counts = np.unique(all_labels, return_counts=True)
stuff_labels = all_labels[np.logical_and(counts < 2,
all_labels != pad_value)]
stuff_masks = gt_seg[None] == stuff_labels[:, None, None]
gt_labels = np.concatenate((gt_labels, stuff_labels), axis=0)
gt_masks = np.concatenate((gt_masks, stuff_masks.astype(np.uint8)),
axis=0)
# If you need to show the bounding boxes,
# please comment the following line
gt_bboxes = None
imshow_det_bboxes(item['img'],
gt_bboxes,
gt_labels,
gt_masks,
class_names=dataset.CLASSES,
show=not args.not_show,
wait_time=args.show_interval,
out_file=filename,
bbox_color=dataset.PALETTE,
text_color=(200, 200, 200),
mask_color=dataset.PALETTE)
progress_bar.update()
def test_imshow_det_bboxes():
tmp_filename = osp.join(tempfile.gettempdir(), 'det_bboxes_image',
'image.jpg')
image = np.ones((10, 10, 3), np.uint8)
bbox = np.array([[2, 1, 3, 3], [3, 4, 6, 6]])
label = np.array([0, 1])
out_image = vis.imshow_det_bboxes(image,
bbox,
label,
out_file=tmp_filename,
show=False)
assert osp.isfile(tmp_filename)
assert image.shape == out_image.shape
assert not np.allclose(image, out_image)
os.remove(tmp_filename)
# test grayscale images
image = np.ones((10, 10), np.uint8)
bbox = np.array([[2, 1, 3, 3], [3, 4, 6, 6]])
label = np.array([0, 1])
out_image = vis.imshow_det_bboxes(image,
bbox,
label,
out_file=tmp_filename,
show=False)
assert osp.isfile(tmp_filename)
assert image.shape == out_image.shape[:2]
os.remove(tmp_filename)
# test shaped (0,)
image = np.ones((10, 10, 3), np.uint8)
bbox = np.ones((0, 4))
label = np.ones((0, ))
vis.imshow_det_bboxes(image,
bbox,
label,
out_file=tmp_filename,
show=False)
assert osp.isfile(tmp_filename)
os.remove(tmp_filename)
# test mask
image = np.ones((10, 10, 3), np.uint8)
bbox = np.array([[2, 1, 3, 3], [3, 4, 6, 6]])
label = np.array([0, 1])
segms = np.random.random((2, 10, 10)) > 0.5
segms = np.array(segms, np.int32)
vis.imshow_det_bboxes(image,
bbox,
label,
segms,
out_file=tmp_filename,
show=False)
assert osp.isfile(tmp_filename)
os.remove(tmp_filename)
# test tensor mask type error
with pytest.raises(AttributeError):
segms = torch.tensor(segms)
vis.imshow_det_bboxes(image, bbox, label, segms, show=False)
def show_result(self,
img,
result,
score_thr=0.3,
bbox_color=(72, 101, 241),
text_color=(72, 101, 241),
mask_color=None,
thickness=2,
font_size=13,
win_name='',
show=False,
wait_time=0,
out_file=None):
"""Draw `result` over `img`.
Args:
img (str or Tensor): The image to be displayed.
result (Tensor or tuple): The results to draw over `img`
bbox_result or (bbox_result, segm_result).
score_thr (float, optional): Minimum score of bboxes to be shown.
Default: 0.3.
bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
The tuple of color should be in BGR order. Default: 'green'
text_color (str or tuple(int) or :obj:`Color`):Color of texts.
The tuple of color should be in BGR order. Default: 'green'
mask_color (None or str or tuple(int) or :obj:`Color`):
Color of masks. The tuple of color should be in BGR order.
Default: None
thickness (int): Thickness of lines. Default: 2
font_size (int): Font size of texts. Default: 13
win_name (str): The window name. Default: ''
wait_time (float): Value of waitKey param.
Default: 0.
show (bool): Whether to show the image.
Default: False.
out_file (str or None): The filename to write the image.
Default: None.
Returns:
img (Tensor): Only if not `show` or `out_file`
"""
img = mmcv.imread(img)
img = img.copy()
if isinstance(result, tuple):
bbox_result, segm_result = result
if isinstance(segm_result, tuple):
segm_result = segm_result[0] # ms rcnn
else:
bbox_result, segm_result = result, None
bboxes = np.vstack(bbox_result)
labels = [
np.full(bbox.shape[0], i, dtype=np.int32)
for i, bbox in enumerate(bbox_result)
]
labels = np.concatenate(labels)
# draw segmentation masks
segms = None
if segm_result is not None and len(labels) > 0: # non empty
segms = mmcv.concat_list(segm_result)
if isinstance(segms[0], torch.Tensor):
segms = torch.stack(segms, dim=0).detach().cpu().numpy()
else:
segms = np.stack(segms, axis=0)
# if out_file specified, do not show image in window
if out_file is not None:
show = False
# draw bounding boxes
img = imshow_det_bboxes(
img,
bboxes,
labels,
segms,
class_names=self.CLASSES,
score_thr=score_thr,
bbox_color=bbox_color,
text_color=text_color,
mask_color=mask_color,
thickness=thickness,
font_size=font_size,
win_name=win_name,
show=show,
wait_time=wait_time,
out_file=out_file)
if not (show or out_file):
return img
def show_result(self,
img,
result,
score_thr=0.3,
bbox_color=(72, 101, 241),
text_color=(72, 101, 241),
mask_color=None,
thickness=2,
font_size=13,
win_name='',
show=False,
wait_time=0,
out_file=None):
"""Draw `result` over `img`.
Args:
img (str or Tensor): The image to be displayed.
result (dict): The results.
score_thr (float, optional): Minimum score of bboxes to be shown.
Default: 0.3.
bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
The tuple of color should be in BGR order. Default: 'green'.
text_color (str or tuple(int) or :obj:`Color`):Color of texts.
The tuple of color should be in BGR order. Default: 'green'.
mask_color (None or str or tuple(int) or :obj:`Color`):
Color of masks. The tuple of color should be in BGR order.
Default: None.
thickness (int): Thickness of lines. Default: 2.
font_size (int): Font size of texts. Default: 13.
win_name (str): The window name. Default: ''.
wait_time (float): Value of waitKey param.
Default: 0.
show (bool): Whether to show the image.
Default: False.
out_file (str or None): The filename to write the image.
Default: None.
Returns:
img (Tensor): Only if not `show` or `out_file`.
"""
img = mmcv.imread(img)
img = img.copy()
pan_results = result['pan_results']
# keep objects ahead
ids = np.unique(pan_results)[::-1]
legal_indices = ids != self.num_classes # for VOID label
ids = ids[legal_indices]
labels = np.array([id % INSTANCE_OFFSET for id in ids], dtype=np.int64)
segms = (pan_results[None] == ids[:, None, None])
# if out_file specified, do not show image in window
if out_file is not None:
show = False
# draw bounding boxes
img = imshow_det_bboxes(
img,
segms=segms,
labels=labels,
class_names=self.CLASSES,
bbox_color=bbox_color,
text_color=text_color,
mask_color=mask_color,
thickness=thickness,
font_size=font_size,
win_name=win_name,
show=show,
wait_time=wait_time,
out_file=out_file)
if not (show or out_file):
return img
def infer_fn(model, img, kwargs=None):
result = inference_detector(model, img)
img = mmcv.imread(img)
img = img.copy()
if isinstance(result, tuple):
bbox_result, segm_result = result
if isinstance(segm_result, tuple):
segm_result = segm_result[0] # ms rcnn
else:
bbox_result, segm_result = result, None
bboxes = np.vstack(bbox_result)
labels = [
np.full(bbox.shape[0], i, dtype=np.int32)
for i, bbox in enumerate(bbox_result)
]
labels = np.concatenate(labels)
# get person index
person_idx = 0
if isinstance(model.CLASSES, tuple):
person_idx = model.CLASSES.index('person')
# draw segmentation masks
segms = None
if segm_result is not None and len(labels) > 0: # non empty
segms = mmcv.concat_list(segm_result)
if isinstance(segms[0], torch.Tensor):
segms = torch.stack(segms, dim=0).detach().cpu().numpy()
else:
segms = np.stack(segms, axis=0)
# filter out results by threshold
scores = bboxes[:, -1]
inds = scores > score_thr
bboxes_ = bboxes[inds, :]
labels_ = labels[inds]
segms_ = None
if segms is not None:
segms_ = segms[inds, ...]
else:
return None, None
# aggregate person indices
seg_map = segms_[labels_ == person_idx] * 1
if seg_map.size == 0: # no segmap is generated
return None, None
seg_map = np.max(seg_map, axis=0)
seg_map = np.clip(seg_map * 1, 0, 1)
seg_map = seg_map.astype(np.uint8)
# draw bounding boxes
img = imshow_det_bboxes(img,
bboxes,
labels,
segms,
class_names=model.CLASSES,
score_thr=score_thr,
bbox_color=(72, 101, 241),
text_color=(72, 101, 241),
mask_color=None,
thickness=2,
font_size=13,
win_name='',
show=False,
wait_time=0,
out_file=None)
return seg_map, img
