def _add_gt_image_summary(self):
# use a customized visualization function to visualize the boxes
self._add_gt_image()
image = draw_bounding_boxes(\
self._gt_image, self._image_gt_summaries['gt_boxes'], self._image_gt_summaries['im_info'])
return tb.summary.image('GROUND_TRUTH', torch.from_numpy(image[0].astype('float32')/ 255.0).permute(2,0,1))
def demo(sess, net, image_name):
# Load the demo image
im_path = os.path.join(cfg.DATA_DIR, 'horus-test', 'images')
im_file = os.path.join(im_path, image_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(sess, net, im)
timer.toc()
print('Detection took {:.3f}s for {:d} object proposals'.format(
timer.total_time, boxes.shape[0]))
# Visualize detections for each class
CONF_THRESH = 0.6
for cls_ind, cls in enumerate(cfg.CLASSES[1:]):
cls_ind += 1 # because we skipped background
inds = np.where(scores[:, cls_ind] >= CONF_THRESH)[0]
cls_boxes = boxes[inds, 4 * cls_ind:4 * (cls_ind + 1)]
cls_scores = scores[inds, cls_ind]
dets = np.hstack(
(cls_boxes, cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, cfg.TEST.NMS)
dets = dets[keep, :]
print(dets)
# vis_detections(im, cls, dets, thresh=CONF_THRESH)
# inds = np.where(dets[:, -1] >= CONF_THRESH)[0]
if len(dets) != 0:
im = draw_bounding_boxes(im, dets, cls_ind, cls)
cv2.imwrite(cfg.DATA_DIR + '/output/output_' + image_name, im)
def _add_gt_image_summary(self):
# use a customized visualization function to visualize the boxes
self._add_gt_image()
image = draw_bounding_boxes(\
self._gt_image, self._image_gt_summaries['gt_boxes'], self._image_gt_summaries['im_info'])
return tb.summary.image('GROUND_TRUTH', image[0].astype('float32').swapaxes(1,0).swapaxes(2,0)/255.0)
def _add_gt_image_summary(self):
# use a customized visualization function to visualize the boxes
self._add_gt_image()
image = draw_bounding_boxes(\
self._gt_image, self._image_gt_summaries['gt_boxes'], self._image_gt_summaries['im_info'])
return tb.summary.image('GROUND_TRUTH', image[0].astype('float32')/255.0)
def _add_gt_image_summary(self):
# use a customized visualization function to visualize the boxes
self._add_gt_image()
image = draw_bounding_boxes(\
self._gt_image, np.zeros((0,5)), self._image_gt_summaries['im_info']) #no bounding_box ground_truth
return tb.summary.image('GROUND_TRUTH',
image[0].astype('float32') / 255.0)
imdb.set_proposal_method('gt')
print('Set proposal method: {:s}'.format("gt"))
# roidb = get_training_roidb(imdb)
import roi_data_layer.roidb as rdl_roidb
print('Preparing training data...')
rdl_roidb.prepare_roidb(imdb)
print('done')
from utils.visualization import draw_bounding_boxes
roidb = imdb.roidb
print("sds")
import cv2
for im_info in roidb:
new_img = draw_bounding_boxes()
cv2.imwrite("data/table/" ,new_img )
"""
[{'boxes': array([[1079, 442, 1497, 517],
[1101, 476, 1499, 549],
[1171, 532, 1497, 642]], dtype=uint16),
'gt_classes': array([1, 1, 1], dtype=int32),
'gt_overlaps': <3x2 sparse matrix of type '<class 'numpy.float32'>'
with 3 stored elements in Compressed Sparse Row format>,
'flipped': False,
'seg_areas': array([31844., 29526., 36297.], dtype=float32),
'image': '/1.jpg',
'width': 1463, 'height': 1198,
'max_classes': array([1, 1, 1]),
'max_overlaps': array([1., 1., 1.], dtype=float32)}]
"""
