map_location=lambda storage, loc: storage)
net_utils.load_ckpt(maskRCNN, checkpoint['model'])
maskRCNN.eval()
maskRCNN = mynn.DataParallel(maskRCNN,
cpu_keywords=['im_info', 'roidb'],
minibatch=True,
device_ids=[0])
# load image
img_path = "/home/work/liupeng11/code/Detectron.pytorch/demo/sample_images/img1.jpg"
im = cv2.imread(img_path)
# detect bouding boxes and segments
from core.test import im_detect_bbox, im_detect_mask, box_results_with_nms_and_limit, segm_results
scores, boxes, im_scale, blob_conv = im_detect_bbox(maskRCNN, im,
cfg.TEST.SCALE,
cfg.TEST.MAX_SIZE, None)
scores, boxes, cls_boxes = box_results_with_nms_and_limit(scores, boxes)
masks = im_detect_mask(maskRCNN, im_scale, boxes, blob_conv)
cls_segms = segm_results(cls_boxes, masks, boxes, im.shape[0], im.shape[1])
cls_keyps = None
# save detected image
name = 'test'
output_dir = '/home/work/liupeng11/code/Detectron.pytorch/tmp'
vis_utils.vis_one_image(
im[:, :, ::-1], # BGR -> RGB for visualization
name,
output_dir,
cls_boxes,
cls_segms,
with open(osp.join(args.output_dir, 'config_args.json'), 'w') as fp:
json.dump(vars(args), fp, indent=4, sort_keys=True)
# -----------------------------------------------------------------------------------
# Detect faces on CS6 frames
# -----------------------------------------------------------------------------------
start = time.time()
for i, im_name in enumerate(image_subset):
print('%d/%d: %s' % (i, len(image_subset), im_name))
im = cv2.imread(osp.join(args.data_dir, im_name))
assert im.size != 0
# Detect faces and regress bounding-boxes
scores, boxes, im_scale, blob_conv = im_detect_bbox(
net, im, cfg.TEST.SCALE, cfg.TEST.MAX_SIZE)
# Format the detection output
cls_ind = 1
cls_boxes = boxes[:, 4 * cls_ind:4 * (cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack(
(cls_boxes, cls_scores[:, np.newaxis])).astype(np.float32)
keep = box_utils.nms(dets, NMS_THRESH)
dets = dets[keep, :]
keep = np.where(dets[:, 4] > CONF_THRESH)
dets = dets[keep]
# (x, y, w, h)
dets[:, 2] = dets[:, 2] - dets[:, 0] + 1
dets[:, 3] = dets[:, 3] - dets[:, 1] + 1
print('Num. detections: %d' % dets.shape[0])