def demo():
model = build_model()
if os.path.isdir(data_f):
all_imgs = glob.glob(os.path.join(data_f, '*.jpg'))
for img in all_imgs:
print('~~~~~ predict on img: {}'.format(img))
im = cv2.imread(img)
ori_im = im.copy()
height, width, _ = im.shape
transform = ValTransform(rgb_means=(
0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
im_input, _ = transform(im, None, target_size)
im_input = im_input.to(device).unsqueeze(0)
with torch.no_grad():
out = model(im_input)
outputs = postprocess(out, num_classes, 0.01, 0.65)
outputs = outputs[0].cpu().data
bboxes = outputs[:, 0:4]
bboxes[:, 0::2] *= width / target_size[0]
bboxes[:, 1::2] *= height / target_size[1]
cls = outputs[:, 6]
scores = outputs[:, 4] * outputs[:, 5]
if isinstance(bboxes, torch.Tensor):
bboxes = bboxes.cpu().numpy()
res = visualize_det_cv2_part(
im, scores, cls, bboxes, coco_label_map_list[1:], 0.1)
cv2.imshow('rr', res)
cv2.waitKey(0)
if len(sys.argv) > 1:
data_f = sys.argv[1]
else:
data_f = './images'
if os.path.isdir(data_f):
img_files = glob.glob(os.path.join(data_f, '*.jpg'))
for img_f in img_files:
ori_img = cv2.imread(img_f)
b = predictor(ori_img)['instances']
boxes = b.pred_boxes.tensor.cpu().numpy()
scores = b.scores.cpu().numpy()
classes = b.pred_classes.cpu().numpy()
print('b.pred_boxes: {}'.format(boxes))
print('b.scores: {}'.format(scores))
print('b.pred_classes: {}'.format(classes))
visualize_det_cv2_part(ori_img, scores, classes, boxes, class_names=coco_label_map_list, thresh=0.16,
is_show=True)
exit(0)
else:
ori_img = cv2.imread(data_f)
b = predictor(ori_img)['instances']
boxes = b.pred_boxes.tensor.cpu().numpy()
scores = b.scores.cpu().numpy()
classes = b.pred_classes.cpu().numpy()
print('b.pred_boxes: {}'.format(boxes))
print('b.scores: {}'.format(scores))
print('b.pred_classes: {}'.format(classes))
visualize_det_cv2_part(ori_img, scores, classes, boxes, class_names=coco_label_map_list, thresh=0.16,
is_show=True)
data_f = sys.argv[1]
else:
data_f = './images'
if os.path.isdir(data_f):
img_files = glob.glob(os.path.join(data_f, '*.jpg'))
for img_f in img_files:
ori_img = cv2.imread(img_f)
b = predictor(ori_img)['instances']
boxes = b.pred_boxes.tensor.cpu().numpy()
scores = b.scores.cpu().numpy()
classes = b.pred_classes.cpu().numpy()
visualize_det_cv2_part(ori_img,
scores,
classes,
boxes,
class_names=categories,
thresh=0.16,
force_color=force_color,
line_thickness=1,
is_show=True,
wait_t=100)
else:
ori_img = cv2.imread(data_f)
b = predictor(ori_img)['instances']
boxes = b.pred_boxes.tensor.cpu().numpy()
scores = b.scores.cpu().numpy()
classes = b.pred_classes.cpu().numpy()
visualize_det_cv2_part(ori_img,
scores,
classes,
boxes,
class_names=categories,
