name = cfg.video.split('/')[-1]
video_writer = cv2.VideoWriter(f'results/videos/{name}', cv2.VideoWriter_fourcc(*"mp4v"), target_fps,
(frame_width, frame_height))
progress_bar = ProgressBar(40, num_frames)
timer.reset()
t_fps = 0
for i in range(num_frames):
if i == 1:
timer.start()
frame_origin = vid.read()[1]
img_h, img_w = frame_origin.shape[0:2]
frame_trans = val_aug(frame_origin, cfg.img_size)[None, :]
with timer.counter('forward'):
class_p, box_p, coef_p, proto_p, anchors = sess.run(None, {input_name: frame_trans})
with timer.counter('nms'):
ids_p, class_p, box_p, coef_p, proto_p = nms_numpy(class_p, box_p, coef_p, proto_p, anchors, cfg)
with timer.counter('after_nms'):
ids_p, class_p, boxes_p, masks_p = after_nms_numpy(ids_p, class_p, box_p, coef_p,
proto_p, img_h, img_w, cfg)
with timer.counter('save_img'):
frame_numpy = draw_img(ids_p, class_p, boxes_p, masks_p, frame_origin, cfg, fps=t_fps)
if cfg.real_time:
def main():
parser = argparse.ArgumentParser(description='YOLACT Detection.')
parser.add_argument('--weight', default='weights/best_30.5_res101_coco_392000.pth', type=str)
parser.add_argument('--image', default=None, type=str, help='The folder of images for detecting.')
parser.add_argument('--video', default=None, type=str, help='The path of the video to evaluate.')
parser.add_argument('--img_size', type=int, default=544, help='The image size for validation.')
parser.add_argument('--traditional_nms', default=False, action='store_true', help='Whether to use traditional nms.')
parser.add_argument('--hide_mask', default=False, action='store_true', help='Hide masks in results.')
parser.add_argument('--hide_bbox', default=False, action='store_true', help='Hide boxes in results.')
parser.add_argument('--hide_score', default=False, action='store_true', help='Hide scores in results.')
parser.add_argument('--cutout', default=False, action='store_true', help='Cut out each object and save.')
parser.add_argument('--save_lincomb', default=False, action='store_true', help='Show the generating process of masks.')
parser.add_argument('--no_crop', default=False, action='store_true',
help='Do not crop the output masks with the predicted bounding box.')
parser.add_argument('--real_time', default=False, action='store_true', help='Show the detection results real-timely.')
parser.add_argument('--visual_thre', default=0.3, type=float,
help='Detections with a score under this threshold will be removed.')
args = parser.parse_args()
prefix = re.findall(r'best_\d+\.\d+_', args.weight)[0]
suffix = re.findall(r'_\d+\.pth', args.weight)[0]
args.cfg = args.weight.split(prefix)[-1].split(suffix)[0]
cfg = get_config(args, mode='detect')
net = Yolact(cfg)
net.load_weights(cfg.weight, cfg.cuda)
net.eval()
if cfg.cuda:
cudnn.benchmark = True
cudnn.fastest = True
net = net.cuda()
# detect images
if cfg.image is not None:
dataset = COCODetection(cfg, mode='detect')
data_loader = data.DataLoader(dataset, 1, num_workers=2, shuffle=False, pin_memory=True, collate_fn=detect_collate)
ds = len(data_loader)
assert ds > 0, 'No .jpg images found.'
progress_bar = ProgressBar(40, ds)
timer.reset()
for i, (img, img_origin, img_name) in enumerate(data_loader):
if i == 1:
timer.start()
if cfg.cuda:
img = img.cuda()
img_h, img_w = img_origin.shape[0:2]
with torch.no_grad(), timer.counter('forward'):
class_p, box_p, coef_p, proto_p = net(img)
with timer.counter('nms'):
ids_p, class_p, box_p, coef_p, proto_p = nms(class_p, box_p, coef_p, proto_p, net.anchors, cfg)
with timer.counter('after_nms'):
ids_p, class_p, boxes_p, masks_p = after_nms(ids_p, class_p, box_p, coef_p, proto_p,
img_h, img_w, cfg, img_name=img_name)
with timer.counter('save_img'):
img_numpy = draw_img(ids_p, class_p, boxes_p, masks_p, img_origin, cfg, img_name=img_name)
cv2.imwrite(f'results/images/{img_name}', img_numpy)
aa = time.perf_counter()
if i > 0:
batch_time = aa - temp
timer.add_batch_time(batch_time)
temp = aa
if i > 0:
t_t, t_d, t_f, t_nms, t_an, t_si = timer.get_times(['batch', 'data', 'forward',
'nms', 'after_nms', 'save_img'])
fps, t_fps = 1 / (t_d + t_f + t_nms + t_an), 1 / t_t
bar_str = progress_bar.get_bar(i + 1)
print(f'\rTesting: {bar_str} {i + 1}/{ds}, fps: {fps:.2f} | total fps: {t_fps:.2f} | '
f't_t: {t_t:.3f} | t_d: {t_d:.3f} | t_f: {t_f:.3f} | t_nms: {t_nms:.3f} | '
f't_after_nms: {t_an:.3f} | t_save_img: {t_si:.3f}', end='')
print('\nFinished, saved in: results/images.')
# detect videos
elif cfg.video is not None:
vid = cv2.VideoCapture(cfg.video)
target_fps = round(vid.get(cv2.CAP_PROP_FPS))
frame_width = round(vid.get(cv2.CAP_PROP_FRAME_WIDTH))
frame_height = round(vid.get(cv2.CAP_PROP_FRAME_HEIGHT))
num_frames = round(vid.get(cv2.CAP_PROP_FRAME_COUNT))
name = cfg.video.split('/')[-1]
video_writer = cv2.VideoWriter(f'results/videos/{name}', cv2.VideoWriter_fourcc(*"mp4v"), target_fps,
(frame_width, frame_height))
progress_bar = ProgressBar(40, num_frames)
timer.reset()
t_fps = 0
for i in range(num_frames):
if i == 1:
timer.start()
frame_origin = vid.read()[1]
img_h, img_w = frame_origin.shape[0:2]
frame_trans = val_aug(frame_origin, cfg.img_size)
frame_tensor = torch.tensor(frame_trans).float()
if cfg.cuda:
frame_tensor = frame_tensor.cuda()
with torch.no_grad(), timer.counter('forward'):
class_p, box_p, coef_p, proto_p = net(frame_tensor.unsqueeze(0))
with timer.counter('nms'):
ids_p, class_p, box_p, coef_p, proto_p = nms(class_p, box_p, coef_p, proto_p, net.anchors, cfg)
with timer.counter('after_nms'):
ids_p, class_p, boxes_p, masks_p = after_nms(ids_p, class_p, box_p, coef_p, proto_p, img_h, img_w, cfg)
with timer.counter('save_img'):
frame_numpy = draw_img(ids_p, class_p, boxes_p, masks_p, frame_origin, cfg, fps=t_fps)
if cfg.real_time:
cv2.imshow('Detection', frame_numpy)
cv2.waitKey(1)
else:
video_writer.write(frame_numpy)
aa = time.perf_counter()
if i > 0:
batch_time = aa - temp
timer.add_batch_time(batch_time)
temp = aa
if i > 0:
t_t, t_d, t_f, t_nms, t_an, t_si = timer.get_times(['batch', 'data', 'forward',
'nms', 'after_nms', 'save_img'])
fps, t_fps = 1 / (t_d + t_f + t_nms + t_an), 1 / t_t
bar_str = progress_bar.get_bar(i + 1)
print(f'\rDetecting: {bar_str} {i + 1}/{num_frames}, fps: {fps:.2f} | total fps: {t_fps:.2f} | '
f't_t: {t_t:.3f} | t_d: {t_d:.3f} | t_f: {t_f:.3f} | t_nms: {t_nms:.3f} | '
f't_after_nms: {t_an:.3f} | t_save_img: {t_si:.3f}', end='')
if not cfg.real_time:
print(f'\n\nFinished, saved in: results/videos/{name}')
vid.release()
video_writer.release()
def __getitem__(self, index):
if self.mode == 'detect':
img_name = self.image_path[index]
img_origin = cv2.imread(img_name)
img_normed = val_aug(img_origin, self.cfg.img_size)
return img_normed, img_origin, img_name.split(osp.sep)[-1]
else:
img_id = self.ids[index]
ann_ids = self.coco.getAnnIds(imgIds=img_id)
# 'target' includes {'segmentation', 'area', iscrowd', 'image_id', 'bbox', 'category_id'}
target = self.coco.loadAnns(ann_ids)
target = [aa for aa in target if not aa['iscrowd']]
file_name = self.coco.loadImgs(img_id)[0]['file_name']
img_path = osp.join(self.image_path, file_name)
assert osp.exists(
img_path), f'Image path does not exist: {img_path}'
img = cv2.imread(img_path)
height, width, _ = img.shape
assert len(target) > 0, 'No annotation in this image!'
box_list, mask_list, label_list = [], [], []
for aa in target:
bbox = aa['bbox']
# When training, some boxes are wrong, ignore them.
if self.mode == 'train':
if bbox[0] < 0 or bbox[1] < 0 or bbox[2] < 4 or bbox[3] < 4:
continue
x1y1x2y2_box = np.array(
[bbox[0], bbox[1], bbox[0] + bbox[2], bbox[1] + bbox[3]])
category = self.continuous_id[aa['category_id']] - 1
box_list.append(x1y1x2y2_box)
mask_list.append(self.coco.annToMask(aa))
label_list.append(category)
if len(box_list) > 0:
boxes = np.array(box_list)
masks = np.stack(mask_list, axis=0)
labels = np.array(label_list)
assert masks.shape == (boxes.shape[0], height,
width), 'Unmatched annotations.'
if self.mode == 'train':
img, masks, boxes, labels = train_aug(
img, masks, boxes, labels, self.cfg.img_size)
if img is None:
return None, None, None
else:
boxes = np.hstack((boxes, np.expand_dims(labels,
axis=1)))
return img, boxes, masks
elif self.mode == 'val':
img = val_aug(img, self.cfg.img_size)
boxes = boxes / np.array([width, height, width, height
]) # to 0~1 scale
boxes = np.hstack((boxes, np.expand_dims(labels, axis=1)))
return img, boxes, masks, height, width
else:
if self.mode == 'val':
raise RuntimeError('Error, no valid object in this image.')
else:
print(
f'No valid object in image: {img_id}. Use a repeated image in this batch.'
)
return None, None, None
name = cfg.video.split('/')[-1]
video_writer = cv2.VideoWriter(f'results/videos/{name}',
cv2.VideoWriter_fourcc(*"mp4v"),
target_fps, (frame_width, frame_height))
progress_bar = ProgressBar(40, num_frames)
timer.reset()
t_fps = 0
for i in range(num_frames):
if i == 1:
timer.start()
frame_origin = vid.read()[1]
img_h, img_w = frame_origin.shape[0:2]
frame_trans = val_aug(frame_origin, cfg)
frame_tensor = torch.tensor(frame_trans).float()
if cfg.cuda:
frame_tensor = frame_tensor.cuda()
with timer.counter('forward'):
net_outs = net(frame_tensor.unsqueeze(0))
with timer.counter('nms'):
nms_outs = nms(cfg, net_outs)
with timer.counter('after_nms'):
results = after_nms(nms_outs, img_h, img_w, cfg)
with timer.counter('save_img'):