def evaluate(net, cfg):
dataset = COCODetection(cfg, mode='val')
data_loader = data.DataLoader(dataset,
1,
num_workers=4,
shuffle=False,
pin_memory=True,
collate_fn=val_collate)
ds = len(data_loader)
progress_bar = ProgressBar(40, ds)
timer.reset()
ap_data = {
'box':
[[APDataObject() for _ in cfg.class_names] for _ in iou_thresholds],
'mask':
[[APDataObject() for _ in cfg.class_names] for _ in iou_thresholds]
}
with torch.no_grad():
for i, (img, gt, gt_masks, num_crowd, height,
width) in enumerate(data_loader):
if i == 1:
timer.start()
if cuda:
img, gt, gt_masks = img.cuda(), gt.cuda(), gt_masks.cuda()
with timer.counter('forward'):
net_outs = net(img)
with timer.counter('nms'):
nms_outs = nms(cfg, net_outs)
with timer.counter('after_nms'):
classes_p, confs_p, boxes_p, masks_p = after_nms(
nms_outs, height, width)
if classes_p.size(0) == 0:
continue
with timer.counter('metric'):
classes_p = list(classes_p.cpu().numpy().astype(int))
confs_p = list(confs_p.cpu().numpy().astype(float))
if cfg.coco_api:
boxes_p = boxes_p.cpu().numpy()
masks_p = masks_p.cpu().numpy()
for j in range(masks_p.shape[0]):
if (boxes_p[j, 3] - boxes_p[j, 1]) * (
boxes_p[j, 2] - boxes_p[j, 0]) > 0:
make_json.add_bbox(dataset.ids[i], classes_p[j],
boxes_p[j, :], confs_p[j])
make_json.add_mask(dataset.ids[i], classes_p[j],
masks_p[j, :, :], confs_p[j])
else:
prep_metrics(ap_data, classes_p, confs_p, boxes_p, masks_p,
gt, gt_masks, num_crowd, height, width)
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_me = timer.get_times(
['batch', 'data', 'forward', 'nms', 'after_nms', 'metric'])
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_metric: {t_me:.3f}',
end='')
if cfg.coco_api:
make_json.dump()
print(
f'\nJson files dumped, saved in: \'results/\', start evaluting.'
)
gt_annotations = COCO(cfg.val_ann)
bbox_dets = gt_annotations.loadRes(f'results/bbox_detections.json')
mask_dets = gt_annotations.loadRes(f'results/mask_detections.json')
print('\nEvaluating BBoxes:')
bbox_eval = COCOeval(gt_annotations, bbox_dets, 'bbox')
bbox_eval.evaluate()
bbox_eval.accumulate()
bbox_eval.summarize()
print('\nEvaluating Masks:')
bbox_eval = COCOeval(gt_annotations, mask_dets, 'segm')
bbox_eval.evaluate()
bbox_eval.accumulate()
bbox_eval.summarize()
else:
table, box_row, mask_row = calc_map(ap_data, cfg)
print(table)
return table, box_row, mask_row
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()
if args.resume == 'latest':
weight = glob.glob('weights/latest*')[0]
net.load_weights(weight, cuda)
start_step = int(weight.split('.pth')[0].split('_')[-1])
print(f'\nResume training with \'{weight}\'.\n')
elif args.resume and 'yolact' in args.resume:
net.load_weights(cfg.weight, cuda)
start_step = int(cfg.weight.split('.pth')[0].split('_')[-1])
print(f'\nResume training with \'{args.resume}\'.\n')
else:
net.init_weights(cfg.weight)
print(
f'\nTraining from begining, weights initialized with {cfg.weight}.\n')
start_step = 0
dataset = COCODetection(cfg, mode='train')
train_sampler = None
main_gpu = False
if cuda:
cudnn.benchmark = True
cudnn.fastest = True
main_gpu = dist.get_rank() == 0
num_gpu = dist.get_world_size()
net_with_loss = NetWithLoss(net, criterion)
net = DDP(net_with_loss.cuda(), [args.local_rank],
output_device=args.local_rank,
broadcast_buffers=True)
train_sampler = DistributedSampler(dataset, shuffle=True)
# shuffle must be False if sampler is specified
# Append the device buffer to device bindings.
bindings.append(int(device_mem))
if engine.binding_is_input(binding):
inputs.append(HostDeviceMem(host_mem, device_mem))
else:
outputs.append(HostDeviceMem(host_mem, device_mem))
# ------------------------------------------------------------------------------------------------------------
# Since also the inference procedure are done on GPU, so any other CUDA relevant operation should be excluded,
# e.g. CUDA operation in PyTorch, or some unexpected error may occur.
# ------------------------------------------------------------------------------------------------------------
# detect images
if cfg.image is not None:
dataset = COCODetection(cfg, mode='detect')
# Only num_workers=0 and pin_memory=True or num_workers>0 and pin_memory=False is OK, if use num_workers>0
# and pin_memory=True, encounter error:
# PyCUDA WARNING: a clean-up operation failed (dead context maybe?)
# cuMemFreeHost failed: context is destroyed
data_loader = data.DataLoader(dataset,
1,
num_workers=4,
shuffle=False,
pin_memory=False,
collate_fn=detect_onnx_collate)
ds = len(data_loader)
assert ds > 0, 'No .jpg images found.'
progress_bar = ProgressBar(40, ds)
timer.reset()
for i, COCOID in enumerate(ids_p):
data.append({"id": COCO_CLASSES[COCOID],
"score": str(class_p[i]),
"bbox": box_p[i].tolist()})
json.dump(data, f)
print(f'{f.name} created.')
f.close()
if __name__ == "__main__":
with torch.no_grad():
# detect the image
if cfg.image is not None:
# 待识别图片
dataset = COCODetection(cfg, mode='detect') # Map-Style dataset
data_loader = data.DataLoader(dataset, 1, num_workers=0, shuffle=False,
pin_memory=True, collate_fn=detect_collate)
startTime = time.perf_counter()
# img是被正规化的550 * 550图片，img_origin是从cv2中读取的BGR图片
for i, (img, img_origin, img_name) in enumerate(data_loader):
if cfg.cuda:
img = img.cuda()
img_name = img_name.split('.')[0] # only save the filename
print("the {} image : {}".format(i, img_name))
print("img size:", img.shape)
img_h, img_w = img_origin.shape[0:2]