def run():
args = parse_args()
# use cuda
if args.cuda:
device = torch.device("cuda")
else:
device = torch.device("cpu")
input_size = [args.input_size, args.input_size]
# load net
if args.version == 'centernet':
from models.centernet import CenterNet
net = CenterNet(device,
input_size=input_size,
num_classes=80,
conf_thresh=args.conf_thresh,
nms_thresh=args.nms_thresh,
use_nms=args.use_nms)
net.load_state_dict(torch.load(args.trained_model, map_location='cuda'))
net.to(device).eval()
print('Finished loading model!')
# run
if args.mode == 'camera':
detect(net, device, BaseTransform(net.input_size),
thresh=args.visual_threshold, mode=args.mode)
elif args.mode == 'image':
detect(net, device, BaseTransform(net.input_size),
thresh=args.visual_threshold, mode=args.mode, path_to_img=args.path_to_img)
elif args.mode == 'video':
detect(net, device, BaseTransform(net.input_size),
thresh=args.visual_threshold, mode=args.mode, path_to_vid=args.path_to_vid, path_to_save=args.path_to_saveVid)
def test():
# get device
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
# load net
num_classes = len(VOC_CLASSES)
testset = VOCDetection(args.voc_root, [('2007', 'test')], None,
VOCAnnotationTransform())
cfg = config.voc_cfg
if args.version == 'centernet':
from models.centernet import CenterNet
net = CenterNet(device,
input_size=cfg['min_dim'],
num_classes=num_classes)
net.load_state_dict(torch.load(args.trained_model, map_location=device))
net.to(device).eval()
print('Finished loading model!')
# evaluation
test_net(net,
device,
testset,
BaseTransform(net.input_size,
mean=(0.406, 0.456, 0.485),
std=(0.225, 0.224, 0.229)),
thresh=args.visual_threshold)
def run():
args = parse_args()
if args.cuda:
device = torch.device("cuda")
else:
device = torch.device("cpu")
if args.setup == 'VOC':
print('use VOC style')
cfg = config.voc_cfg
num_classes = 20
elif args.setup == 'COCO':
print('use COCO style')
cfg = config.coco_cfg
num_classes = 80
else:
print('Only support VOC and COCO !!!')
exit(0)
if args.version == 'centernet':
from models.centernet import CenterNet
net = CenterNet(device, input_size=cfg['min_dim'], num_classes=num_classes, use_nms=True)
net.load_state_dict(torch.load(args.trained_model, map_location=device))
net.to(device).eval()
print('Finished loading model!')
# run
if args.mode == 'camera':
detect(net, device, BaseTransform(net.input_size, mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)),
thresh=args.vis_thresh, mode=args.mode, setup=args.setup)
elif args.mode == 'image':
detect(net, device, BaseTransform(net.input_size, mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)),
thresh=args.vis_thresh, mode=args.mode, path_to_img=args.path_to_img, setup=args.setup)
elif args.mode == 'video':
detect(net, device, BaseTransform(net.input_size, mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)),
thresh=args.vis_thresh, mode=args.mode, path_to_vid=args.path_to_vid, path_to_save=args.path_to_saveVid, setup=args.setup)
def test():
# get device
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
# load net
num_classes = 80
if args.dataset == 'COCO':
cfg = config.coco_cfg
testset = COCODataset(
data_dir=args.dataset_root,
json_file='instances_val2017.json',
name='val2017',
img_size=cfg['min_dim'][0],
debug=args.debug)
elif args.dataset == 'VOC':
cfg = config.voc_cfg
testset = VOCDetection(VOC_ROOT, [('2007', 'test')], None, VOCAnnotationTransform())
if args.version == 'centernet':
from models.centernet import CenterNet
net = CenterNet(device, input_size=cfg['min_dim'], num_classes=num_classes)
net.load_state_dict(torch.load(args.trained_model, map_location='cuda'))
net.to(device).eval()
print('Finished loading model!')
# evaluation
test_net(net, device, testset,
BaseTransform(net.input_size, mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)),
thresh=args.visual_threshold)
device = torch.device("cuda")
else:
device = torch.device("cpu")
# input size
input_size = [args.input_size, args.input_size]
# load net
if args.version == 'centernet':
from models.centernet import CenterNet
net = CenterNet(device,
input_size=input_size,
num_classes=num_classes,
backbone=args.backbone,
use_nms=args.use_nms)
# load net
net.load_state_dict(torch.load(args.trained_model, map_location='cuda'))
net.eval()
print('Finished loading model!')
net = net.to(device)
# evaluation
with torch.no_grad():
if args.dataset == 'voc':
voc_test(net, device, input_size)
elif args.dataset == 'coco-val':
coco_test(net, device, input_size, test=False)
elif args.dataset == 'coco-test':
coco_test(net, device, input_size, test=True)
name='val2017',
img_size=input_size[0])
class_colors = [(np.random.randint(255), np.random.randint(255),
np.random.randint(255)) for _ in range(num_classes)]
# load net
if args.version == 'centernet':
from models.centernet import CenterNet
net = CenterNet(device,
input_size=input_size,
num_classes=num_classes,
conf_thresh=args.conf_thresh,
nms_thresh=args.nms_thresh,
use_nms=args.use_nms)
net.load_state_dict(torch.load(args.trained_model, map_location=device))
net.to(device).eval()
print('Finished loading model!')
# evaluation
test(net=net,
device=device,
testset=dataset,
transform=BaseTransform(input_size),
thresh=args.visual_threshold,
class_colors=class_colors,
class_names=class_names,
class_indexs=class_indexs,
dataset=args.dataset)
def train():
args = parse_args()
path_to_save = os.path.join(args.save_folder, args.version)
os.makedirs(path_to_save, exist_ok=True)
cfg = voc_cfg
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
input_size = cfg['min_dim']
dataset = VOCDetection(root=args.dataset_root,
transform=SSDAugmentation(cfg['min_dim'],
mean=(0.406, 0.456,
0.485),
std=(0.225, 0.224,
0.229)))
# build model
if args.version == 'centernet':
from models.centernet import CenterNet
net = CenterNet(device,
input_size=input_size,
num_classes=args.num_classes,
trainable=True)
print('Let us train centernet on the VOC0712 dataset ......')
else:
print('Unknown version !!!')
exit()
# finetune the model trained on COCO
if args.resume is not None:
print('finetune COCO trained ')
net.load_state_dict(torch.load(args.resume, map_location=device),
strict=False)
# use tfboard
if args.tfboard:
print('use tensorboard')
from torch.utils.tensorboard import SummaryWriter
c_time = time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
log_path = os.path.join('log/voc/', args.version, c_time)
os.makedirs(log_path, exist_ok=True)
writer = SummaryWriter(log_path)
print(
"----------------------------------------Object Detection--------------------------------------------"
)
model = net
model.to(device)
base_lr = args.lr
tmp_lr = base_lr
optimizer = optim.SGD(model.parameters(),
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
# loss counters
print("----------------------------------------------------------")
print("Let's train OD network !")
print('Training on:', dataset.name)
print('The dataset size:', len(dataset))
print("----------------------------------------------------------")
epoch_size = len(dataset) // args.batch_size
max_epoch = cfg['max_epoch']
data_loader = data.DataLoader(dataset,
args.batch_size,
num_workers=args.num_workers,
shuffle=True,
collate_fn=detection_collate,
pin_memory=True)
# create batch iterator
t0 = time.time()
# start training
for epoch in range(max_epoch):
# use cos lr
if args.cos and epoch > 20 and epoch <= max_epoch - 20:
# use cos lr
tmp_lr = 0.00001 + 0.5 * (base_lr - 0.00001) * (
1 + math.cos(math.pi * (epoch - 20) * 1. / (max_epoch - 20)))
set_lr(optimizer, tmp_lr)
elif args.cos and epoch > max_epoch - 20:
tmp_lr = 0.00001
set_lr(optimizer, tmp_lr)
# use step lr
else:
if epoch in cfg['lr_epoch']:
tmp_lr = tmp_lr * 0.1
set_lr(optimizer, tmp_lr)
for iter_i, (images, targets) in enumerate(data_loader):
# WarmUp strategy for learning rate
if not args.no_warm_up:
if epoch < args.wp_epoch:
tmp_lr = base_lr * pow((iter_i + epoch * epoch_size) * 1. /
(args.wp_epoch * epoch_size), 4)
# tmp_lr = 1e-6 + (base_lr-1e-6) * (iter_i+epoch*epoch_size) / (epoch_size * (args.wp_epoch))
set_lr(optimizer, tmp_lr)
elif epoch == args.wp_epoch and iter_i == 0:
tmp_lr = base_lr
set_lr(optimizer, tmp_lr)
targets = [label.tolist() for label in targets]
# vis_data(images, targets, input_size)
# make train label
targets = tools.gt_creator(input_size, net.stride,
args.num_classes, targets)
# vis_heatmap(targets)
# to device
images = images.to(device)
targets = torch.tensor(targets).float().to(device)
# forward and loss
cls_loss, txty_loss, twth_loss, total_loss = model(images,
target=targets)
# backprop and update
total_loss.backward()
optimizer.step()
optimizer.zero_grad()
if iter_i % 10 == 0:
if args.tfboard:
# viz loss
writer.add_scalar('class loss', cls_loss.item(),
iter_i + epoch * epoch_size)
writer.add_scalar('txty loss', txty_loss.item(),
iter_i + epoch * epoch_size)
writer.add_scalar('twth loss', twth_loss.item(),
iter_i + epoch * epoch_size)
writer.add_scalar('total loss', total_loss.item(),
iter_i + epoch * epoch_size)
t1 = time.time()
print(
'[Epoch %d/%d][Iter %d/%d][lr %.6f]'
'[Loss: cls %.2f || txty %.2f || twth %.2f ||total %.2f || size %d || time: %.2f]'
% (epoch + 1, max_epoch, iter_i, epoch_size, tmp_lr,
cls_loss.item(), txty_loss.item(), twth_loss.item(),
total_loss.item(), input_size, t1 - t0),
flush=True)
t0 = time.time()
if (epoch + 1) % 10 == 0:
print('Saving state, epoch:', epoch + 1)
torch.save(
model.state_dict(),
os.path.join(path_to_save,
args.version + '_' + repr(epoch + 1) + '.pth'))