def test():
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
# load net
cfg = config.WF_config
input_size = cfg['min_dim']
# dataset
if args.dataset == 'widerface':
testset = WIDERFaceDetection(args.dataset_root, image_sets='val')
else:
print('Only support Wider-Face dataset !!')
exit(0)
# build model
if args.version == 'TinyYOLAF':
from models.TinyYOLAF import TinyYOLAF
anchor_size = tools.get_total_anchor_size(name=args.dataset, version=args.version)
net = TinyYOLAF(device, input_size=input_size, trainable=False, anchor_size=anchor_size)
print('Let us test TinyYOLAF......')
elif args.version == 'CenterYOLAF':
from models.CenterYOLAF import CenterYOLAF
net = CenterYOLAF(device, input_size=input_size, trainable=False)
print('Let us test CenterYOLAF......')
else:
print('Unknown version !!!')
exit()
net.load_state_dict(torch.load(args.trained_model, map_location=device))
net.eval()
print('Finished loading model!')
net = net.to(device)
# 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.vis_thresh)
def train():
args = parse_args()
path_to_save = os.path.join(args.save_folder, args.version)
os.makedirs(path_to_save, exist_ok=True)
hr = False
if args.high_resolution:
print('use hi-res backbone')
hr = True
cfg = WF_config
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
# use multi-scale trick
input_size = cfg['min_dim']
dataset = WIDERFaceDetection(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 == 'TinyYOLAF':
from models.TinyYOLAF import TinyYOLAF
anchor_size = tools.get_total_anchor_size(name=args.dataset,
version=args.version)
net = TinyYOLAF(device,
input_size=input_size,
trainable=True,
anchor_size=anchor_size,
hr=hr)
print('Let us train TinyYOLAF......')
elif args.version == 'CenterYOLAF':
from models.CenterYOLAF import CenterYOLAF
net = CenterYOLAF(device, input_size=input_size, trainable=True, hr=hr)
print('Let us train CenterYOLAF......')
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/widerface/', args.version, c_time)
os.makedirs(log_path, exist_ok=True)
writer = SummaryWriter(log_path)
print(
"----------------------------------------Face 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('Training on:', dataset.name)
print('The dataset size:', len(dataset))
print('Initial learning rate: ', args.lr)
print("----------------------------------------------------------")
epoch_size = len(dataset) // args.batch_size
max_epoch = cfg['max_epoch']
step_index = 0
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)
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
if args.version == 'TinyYOLAF':
targets = tools.multi_gt_creator_ab(input_size,
net.stride,
label_lists=targets,
name=args.dataset,
version=args.version)
elif args.version == 'CenterYOLAF':
targets = tools.gt_creator(input_size,
net.stride,
targets,
name=args.dataset)
# vis heatmap
# vis_heatmap(targets)
# to device
images = images.to(device)
targets = torch.tensor(targets).float().to(device)
# forward and loss
conf_loss, txtytwth_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('object loss', conf_loss.item(),
iter_i + epoch * epoch_size)
writer.add_scalar('local loss', txtytwth_loss.item(),
iter_i + epoch * epoch_size)
t1 = time.time()
print(
'[Epoch %d/%d][Iter %d/%d][lr %.6f]'
'[Loss: obj %.2f || bbox %.2f || total %.2f || size %d || time: %.2f]'
% (epoch + 1, max_epoch, iter_i, epoch_size, tmp_lr,
conf_loss.item(), txtytwth_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'))
def run():
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
# load net
cfg = config.WF_config
input_size = cfg['min_dim']
# build model
if args.version == 'TinyYOLAF':
from models.TinyYOLAF import TinyYOLAF
anchor_size = tools.get_total_anchor_size(name=args.setup,
version=args.version)
net = TinyYOLAF(device,
input_size=input_size,
trainable=False,
anchor_size=anchor_size)
print('Let us test TinyYOLAF......')
elif args.version == 'CenterYOLAF':
from models.CenterYOLAF import CenterYOLAF
net = CenterYOLAF(device,
input_size=input_size,
trainable=False,
conf_thresh=0.3,
topk=200)
print('Let us test CenterYOLAF......')
else:
print('Unknown version !!!')
exit()
net.load_state_dict(torch.load(args.trained_model, map_location=device))
net.eval()
print('Finished loading model!')
net = net.to(device)
# 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)),
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)),
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)),
mode=args.mode,
path_to_vid=args.path_to_vid,
path_to_save=args.path_to_saveVid,
setup=args.setup)
if __name__ == '__main__':
global hr, cfg
hr = False
device = get_device(args.gpu_ind)
if args.high_resolution == 1:
hr = True
cfg = coco_ab
if args.version == 'yolo_v2':
from models.yolo_v2 import myYOLOv2
total_anchor_size = tools.get_total_anchor_size(name='COCO')
yolo_net = myYOLOv2(device,
input_size=cfg['min_dim'],
num_classes=args.num_classes,
trainable=True,
anchor_size=total_anchor_size,
hr=hr)
print('Let us train yolo-v2 on the MSCOCO dataset ......')
elif args.version == 'yolo_v3':
from models.yolo_v3 import myYOLOv3
total_anchor_size = tools.get_total_anchor_size(multi_scale=True,
name='COCO')
yolo_net = myYOLOv3(device,
input_size=cfg['min_dim'],
def train():
args = parse_args()
path_to_save = os.path.join(args.save_folder, args.version)
os.makedirs(path_to_save, exist_ok=True)
hr = False
if args.high_resolution:
print('use hi-res backbone')
hr = True
cfg = voc_ab
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
# use multi-scale trick
if args.multi_scale:
print('use multi-scale trick.')
input_size = [608, 608]
dataset = VOCDetection(root=args.dataset_root, transform=SSDAugmentation([608, 608], mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)))
else:
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 == 'yolo_v2':
from models.yolo_v2 import myYOLOv2
total_anchor_size = tools.get_total_anchor_size()
yolo_net = myYOLOv2(device, input_size=input_size, num_classes=args.num_classes, trainable=True, anchor_size=total_anchor_size, hr=hr)
print('Let us train yolo-v2 on the VOC0712 dataset ......')
elif args.version == 'yolo_v3':
from models.yolo_v3 import myYOLOv3
total_anchor_size = tools.get_total_anchor_size(multi_level=True, version='yolo_v3')
yolo_net = myYOLOv3(device, input_size=input_size, num_classes=args.num_classes, trainable=True, anchor_size=total_anchor_size, hr=hr)
print('Let us train yolo-v3 on the VOC0712 dataset ......')
elif args.version == 'slim_yolo_v2':
from models.slim_yolo_v2 import SlimYOLOv2
total_anchor_size = tools.get_total_anchor_size()
yolo_net = SlimYOLOv2(device, input_size=input_size, num_classes=args.num_classes, trainable=True, anchor_size=total_anchor_size, hr=hr)
print('Let us train slim-yolo-v2 on the VOC0712 dataset ......')
elif args.version == 'tiny_yolo_v3':
from models.tiny_yolo_v3 import YOLOv3tiny
total_anchor_size = tools.get_total_anchor_size(multi_level=True, version='tiny_yolo_v3')
yolo_net = YOLOv3tiny(device, input_size=input_size, num_classes=args.num_classes, trainable=True, anchor_size=total_anchor_size, hr=hr)
print('Let us train tiny-yolo-v3 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 ')
yolo_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 = yolo_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]
# make train label
if args.version == 'yolo_v2' or args.version == 'slim_yolo_v2':
targets = tools.gt_creator(input_size, yolo_net.stride, targets, version=args.version)
elif args.version == 'yolo_v3' or args.version == 'tiny_yolo_v3':
targets = tools.multi_gt_creator(input_size, yolo_net.stride, targets, version=args.version)
# to device
images = images.to(device)
targets = torch.tensor(targets).float().to(device)
# forward and loss
conf_loss, cls_loss, txtytwth_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('object loss', conf_loss.item(), iter_i + epoch * epoch_size)
writer.add_scalar('class loss', cls_loss.item(), iter_i + epoch * epoch_size)
writer.add_scalar('local loss', txtytwth_loss.item(), iter_i + epoch * epoch_size)
t1 = time.time()
print('[Epoch %d/%d][Iter %d/%d][lr %.6f]'
'[Loss: obj %.2f || cls %.2f || bbox %.2f || total %.2f || size %d || time: %.2f]'
% (epoch+1, max_epoch, iter_i, epoch_size, tmp_lr,
conf_loss.item(), cls_loss.item(), txtytwth_loss.item(), total_loss.item(), input_size[0], t1-t0),
flush=True)
t0 = time.time()
# multi-scale trick
if iter_i % 10 == 0 and iter_i > 0 and args.multi_scale:
size = random.randint(10, 19) * 32
input_size = [size, size]
model.set_grid(input_size)
# change input dim
# But this operation will report bugs when we use more workers in data loader, so I have to use 0 workers.
# I don't know how to make it suit more workers, and I'm trying to solve this question.
data_loader.dataset.reset_transform(SSDAugmentation(input_size, mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)))
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')
)
if __name__ == '__main__':
global hr, cfg
hr = False
device = get_device(args.gpu_ind)
if args.high_resolution == 1:
hr = True
cfg = voc_ab
if args.version == 'yolo_v2':
from models.yolo_v2 import myYOLOv2
total_anchor_size = tools.get_total_anchor_size()
yolo_net = myYOLOv2(device,
input_size=cfg['min_dim'],
num_classes=args.num_classes,
trainable=True,
anchor_size=total_anchor_size,
hr=hr)
print('Let us train yolo-v2 on the VOC0712 dataset ......')
elif args.version == 'yolo_v3':
from models.yolo_v3 import myYOLOv3
total_anchor_size = tools.get_total_anchor_size(multi_scale=True)
yolo_net = myYOLOv3(device,
input_size=cfg['min_dim'],
if __name__ == "__main__":
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
cfg = config.WF_config
input_size = cfg['min_dim']
transform = BaseTransform(input_size)
# load net
if args.version == 'TinyYOLAF':
from models.TinyYOLAF import TinyYOLAF
anchor_size = tools.get_total_anchor_size(name='widerface',
version=args.version)
net = TinyYOLAF(device,
input_size=input_size,
trainable=False,
anchor_size=anchor_size)
print('Let us eval TinyYOLAF......')
elif args.version == 'CenterYOLAF':
from models.CenterYOLAF import CenterYOLAF
net = CenterYOLAF(device,
input_size=input_size,
trainable=False,
conf_thresh=0.01,
topk=1000)
def train():
args = parse_args()
data_dir = args.dataset_root
path_to_save = os.path.join(args.save_folder, args.version)
os.makedirs(path_to_save, exist_ok=True)
hr = False
if args.high_resolution:
print('use hi-res backbone')
hr = True
cfg = coco_ab
if args.cuda:
print('use cuda')
cudnn.benchmark = True
device = torch.device("cuda")
else:
device = torch.device("cpu")
if args.multi_scale:
print('Let us use the multi-scale trick.')
input_size = [608, 608]
dataset = COCODataset(data_dir=data_dir,
img_size=608,
transform=SSDAugmentation([608, 608],
mean=(0.406, 0.456,
0.485),
std=(0.225, 0.224,
0.229)),
debug=args.debug)
else:
input_size = cfg['min_dim']
dataset = COCODataset(data_dir=data_dir,
img_size=cfg['min_dim'][0],
transform=SSDAugmentation(cfg['min_dim'],
mean=(0.406, 0.456,
0.485),
std=(0.225, 0.224,
0.229)),
debug=args.debug)
# build model
if args.version == 'yolo_v2':
from models.yolo_v2 import myYOLOv2
total_anchor_size = tools.get_total_anchor_size(name='COCO')
yolo_net = myYOLOv2(device,
input_size=input_size,
num_classes=args.num_classes,
trainable=True,
anchor_size=total_anchor_size,
hr=hr)
print('Let us train yolo-v2 on the COCO dataset ......')
elif args.version == 'yolo_v3':
from models.yolo_v3 import myYOLOv3
total_anchor_size = tools.get_total_anchor_size(multi_level=True,
name='COCO')
yolo_net = myYOLOv3(device,
input_size=input_size,
num_classes=args.num_classes,
trainable=True,
anchor_size=total_anchor_size,
hr=hr)
print('Let us train yolo-v3 on the COCO dataset ......')
elif args.version == 'tiny_yolo_v2':
from models.tiny_yolo_v2 import YOLOv2tiny
total_anchor_size = tools.get_total_anchor_size(name='COCO')
yolo_net = YOLOv2tiny(device,
input_size=input_size,
num_classes=args.num_classes,
trainable=True,
anchor_size=total_anchor_size,
hr=hr)
print('Let us train tiny-yolo-v2 on the COCO dataset ......')
elif args.version == 'tiny_yolo_v3':
from models.tiny_yolo_v3 import YOLOv3tiny
total_anchor_size = tools.get_total_anchor_size(multi_level=True,
name='COCO')
yolo_net = YOLOv3tiny(device,
input_size=input_size,
num_classes=args.num_classes,
trainable=True,
anchor_size=total_anchor_size,
hr=hr)
print('Let us train tiny-yolo-v3 on the COCO dataset ......')
else:
print('Unknown version !!!')
exit()
print("Setting Arguments.. : ", args)
print("----------------------------------------------------------")
print('Loading the MSCOCO dataset...')
print('Training model on:', dataset.name)
print('The dataset size:', len(dataset))
print("----------------------------------------------------------")
# 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/coco/', args.version, c_time)
os.makedirs(log_path, exist_ok=True)
writer = SummaryWriter(log_path)
print('Let us train yolo-v2 on the MSCOCO dataset ......')
model = yolo_net
model.to(device).train()
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=args.batch_size,
shuffle=True,
collate_fn=detection_collate,
num_workers=args.num_workers)
evaluator = COCOAPIEvaluator(data_dir=data_dir,
img_size=cfg['min_dim'],
device=device,
transform=BaseTransform(cfg['min_dim'],
mean=(0.406, 0.456,
0.485),
std=(0.225, 0.224,
0.229)))
# optimizer setup
base_lr = args.lr
tmp_lr = base_lr
optimizer = optim.SGD(model.parameters(),
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
max_epoch = cfg['max_epoch']
epoch_size = len(dataset) // args.batch_size
# start training loop
t0 = time.time()
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)
# COCO evaluation
if (epoch + 1) % args.eval_epoch == 0:
model.trainable = False
model.set_grid(cfg['min_dim'])
# evaluate
ap50_95, ap50 = evaluator.evaluate(model)
print('ap50 : ', ap50)
print('ap50_95 : ', ap50_95)
# convert to training mode.
model.trainable = True
model.set_grid(input_size)
model.train()
if args.tfboard:
writer.add_scalar('val/COCOAP50', ap50, epoch + 1)
writer.add_scalar('val/COCOAP50_95', ap50_95, epoch + 1)
for iter_i, (images, targets) in enumerate(dataloader):
# 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]
if args.version == 'yolo_v2' or args.version == 'tiny_yolo_v2':
targets = tools.gt_creator(input_size,
yolo_net.stride,
targets,
name='COCO')
elif args.version == 'yolo_v3' or args.version == 'tiny_yolo_v3':
targets = tools.multi_gt_creator(input_size,
yolo_net.stride,
targets,
name='COCO')
# to device
images = images.to(device)
targets = torch.tensor(targets).float().to(device)
# forward and loss
conf_loss, cls_loss, txtytwth_loss, total_loss = model(
images, target=targets)
# backprop
total_loss.backward()
optimizer.step()
optimizer.zero_grad()
if args.tfboard:
# viz loss
writer.add_scalar('object loss', conf_loss.item(),
iter_i + epoch * epoch_size)
writer.add_scalar('class loss', cls_loss.item(),
iter_i + epoch * epoch_size)
writer.add_scalar('local loss', txtytwth_loss.item(),
iter_i + epoch * epoch_size)
if iter_i % 10 == 0:
t1 = time.time()
print(
'[Epoch %d/%d][Iter %d/%d][lr %.6f]'
'[Loss: obj %.2f || cls %.2f || bbox %.2f || total %.2f || size %d || time: %.2f]'
% (epoch + 1, max_epoch, iter_i, epoch_size, tmp_lr,
conf_loss.item(), cls_loss.item(), txtytwth_loss.item(),
total_loss.item(), input_size[0], t1 - t0),
flush=True)
t0 = time.time()
# multi-scale trick
if iter_i % 10 == 0 and iter_i > 0 and args.multi_scale:
# ms_ind = random.sample(ms_inds, 1)[0]
# input_size = cfg['multi_scale'][int(ms_ind)]
size = random.randint(10, 19) * 32
input_size = [size, size]
model.set_grid(input_size)
# change input dim
# But this operation will report bugs when we use more workers in data loader, so I have to use 0 workers.
# I don't know how to make it suit more workers, and I'm trying to solve this question.
dataloader.dataset.reset_transform(
SSDAugmentation(input_size,
mean=(0.406, 0.456, 0.485),
std=(0.225, 0.224, 0.229)))
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'))
from models.yolo_v1 import myYOLOv1
cfg = voc_af
yolo_net = myYOLOv1(device,
input_size=cfg['min_dim'],
num_classes=args.num_classes,
trainable=True,
hr=hr,
backbone=args.backbone)
print('Let us train yolo-v1 on the VOC0712 dataset ......')
elif args.version == 'yolo_anchor':
from models.yolo_anchor import myYOLOv1
cfg = voc_ab
use_anchor = True
total_anchor_size = tools.get_total_anchor_size(
cfg['min_dim'], cfg['stride'])
yolo_net = myYOLOv1(device,
input_size=cfg['min_dim'],
num_classes=args.num_classes,
trainable=True,
anchor_size=total_anchor_size,
hr=hr,
backbone=args.backbone)
print('Let us train yolo-anchor on the VOC0712 dataset ......')
elif args.version == 'yolo_v1_ms':
from models.yolo_v1_ms import myYOLOv1
cfg = voc_af
yolo_net = myYOLOv1(device,
