'loss_rpn_box': loss_rpn_box,
'loss_rcnn_cls': loss_rcnn_cls,
'loss_rcnn_box': loss_rcnn_box
}
for tag, value in info.items():
logger.scalar_summary(tag, value, step)
loss_temp = 0
start = time.time()
if args.mGPUs:
save_name = os.path.join(output_dir, 'faster_rcnn_{}_{}_{}.pth'.format(args.session, epoch, step))
save_checkpoint({
'session': args.session,
'epoch': epoch + 1,
'model': model.module.state_dict(),
'optimizer': optimizer.state_dict(),
'pooling_mode': cfg.POOLING_MODE,
'class_agnostic': args.class_agnostic,
}, save_name)
else:
save_name = os.path.join(output_dir, 'faster_rcnn_{}_{}_{}.pth'.format(args.session, epoch, step))
save_checkpoint({
'session': args.session,
'epoch': epoch + 1,
'model': model.state_dict(),
'optimizer': optimizer.state_dict(),
'pooling_mode': cfg.POOLING_MODE,
'class_agnostic': args.class_agnostic,
}, save_name)
print('save model: {}'.format(save_name))
def exp_htcn_mixed(cfg_file, output_dir, dataset_source, dataset_target, val_datasets,
device, net, optimizer, num_workers,
lr, batch_size, start_epoch, max_epochs, lr_decay_gamma, lr_decay_step,
resume, load_name,
eta, gamma, ef, class_agnostic, lc, gc, LA_ATT, MID_ATT,
debug, _run):
args = Args(dataset=dataset_source, dataset_t=dataset_target, imdb_name_target=[], cfg_file=cfg_file, net=net)
args = set_dataset_args(args)
args_val = Args(dataset=dataset_source, dataset_t=val_datasets, imdb_name_target=[], cfg_file=cfg_file, net=net)
args_val = set_dataset_args(args_val, test=True)
logger = LoggerForSacred(None, ex, True)
if cfg_file is not None:
cfg_from_file(cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
np.random.seed(cfg.RNG_SEED)
cfg.TRAIN.USE_FLIPPED = True
cfg.USE_GPU_NMS = True if device == 'cuda' else False
device = torch.device(device)
output_dir = output_dir + "_{}".format(_run._id)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
dataloader_s, dataloader_t, imdb = init_dataloaders_1s_mixed_mt(args, batch_size, num_workers)
val_dataloader_ts, val_imdb_ts = init_val_dataloaders_mt(args_val, 1, num_workers)
session = 1
fasterRCNN, lr, optimizer, session, start_epoch, _ = init_htcn_model_optimizer(lr, LA_ATT, MID_ATT, class_agnostic, device, gc,
imdb, lc, load_name, net, optimizer, resume,
session, start_epoch)
if torch.cuda.device_count() > 1:
fasterRCNN = nn.DataParallel(fasterRCNN)
iters_per_epoch = int(10000 / batch_size)
if ef:
FL = EFocalLoss(class_num=2, gamma=gamma)
else:
FL = FocalLoss(class_num=2, gamma=gamma)
total_step = 0
for epoch in range(start_epoch, max_epochs + 1):
# setting to train mode
fasterRCNN.train()
if epoch - 1 in lr_decay_step:
adjust_learning_rate(optimizer, lr_decay_gamma)
lr *= lr_decay_gamma
total_step = frcnn_utils.train_htcn_one_epoch(args, FL, total_step, dataloader_s, dataloader_t, iters_per_epoch, fasterRCNN, optimizer, device, eta, logger)
save_name = os.path.join(output_dir,
'target_{}_eta_{}_local_{}_global_{}_gamma_{}_session_{}_epoch_{}_total_step_{}.pth'.format(
args.dataset_t, args.eta,
lc, gc, gamma,
session, epoch,
total_step))
save_checkpoint({
'session': session,
'epoch': epoch + 1,
'model': fasterRCNN.module.state_dict() if torch.cuda.device_count() > 1 else fasterRCNN.state_dict(),
'optimizer': optimizer.state_dict(),
'pooling_mode': cfg.POOLING_MODE,
'class_agnostic': class_agnostic,
}, save_name)
return 0
logger.add_scalars("logs_s_{}/losses".format(args.session),
info,
(epoch - 1) * iters_per_epoch + step)
loss_temp = 0
start = time.time()
save_name = os.path.join(
output_dir,
'faster_rcnn_{}_{}_{}.pth'.format(args.session, epoch, step))
save_checkpoint(
{
'session':
args.session,
'epoch':
epoch + 1,
'model':
fasterRCNN.module.state_dict()
if args.mGPUs else fasterRCNN.state_dict(),
'optimizer':
optimizer.state_dict(),
'pooling_mode':
cfg.POOLING_MODE,
'class_agnostic':
args.class_agnostic,
}, save_name)
print('save model: {}'.format(save_name))
if args.use_tfboard:
logger.close()
def training_fusion():
# initilize the tensor holder here.
im_data1 = torch.FloatTensor(1)
im_data2 = torch.FloatTensor(1)
im_info = torch.FloatTensor(1)
num_boxes = torch.LongTensor(1)
gt_boxes = torch.FloatTensor(1)
# ship to cuda
if args.cuda:
im_data1 = im_data1.cuda()
im_data2 = im_data2.cuda()
im_info = im_info.cuda()
num_boxes = num_boxes.cuda()
gt_boxes = gt_boxes.cuda()
# make variable
im_data1 = Variable(im_data1)
im_data2 = Variable(im_data2)
im_info = Variable(im_info)
num_boxes = Variable(num_boxes)
gt_boxes = Variable(gt_boxes)
if args.cuda:
cfg.CUDA = True
# initilize the network here.
if args.net == 'vgg16f':
fasterRCNN = vgg16f(imdb.classes,
pretrained=True,
class_agnostic=args.class_agnostic,
fusion_mode=args.fusion_mode)
elif args.net == 'vgg16c':
fasterRCNN = vgg16c(imdb.classes,
pretrained=True,
class_agnostic=args.class_agnostic)
elif args.net == 'res101':
fasterRCNN = resnet(imdb.classes,
101,
pretrained=True,
class_agnostic=args.class_agnostic)
elif args.net == 'res50':
fasterRCNN = resnet(imdb.classes,
50,
pretrained=True,
class_agnostic=args.class_agnostic)
elif args.net == 'res152':
fasterRCNN = resnet(imdb.classes,
152,
pretrained=True,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
fasterRCNN.create_architecture()
lr = cfg.TRAIN.LEARNING_RATE
lr = args.lr
# tr_momentum = cfg.TRAIN.MOMENTUM
# tr_momentum = args.momentum
params = []
for key, value in dict(fasterRCNN.named_parameters()).items():
if value.requires_grad:
if 'bias' in key:
params += [{'params': [value], 'lr': lr * (cfg.TRAIN.DOUBLE_BIAS + 1), \
'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
else:
params += [{
'params': [value],
'lr': lr,
'weight_decay': cfg.TRAIN.WEIGHT_DECAY
}]
if args.cuda:
fasterRCNN.cuda()
if args.optimizer == "adam":
lr = lr * 0.1
optimizer = torch.optim.Adam(params)
elif args.optimizer == "sgd":
optimizer = torch.optim.SGD(params, momentum=cfg.TRAIN.MOMENTUM)
if args.resume:
load_name = os.path.join(
output_dir,
'faster_rcnn_{}_{}_{}.pth'.format(args.checksession,
args.checkepoch,
args.checkpoint))
print("loading checkpoint %s" % (load_name))
checkpoint = torch.load(load_name)
args.session = checkpoint['session']
args.start_epoch = checkpoint['epoch']
fasterRCNN.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
lr = optimizer.param_groups[0]['lr']
if 'pooling_mode' in checkpoint.keys():
cfg.POOLING_MODE = checkpoint['pooling_mode']
print("loaded checkpoint %s" % (load_name))
if args.mGPUs:
fasterRCNN = nn.DataParallel(fasterRCNN)
iters_per_epoch = int(train_size / args.batch_size)
# tfboard
if args.use_tfboard:
from tensorboardX import SummaryWriter
logger = SummaryWriter("logs")
#TODO
#logger.add_graph(fasterRCNN, (im_data1, im_data2, im_info, gt_boxes, num_boxes))
#TODO
if args.net == 'vgg16f':
for epoch in range(args.start_epoch, args.max_epochs + 1):
# setting to train mode
fasterRCNN.train()
loss_temp = 0
start = time.time()
if epoch % (args.lr_decay_step + 1) == 0:
adjust_learning_rate(optimizer, args.lr_decay_gamma)
lr *= args.lr_decay_gamma
data_iter = iter(dataloader)
for step in range(iters_per_epoch):
data = next(data_iter)
im_data1.resize_(data[0].size()).copy_(data[0])
im_data2.resize_(data[1].size()).copy_(data[1])
im_info.resize_(data[2].size()).copy_(data[2])
gt_boxes.resize_(data[3].size()).copy_(data[3])
num_boxes.resize_(data[4].size()).copy_(data[4])
fasterRCNN.zero_grad()
rois, cls_prob, bbox_pred, \
rpn_loss_cls, rpn_loss_box, \
RCNN_loss_cls, RCNN_loss_bbox, \
rois_label = fasterRCNN(im_data1, im_data2, im_info, gt_boxes, num_boxes)
loss = rpn_loss_cls.mean() + rpn_loss_box.mean() \
+ RCNN_loss_cls.mean() + RCNN_loss_bbox.mean()
loss_temp += loss.item()
# backward
optimizer.zero_grad()
loss.backward()
if args.net == "vgg16":
clip_gradient(fasterRCNN, 10.)
optimizer.step()
if step % args.disp_interval == 0:
end = time.time()
if step > 0:
loss_temp /= (args.disp_interval + 1)
if args.mGPUs:
loss_rpn_cls = rpn_loss_cls.mean().item()
loss_rpn_box = rpn_loss_box.mean().item()
loss_rcnn_cls = RCNN_loss_cls.mean().item()
loss_rcnn_box = RCNN_loss_bbox.mean().item()
fg_cnt = torch.sum(rois_label.data.ne(0))
bg_cnt = rois_label.data.numel() - fg_cnt
else:
loss_rpn_cls = rpn_loss_cls.item()
loss_rpn_box = rpn_loss_box.item()
loss_rcnn_cls = RCNN_loss_cls.item()
loss_rcnn_box = RCNN_loss_bbox.item()
fg_cnt = torch.sum(rois_label.data.ne(0))
bg_cnt = rois_label.data.numel() - fg_cnt
Log.info("[session %d][epoch %2d][iter %4d/%4d] loss: %.4f, lr: %.2e" \
% (args.session, epoch, step, iters_per_epoch, loss_temp, lr))
Log.info("\t\t\tfg/bg=(%d/%d), time cost: %f" %
(fg_cnt, bg_cnt, end - start))
Log.info("\t\t\trpn_cls: %.4f, rpn_box: %.4f, rcnn_cls: %.4f, rcnn_box %.4f" \
% (loss_rpn_cls, loss_rpn_box, loss_rcnn_cls, loss_rcnn_box))
if args.use_tfboard:
info = {
'loss': loss_temp,
'loss_rpn_cls': loss_rpn_cls,
'loss_rpn_box': loss_rpn_box,
'loss_rcnn_cls': loss_rcnn_cls,
'loss_rcnn_box': loss_rcnn_box
}
logger.add_scalars(
"logs_s_{}/losses".format(args.session), info,
(epoch - 1) * iters_per_epoch + step)
loss_temp = 0
start = time.time()
save_name = os.path.join(
output_dir,
'faster_rcnn_{}_{}_{}.pth'.format(args.session, epoch, step))
save_checkpoint(
{
'session':
args.session,
'epoch':
epoch + 1,
'model':
fasterRCNN.module.state_dict()
if args.mGPUs else fasterRCNN.state_dict(),
'optimizer':
optimizer.state_dict(),
'pooling_mode':
cfg.POOLING_MODE,
'class_agnostic':
args.class_agnostic,
}, save_name)
print('save model: {}'.format(save_name))
elif args.net == 'vgg16c':
for epoch in range(args.start_epoch, args.max_epochs + 1):
# setting to train mode
fasterRCNN.train()
loss_temp = 0
start = time.time()
if epoch % (args.lr_decay_step + 1) == 0:
adjust_learning_rate(optimizer, args.lr_decay_gamma)
lr *= args.lr_decay_gamma
data_iter = iter(dataloader)
for step in range(iters_per_epoch):
data = next(data_iter)
im_data1.resize_(data[0].size()).copy_(data[0])
im_data2.resize_(data[1].size()).copy_(data[1])
im_info.resize_(data[2].size()).copy_(data[2])
gt_boxes.resize_(data[3].size()).copy_(data[3])
num_boxes.resize_(data[4].size()).copy_(data[4])
fasterRCNN.zero_grad()
rois, cls_prob, bbox_pred, \
rpn_loss_cls1, rpn_loss_box1, \
rpn_loss_cls2, rpn_loss_box2, \
RCNN_loss_cls, RCNN_loss_bbox, \
rois_label = fasterRCNN(im_data1, im_data2, im_info, gt_boxes, num_boxes)
loss = rpn_loss_cls1.mean() + rpn_loss_box1.mean() \
+ rpn_loss_cls2.mean() + rpn_loss_box2.mean() \
+ RCNN_loss_cls.mean() + RCNN_loss_bbox.mean()
loss_temp += loss.item()
# backward
optimizer.zero_grad()
loss.backward()
if args.net == "vgg16":
clip_gradient(fasterRCNN, 10.)
optimizer.step()
if step % args.disp_interval == 0:
end = time.time()
if step > 0:
loss_temp /= (args.disp_interval + 1)
if args.mGPUs:
loss_rpn_cls1 = rpn_loss_cls1.mean().item()
loss_rpn_cls2 = rpn_loss_cls2.mean().item()
loss_rpn_box1 = rpn_loss_box1.mean().item()
loss_rpn_box2 = rpn_loss_box2.mean().item()
loss_rcnn_cls = RCNN_loss_cls.mean().item()
loss_rcnn_box = RCNN_loss_bbox.mean().item()
fg_cnt = torch.sum(rois_label.data.ne(0))
bg_cnt = rois_label.data.numel() - fg_cnt
else:
loss_rpn_cls1 = rpn_loss_cls1.item()
loss_rpn_cls2 = rpn_loss_cls2.item()
loss_rpn_box1 = rpn_loss_box1.item()
loss_rpn_box2 = rpn_loss_box2.item()
loss_rcnn_cls = RCNN_loss_cls.item()
loss_rcnn_box = RCNN_loss_bbox.item()
fg_cnt = torch.sum(rois_label.data.ne(0))
bg_cnt = rois_label.data.numel() - fg_cnt
Log.info("[session %d][epoch %2d][iter %4d/%4d] loss: %.4f, lr: %.2e" \
% (args.session, epoch, step, iters_per_epoch, loss_temp, lr))
Log.info("\t\t\tfg/bg=(%d/%d), time cost: %f" %
(fg_cnt, bg_cnt, end - start))
Log.info("\t\t\trpn_cls1: %.4f,rpn_cls2: %.4f, rpn_box1: %.4f, rpn_box2: %.4f,rcnn_cls: %.4f, rcnn_box %.4f" \
% (loss_rpn_cls1, loss_rpn_cls2,loss_rpn_box1,loss_rpn_box2, loss_rcnn_cls, loss_rcnn_box))
if args.use_tfboard:
info = {
'loss': loss_temp,
'loss_rpn_cls1': loss_rpn_cls1,
'loss_rpn_cls2': loss_rpn_cls2,
'loss_rpn_box1': loss_rpn_box1,
'loss_rpn_box2': loss_rpn_box2,
'loss_rcnn_cls': loss_rcnn_cls,
'loss_rcnn_box': loss_rcnn_box
}
logger.add_scalars(
"logs_s_{}/losses".format(args.session), info,
(epoch - 1) * iters_per_epoch + step)
loss_temp = 0
start = time.time()
save_name = os.path.join(
output_dir,
'faster_rcnn_{}_{}_{}.pth'.format(args.session, epoch, step))
save_checkpoint(
{
'session':
args.session,
'epoch':
epoch + 1,
'model':
fasterRCNN.module.state_dict()
if args.mGPUs else fasterRCNN.state_dict(),
'optimizer':
optimizer.state_dict(),
'pooling_mode':
cfg.POOLING_MODE,
'class_agnostic':
args.class_agnostic,
}, save_name)
print('save model: {}'.format(save_name))
#logger.add_graph(fasterRCNN, (im_data1, im_data2, im_info, gt_boxes, num_boxes))
if args.use_tfboard:
logger.close()