def get_cfg():
args = parse_args()
print("Called with args:")
print(args)
args = set_dataset_args(args)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print("Using config:")
pprint.pprint(cfg)
# np.random.seed(cfg.RNG_SEED)
setup_seed(cfg.RNG_SEED)
return args
import torch.nn as nn
from roi_data_layer.roidb import combined_roidb
from roi_data_layer.roibatchLoader import roibatchLoader
from model.utils.config import cfg, cfg_from_file, cfg_from_list, get_output_dir
from model.utils.net_utils import weights_normal_init, save_net, load_net, \
adjust_learning_rate, save_checkpoint, clip_gradient, FocalLoss, sampler, calc_supp, EFocalLoss
from model.utils.parser_func import parse_args, set_dataset_args
if __name__ == '__main__':
args = parse_args()
print('Called with args:')
print(args)
args = set_dataset_args(args)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
np.random.seed(cfg.RNG_SEED)
# torch.backends.cudnn.benchmark = True
if torch.cuda.is_available() and not args.cuda:
print(
"WARNING: You have a CUDA device, so you should probably run with --cuda"
)
try:
xrange # Python 2
except NameError:
xrange = range # Python 3
lr = cfg.TRAIN.LEARNING_RATE
momentum = cfg.TRAIN.MOMENTUM
weight_decay = cfg.TRAIN.WEIGHT_DECAY
if __name__ == '__main__':
args = parse_args()
print('Called with args:')
print(args)
args = set_dataset_args(args, test=True)
if torch.cuda.is_available() and not args.cuda:
print(
"WARNING: You have a CUDA device, so you should probably run with --cuda"
)
np.random.seed(cfg.RNG_SEED)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
print('Using config:')
pprint.pprint(cfg)
cfg.TRAIN.USE_FLIPPED = False
def exp_htcn_mixed(cfg_file, output_dir, dataset_source, val_datasets, device,
net, optimizer, num_workers, lr, batch_size, start_epoch,
max_epochs, lr_decay_gamma, lr_decay_step, resume,
load_name, class_agnostic, debug, _run):
args = Args(dataset=dataset_source,
dataset_t="",
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, _, imdb, imdb_t = init_dataloaders_1s_1t(
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_frcnn_utils.init_non_damodel_optimizer(
lr,
class_agnostic,
device,
imdb,
load_name,
net,
optimizer,
resume,
session,
start_epoch,
is_all_params=True)
if torch.cuda.device_count() > 1:
fasterRCNN = nn.DataParallel(fasterRCNN)
iters_per_epoch = int(10000 / batch_size)
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_no_da_frcnn_one_epoch(
args, total_step, dataloader_s, iters_per_epoch, fasterRCNN,
optimizer, device, logger)
save_name = os.path.join(
output_dir,
'source_train_{}_session_{}_epoch_{}_total_step_{}.pth'.format(
dataset_source, 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
def exp_htcn_mixed(cfg_file, output_dir, dataset_source, dataset_target,
val_datasets, device, net, optimizer, num_workers,
teacher_pth, student_pth, lr, batch_size, start_epoch,
max_epochs, lr_decay_gamma, lr_decay_step, resume,
load_name, imitation_loss_weight, eta, gamma, ef,
class_agnostic, lc, gc, LA_ATT, MID_ATT, debug, _run):
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, False)
if cfg_file is not None:
cfg_from_file(cfg_file)
if args_val.set_cfgs is not None:
cfg_from_list(args_val.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)
val_dataloader_ts, val_imdb_ts = init_frcnn_utils.init_val_dataloaders_mt(
args_val, 1, num_workers)
session = 1
teacher = init_frcnn_utils.init_model_only(device,
"res101",
htcn_resnet,
val_imdb_ts[0],
teacher_pth,
class_agnostic=class_agnostic,
lc=lc,
gc=gc,
la_attention=LA_ATT,
mid_attention=MID_ATT)
fasterRCNN = init_frcnn_utils.init_model_only(
device,
"res50",
htcn_resnet,
val_imdb_ts[0],
student_pth,
class_agnostic=class_agnostic,
lc=lc,
gc=gc,
la_attention=LA_ATT,
mid_attention=MID_ATT)
fasterRCNN_2 = init_frcnn_utils.init_model_only(
device,
"res50",
htcn_resnet,
val_imdb_ts[0],
student_pth,
class_agnostic=class_agnostic,
lc=lc,
gc=gc,
la_attention=LA_ATT,
mid_attention=MID_ATT)
fasterRCNN.RCNN_rpn = teacher.RCNN_rpn
if torch.cuda.device_count() > 1:
fasterRCNN = nn.DataParallel(fasterRCNN)
total_step = 0
best_ap = 0.
if isinstance(val_datasets, list):
avg_ap = 0
for i, val_dataloader_t in enumerate(val_dataloader_ts):
map = frcnn_utils.eval_one_dataloader(output_dir, val_dataloader_t,
fasterRCNN, device,
val_imdb_ts[i])
logger.log_scalar(
"student with teacher rpn map on {}".format(val_datasets[i]),
map, 0)
map = frcnn_utils.eval_one_dataloader(output_dir, val_dataloader_t,
teacher, device,
val_imdb_ts[i])
logger.log_scalar(
"teacher original map on {}".format(val_datasets[i]), map, 0)
teacher.RCNN_rpn = fasterRCNN_2.RCNN_rpn
map = frcnn_utils.eval_one_dataloader(output_dir, val_dataloader_t,
teacher, device,
val_imdb_ts[i])
logger.log_scalar(
"teacher with stu rpn map on {}".format(val_datasets[i]), map,
0)
def exp_htcn_mixed(cfg_file, output_dir, dataset_source, dataset_target, val_datasets,
model_type, device, net, optimizer, num_workers, model_pth, class_agnostic, lc, gc, LA_ATT, MID_ATT,
debug, _run):
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_val.set_cfgs is not None:
cfg_from_list(args_val.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)
val_dataloader_ts, val_imdb_ts = init_frcnn_utils.init_val_dataloaders_mt(args_val, 1, num_workers)
session = 1
backbone_fn = htcn_resnet
if 'res' in net:
if model_type == 'normal':
backbone_fn = n_resnet
elif model_type == 'saitp':
backbone_fn = s_resnet
else:
if model_type == 'normal':
backbone_fn = n_vgg16
elif model_type == 'htcn':
backbone_fn = htcn_vgg16
elif model_type == 'saitp':
backbone_fn = None
model = init_frcnn_utils.init_model_only(device, net, backbone_fn, val_imdb_ts[0], model_pth, class_agnostic=class_agnostic, lc=lc,
gc=gc, la_attention=LA_ATT, mid_attention=MID_ATT)
total_step = 0
best_ap = 0.
avg_ap = 0.
avg_ap_per_class = {}
if isinstance(val_datasets, list):
for i, val_dataloader_t in enumerate(val_dataloader_ts):
map, ap_per_class = frcnn_utils.eval_one_dataloader(output_dir, val_dataloader_t, model, device, val_imdb_ts[i], return_ap_class=True)
logger.log_scalar(" map on {}".format(val_datasets[i]), map, 0)
for cls, ap in ap_per_class.items():
if cls in avg_ap_per_class:
avg_ap_per_class[cls] += ap
else:
avg_ap_per_class[cls] = ap
avg_ap += map
avg_ap /= len(val_dataloader_ts)
for cls, ap in avg_ap_per_class.items():
ap /= len(val_dataloader_ts)
logger.log_scalar(" map of class {}".format(cls), ap, 0)
logger.log_scalar("avp map",avg_ap, 0)
return avg_ap.item()
def exp_htcn_mixed(cfg_file, output_dir, dataset_source, device, net,
optimizer, num_workers, lr, batch_size, start_epoch,
max_epochs, lr_decay_gamma, lr_decay_step, resume,
load_name, pretrained, eta, gamma, ef, class_agnostic, lc,
gc, LA_ATT, MID_ATT, debug, _run):
args = Args(dataset=dataset_source,
dataset_t=[],
imdb_name_target=[],
cfg_file=cfg_file,
net=net)
args = set_dataset_args(args)
is_bgr = False
if net in ['res101', 'res50', 'res152', 'vgg16']:
is_bgr = True
logger = LoggerForSacred(None, ex)
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)
load_id = re.findall("\d+", load_name)[0]
output_dir = output_dir + "_{}".format(load_id)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
dataloader_s, _, imdb, _ = init_dataloaders_1s_mt(args, batch_size,
num_workers, is_bgr)
session = 1
fasterRCNN = init_htcn_model(LA_ATT,
MID_ATT,
class_agnostic,
device,
gc,
imdb,
lc,
load_name,
net,
strict=False,
pretrained=pretrained)
dtm = nn.Sequential(nn.Conv2d(3, 256, 1, stride=1, padding=0, bias=False),
nn.ReLU(), nn.Conv2d(256, 3, 1))
dtm.to(device)
optimizer = torch.optim.SGD(dtm.parameters(), lr=lr, momentum=0.9)
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)
dtm_util.get_mask_for_target(args, FL, 0, dataloader_s, iters_per_epoch,
fasterRCNN, dtm, optimizer, device, logger)
find_id = re.findall("\d+", load_name)
if len(find_id) == 0:
find_id = 0
else:
find_id = re.findall("\d+", load_name)[-1]
torch.save(
dtm,
os.path.join(output_dir,
'dtm_target_cnn_{}_{}.p'.format(load_id, find_id)))
return 0
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, mask_load_p, resume, load_name, pretrained,
model_type, eta, gamma, ef, class_agnostic, lc, gc, LA_ATT,
MID_ATT, debug, _run):
args = Args(dataset=dataset_source,
dataset_t=dataset_target,
cfg_file=cfg_file,
net=net)
args = set_dataset_args(args)
is_bgr = False
if net in ['res101', 'res50', 'res152', 'vgg16']:
is_bgr = True
logger = LoggerForSacred(None, ex, False)
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)
backbone_fn = htcn_resnet
if 'res' in net:
if model_type == 'normal':
backbone_fn = n_resnet
elif model_type == 'saitp':
backbone_fn = s_resnet
else:
if model_type == 'normal':
backbone_fn = n_vgg16
elif model_type == 'htcn':
backbone_fn = htcn_vgg16
elif model_type == 'saitp':
backbone_fn = None
dataloader_s, dataloader_t, imdb, imdb_t = init_dataloaders_1s_1t(
args, batch_size, num_workers, is_bgr, False)
model = init_frcnn_utils.init_model_only(device,
net,
backbone_fn,
imdb_t,
'',
class_agnostic=class_agnostic,
lc=lc,
gc=gc,
la_attention=LA_ATT,
mid_attention=MID_ATT)
model.eval()
im_data = torch.randn(1, 3, 600, 1200).to(device)
im_info = torch.FloatTensor([[600, 900, 2]]).to(device)
gt_boxes = torch.zeros((1, 1, 5)).to(device)
num_boxes = torch.zeros([1]).to(device)
macs, params = profile(model,
inputs=(im_data, im_info, gt_boxes, num_boxes))
macs, params = clever_format([macs, params], "%.3f")
print("Model CFLOPS: {}".format(macs))
print("Model Cparams: {}".format(params))
random_mask = nn.Sequential(
nn.Conv2d(3, 256, 1, stride=1, padding=0, bias=False), nn.ReLU(),
nn.Conv2d(256, 3, 1)).to(device)
macs, params = profile(random_mask, inputs=(im_data, ))
macs, params = clever_format([macs, params], "%.3f")
print("Mask CFLOPS: {}".format(macs))
print("Mask Cparams: {}".format(params))
iters_per_epoch = int(1000 / batch_size)
data_iter_s = iter(dataloader_s)
for step in range(1, iters_per_epoch + 1):
try:
data_s = next(data_iter_s)
except:
data_iter_s = iter(dataloader_s)
data_s = next(data_iter_s)
im_data = data_s[0].to(device)
im_info = data_s[1].to(device)
gt_boxes = data_s[2].to(device)
num_boxes = data_s[3].to(device)
pass
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, pretrained,
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)
is_bgr = False
if net in ['res101', 'res50', 'res152', 'vgg16']:
is_bgr = 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, m_dataloader_t, imdb, m_imdb_t = init_dataloaders_1s_mt(args, batch_size, num_workers, is_bgr)
val_dataloader_ts, val_imdb_ts = init_val_dataloaders_mt(args_val, 1, num_workers, is_bgr)
session = 1
fasterRCNN = init_htcn_model(LA_ATT, MID_ATT, class_agnostic, device, gc, imdb, lc, load_name, net, pretrained=pretrained)
#fasterRCNN.re_init_da_layers(device)
lr, optimizer, session, start_epoch = init_optimizer(lr, fasterRCNN, optimizer, resume, load_name, session, start_epoch, is_all_params=True)
# _, optimizer_unsup, _, _ = init_optimizer(lr, fasterRCNN, optimizer, resume, load_name, session,
# start_epoch, is_all_params=True)
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
if resume:
total_step = (start_epoch - 1) * 10000
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 = inc_frcnn_utils.train_htcn_one_epoch_inc_union(args, FL, total_step, dataloader_s, m_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
