def main(args):
distributed, device_ids = main_util.init_distributed_mode(
args.world_size, args.dist_url)
config = yaml_util.load_yaml_file(args.config)
if args.json is not None:
main_util.overwrite_config(config, args.json)
device = torch.device(args.device)
print(args)
print('Loading data')
train_config = config['train']
train_sampler, train_data_loader, val_data_loader, test_data_loader =\
data_util.get_coco_data_loaders(config['dataset'], train_config['batch_size'], distributed)
print('Creating model')
model_config = config['model']
model = get_model(model_config, device)
print('Model Created')
if distributed:
model = nn.parallel.DistributedDataParallel(model,
device_ids=device_ids)
if args.train:
print('Start training')
start_time = time.time()
train(model, train_sampler, train_data_loader, val_data_loader, device,
distributed, config, args, model_config['ckpt'])
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('Training time {}'.format(total_time_str))
main_util.evaluate(model, test_data_loader, device=device)
def main(args):
config = yaml_util.load_yaml_file(args.config)
if args.json is not None:
main_util.overwrite_config(config, args.json)
distributed, device_ids = main_util.init_distributed_mode(
args.world_size, args.dist_url)
device = torch.device(args.device if torch.cuda.is_available() else 'cpu')
teacher_model = get_model(config['teacher_model'], device)
module_util.freeze_module_params(teacher_model)
student_model_config = config['student_model']
student_model = get_model(student_model_config, device)
freeze_modules(student_model, student_model_config)
print('Updatable parameters: {}'.format(
module_util.get_updatable_param_names(student_model)))
distill_backbone_only = student_model_config['distill_backbone_only']
train_config = config['train']
train_sampler, train_data_loader, val_data_loader, test_data_loader = \
data_util.get_coco_data_loaders(config['dataset'], train_config['batch_size'], distributed)
if distributed:
teacher_model = DataParallel(teacher_model, device_ids=device_ids)
student_model = DistributedDataParallel(student_model,
device_ids=device_ids)
if args.distill:
distill(teacher_model, student_model, train_sampler, train_data_loader,
val_data_loader, device, distributed, distill_backbone_only,
config, args)
load_ckpt(
config['student_model']['ckpt'],
model=student_model.module if isinstance(
student_model, DistributedDataParallel) else student_model)
evaluate(teacher_model, student_model, test_data_loader, device,
args.skip_teacher_eval, args.transform_bottleneck)
def main(args):
config = yaml_util.load_yaml_file(args.config)
if args.json is not None:
main_util.overwrite_config(config, args.json)
device = torch.device(args.device)
print(args)
model_config = config.get('model', None)
if args.model_params and model_config is not None:
model = get_model(model_config, device)
analyze_model_params(model, args.modules)
if args.data_size is not None:
analyze_data_size(config['dataset'], split_name=args.data_size, resized=args.resized)
student_model_config = config.get('student_model', None)
if args.bottleneck_size is not None and (student_model_config is not None or
(model_config is not None and 'ext_config' in model_config['backbone'])):
data_logger = DataLogger()
tmp_model_config = student_model_config if student_model_config is not None else model_config
model = get_model(tmp_model_config, device, bottleneck_transformer=data_logger)
model.backbone.body.layer1.use_bottleneck_transformer = True
analyze_bottleneck_size(model, data_logger, device, config['dataset'], split_name=args.bottleneck_size)
if student_model_config is not None:
model_config = student_model_config
if args.split_model is not None:
model = get_model(model_config, device)
analyze_split_model_inference(model, device, args.quantize, args.skip_tail, config['dataset'], args.split_model)
def main(args):
config = yaml_util.load_yaml_file(args.config)
if args.json is not None:
main_util.overwrite_config(config, args.json)
device = torch.device(args.device)
print(args)
print('Creating model')
model_config = config['model'] if 'model' in config else config.get(
'student_model', None)
if model_config is None:
raise ValueError(
'`{}` should contain model or student config at root'.format(
args.config))
model = get_model(model_config, device, strict=False)
visualize_predictions(model, args.image, device, args.output)
def main(args):
distributed, device_ids = main_util.init_distributed_mode(
args.world_size, args.dist_url)
config = yaml_util.load_yaml_file(args.config)
if args.json is not None:
main_util.overwrite_config(config, args.json)
device = torch.device(args.device)
print(args)
print('Loading data')
train_config = config['train']
train_sampler, train_data_loader, val_data_loader, test_data_loader =\
data_util.get_coco_data_loaders(config['dataset'], train_config['batch_size'], distributed)
print('Creating model')
model_config = config['model']
model = get_model(model_config, device, strict=False)
module_util.freeze_module_params(model)
ext_classifier = model.get_ext_classifier()
module_util.unfreeze_module_params(ext_classifier)
print('Updatable parameters: {}'.format(
module_util.get_updatable_param_names(model)))
model.train_ext()
if distributed:
model = nn.parallel.DistributedDataParallel(model,
device_ids=device_ids)
if args.train:
print('Start training')
start_time = time.time()
ckpt_file_path = model_config['backbone']['ext_config']['ckpt']
train(model, ext_classifier, train_sampler, train_data_loader,
val_data_loader, device, distributed, config, args,
ckpt_file_path)
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
print('Training time {}'.format(total_time_str))
load_ckpt(ckpt_file_path, model=ext_classifier)
evaluate(model,
test_data_loader,
device=device,
min_recall=args.min_recall,
split_name='Test')
def main(args):
config = yaml_util.load_yaml_file(args.config)
if args.json is not None:
main_util.overwrite_config(config, args.json)
distributed, device_ids = main_util.init_distributed_mode(args.world_size, args.dist_url)
device = torch.device(args.device if torch.cuda.is_available() else 'cpu')
teacher_model = get_model(config['teacher_model'], device)
module_util.freeze_module_params(teacher_model)
student_model_config = config['student_model']
student_model = get_model(student_model_config, device)
freeze_modules(student_model, student_model_config)
ckpt_file_path = config['student_model']['ckpt']
train_config = config['train']
optim_config = train_config['optimizer']
optimizer = func_util.get_optimizer(student_model, optim_config['type'], optim_config['params'])
scheduler_config = train_config['scheduler']
lr_scheduler = func_util.get_scheduler(optimizer, scheduler_config['type'], scheduler_config['params'])
if file_util.check_if_exists(ckpt_file_path):
best_val_map, _, _ = load_ckpt(ckpt_file_path, optimizer=optimizer, lr_scheduler=lr_scheduler)
save_ckpt(student_model, optimizer, lr_scheduler, best_val_map, config, args, ckpt_file_path)