def train(cfg, local_rank, distributed, use_tensorboard=False):
model = build_detection_model(cfg)
device = torch.device(cfg.MODEL.DEVICE)
model.to(device)
optimizer = make_optimizer(cfg, model)
scheduler = make_lr_scheduler(cfg, optimizer)
# Initialize mixed-precision training
use_mixed_precision = cfg.DTYPE == "float16"
amp_opt_level = 'O1' if use_mixed_precision else 'O0'
model, optimizer = amp.initialize(model, optimizer, opt_level=amp_opt_level)
if distributed:
model = torch.nn.parallel.DistributedDataParallel(
model, device_ids=[local_rank], output_device=local_rank,
# this should be removed if we update BatchNorm stats
broadcast_buffers=False, find_unused_parameters=True,
)
arguments = {"iteration": 0, "iter_size": cfg.SOLVER.ITER_SIZE}
output_dir = cfg.OUTPUT_DIR
save_to_disk = get_rank() == 0
checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD
checkpointer = DetectronCheckpointer(
cfg, model, optimizer, scheduler, output_dir, save_to_disk
)
extra_checkpoint_data = checkpointer.load(cfg.MODEL.WEIGHT)
arguments.update(extra_checkpoint_data)
data_loader = make_data_loader(
cfg,
is_train=True,
is_distributed=distributed,
start_iter=arguments["iteration"],
)
if use_tensorboard:
meters = TensorboardLogger(
log_dir=os.path.join(cfg['OUTPUT_DIR'], 'log/'),
start_iter=arguments['iteration'],
delimiter=" ")
else:
meters = MetricLogger(delimiter=" ")
do_train(
model,
data_loader,
optimizer,
scheduler,
checkpointer,
device,
checkpoint_period,
arguments,
meters
)
return model
def train_cdb(cfg, local_rank, distributed, use_tensorboard=False):
model = build_detection_model(cfg)
device = torch.device(cfg.MODEL.DEVICE)
model.to(device)
model_cdb = ConvConcreteDB(cfg, model.backbone.out_channels)
model_cdb.to(device)
optimizer = make_optimizer(cfg, model)
scheduler = make_lr_scheduler(cfg, optimizer)
optimizer_cdb = make_cdb_optimizer(cfg, model_cdb)
scheduler_cdb = make_lr_cdb_scheduler(cfg, optimizer_cdb)
# Initialize mixed-precision training
use_mixed_precision = cfg.DTYPE == "float16"
amp_opt_level = 'O1' if use_mixed_precision else 'O0'
model, optimizer = amp.initialize(model,
optimizer,
opt_level=amp_opt_level)
model_cdb, optimizer_cdb, = amp.initialize(model_cdb,
optimizer_cdb,
opt_level=amp_opt_level)
if distributed:
model = torch.nn.parallel.DistributedDataParallel(
model,
device_ids=[local_rank],
output_device=local_rank,
# this should be removed if we update BatchNorm stats
broadcast_buffers=False,
find_unused_parameters=True,
)
model_cdb = torch.nn.parallel.DistributedDataParallel(
model_cdb,
device_ids=[local_rank],
output_device=local_rank,
# this should be removed if we update BatchNorm stats
broadcast_buffers=False,
find_unused_parameters=True,
)
arguments = {"iteration": 0}
output_dir = cfg.OUTPUT_DIR
save_to_disk = get_rank() == 0
checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD
# TODO: check whether the *_cdb is properly loaded for inference when using 1 GPU
checkpointer = DetectronCheckpointer(cfg,
model,
optimizer,
scheduler,
output_dir,
save_to_disk,
model_cdb=model_cdb)
extra_checkpoint_data = checkpointer.load(cfg.MODEL.WEIGHT)
arguments.update(extra_checkpoint_data)
print('Do CFG_DIRE', cfg.PATH_DATA_TRAIN)
data_loader = make_data_loader(
cfg,
is_train=True,
is_distributed=distributed,
start_iter=arguments["iteration"],
)
if use_tensorboard:
meters = TensorboardLogger(log_dir=os.path.join(
cfg['OUTPUT_DIR'], 'log/'),
start_iter=arguments['iteration'],
delimiter=" ")
else:
meters = MetricLogger(delimiter=" ")
do_train_cdb(model, model_cdb, data_loader, optimizer, optimizer_cdb,
scheduler, scheduler_cdb, checkpointer, device,
checkpoint_period, arguments, meters, cfg)
return model
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/private/home/fmassa/github/detectron.pytorch_v2/configs/e2e_faster_rcnn_R_50_C4_1x_caffe2.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--ckpt",
help=
"The path to the checkpoint for test, default is the latest checkpoint.",
default=None,
)
parser.add_argument(
"--task",
default="det",
type=str,
help="eval task: det | corloc",
)
parser.add_argument(
"--vis",
dest="vis",
help="Visualize the final results",
action="store_true",
)
parser.add_argument(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("wetectron", save_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(cfg)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
# Initialize mixed-precision if necessary
use_mixed_precision = cfg.DTYPE == 'float16'
amp_handle = amp.init(enabled=use_mixed_precision, verbose=cfg.AMP_VERBOSE)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
ckpt = cfg.MODEL.WEIGHT if args.ckpt is None else args.ckpt
_ = checkpointer.load(ckpt, use_latest=args.ckpt is None)
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
if cfg.MODEL.KEYPOINT_ON:
iou_types = iou_types + ("keypoints", )
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
data_loaders_val = make_data_loader(cfg,
is_train=False,
is_distributed=distributed)
for output_folder, dataset_name, data_loader_val in zip(
output_folders, dataset_names, data_loaders_val):
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=False if cfg.MODEL.RETINANET_ON else cfg.MODEL.RPN_ONLY,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
vis=args.vis,
task=args.task,
)
synchronize()