def __init__(
self,
cfg,
confidence_threshold=0.7,
show_mask_heatmaps=False,
masks_per_dim=2,
min_image_size=224,
):
self.cfg = cfg.clone()
self.model = build_detection_model(cfg)
self.model.eval()
self.device = torch.device(cfg.MODEL.DEVICE)
self.model.to(self.device)
self.min_image_size = min_image_size
save_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg,
self.model,
save_dir=save_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
self.transforms = self.build_transform()
mask_threshold = -1 if show_mask_heatmaps else 0.5
self.masker = Masker(threshold=mask_threshold, padding=1)
# used to make colors for each class
self.palette = torch.tensor([2**25 - 1, 2**15 - 1, 2**21 - 1])
self.cpu_device = torch.device("cpu")
self.confidence_threshold = confidence_threshold
self.show_mask_heatmaps = show_mask_heatmaps
self.masks_per_dim = masks_per_dim
def train(cfg, local_rank, distributed):
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,
find_unused_parameters=True,
device_ids=[local_rank],
output_device=local_rank,
# this should be removed if we update BatchNorm stats
broadcast_buffers=False,
)
arguments = {}
arguments["iteration"] = 0
output_dir = cfg.OUTPUT_DIR
save_to_disk = get_rank() == 0
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_train = make_data_loader(
cfg,
is_train=True,
is_distributed=distributed,
start_iter=arguments["iteration"],
)
checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD
data_loader_val = make_data_loader(cfg,
is_train=False,
is_distributed=distributed)
data_loader_val = data_loader_val[0]
do_train(
model,
data_loader_train,
data_loader_val,
optimizer,
scheduler,
checkpointer,
device,
checkpoint_period,
arguments,
output_dir,
)
return model
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="data/occlusion_net_train.yaml",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--cometml-tag",
dest="cometml_tag",
default="occlusion-net",
)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
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
args.distributed = num_gpus > 1
if args.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()
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
logger = setup_logger("maskrcnn_benchmark", output_dir, get_rank())
logger.info("Using {} GPUs".format(num_gpus))
logger.info(args)
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
#model = train(cfg, args.local_rank, args.distributed)
model = build_detection_model(cfg)
device = torch.device(cfg.MODEL.DEVICE)
model.to(device).eval()
if not args.skip_test:
run_test(cfg, model, args.distributed)