def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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://")
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)
if not args.skip_test:
test(cfg, model, args.distributed)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default=
"/home/qinjianbo/SRC/maskrcnn-benchmark/configs/e2e_faster_rcnn_R_50_FPN_1x.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
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("maskrcnn_benchmark", 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)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
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_inference = make_data_loader(cfg, is_train=False, is_distributed=distributed)
return model, cfg, distributed
def setup_env_and_logger(args, cfg):
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()
model_name = get_model_name(cfg, args.model_suffix)
train_dir = os.path.join(args.train_dir, model_name)
if train_dir:
mkdir(train_dir)
logger = setup_logger("siammot", train_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))
output_config_path = os.path.join(train_dir, 'config.yml')
logger.info("Saving config into: {}".format(output_config_path))
save_config(cfg, output_config_path)
return train_dir, logger
def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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.deprecated.init_process_group(
backend="nccl", init_method="env://"
)
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)
if not args.skip_test:
test(cfg, model, args.distributed)
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(
"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_list(args.opts)
output_dir = cfg.OUTPUT_DIR
config_file = os.path.join(output_dir, "runtime_config.yaml")
if args.config_file != "":
config_file = args.config_file
cfg.merge_from_file(config_file)
cfg.merge_from_list(args.opts)
adjustment_for_relation(cfg)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", 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())
data_loader_val = make_data_loader(cfg, is_train=False, is_distributed=distributed)
model = build_detection_model(cfg)
model.to(cfg.MODEL.DEVICE)
checkpoint_output_dir = os.path.join(output_dir, 'checkpoints')
checkpointer = DetectronCheckpointer(cfg, model, save_dir=checkpoint_output_dir)
checkpoint, ckpt_fname = checkpointer.load(cfg.MODEL.WEIGHT)
results_dict = compute_on_dataset(model, data_loader_val[0], cfg.MODEL.DEVICE)
predictions = _accumulate_predictions_from_multiple_gpus(results_dict)
torch.save(predictions, '/p300/flickr30k_images/flickr30k_anno/precomp_proposals_nms1e5.pth')
def main():
parser = argparse.ArgumentParser(description="PyTorch Relation Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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("image_retrieval_using_sg", 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))
output_config_path = os.path.join(cfg.OUTPUT_DIR, 'config.yml')
logger.info("Saving config into: {}".format(output_config_path))
# save overloaded model config in the output directory
save_config(cfg, output_config_path)
model, test_result = train(cfg, args.local_rank, args.distributed, logger)
evaluator(logger, test_result)
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("--benchmark",
help='enable `torch.backends.cudnn.benchmark`',
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.backends.cudnn.benchmark = args.benchmark
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("maskrcnn_benchmark", 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)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
do_test(cfg, model, distributed)
def main():
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(local_rank)
torch.distributed.init_process_group(
backend="nccl", init_method="env://"
)
cfg.merge_from_file(config_file)
cfg.merge_from_list(opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", 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)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
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=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,
)
synchronize()
def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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()
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(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)
if not args.skip_test:
run_test(cfg, model)
def main():
args = 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://"
)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
### Training Setups ###
args.run_name = get_run_name() + '_step'
output_dir = get_output_dir(args, args.run_name, args.output_dir)
args.cfg_filename = os.path.basename(args.config_file)
cfg.OUTPUT_DIR = output_dir
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=cfg,
local_rank=args.local_rank,
distributed=args.distributed,
use_tensorboard=args.use_tensorboard
)
if not args.skip_test:
test(cfg, model, args.distributed)
def main(args):
cfg.merge_from_file(args.config_file)
num_gpus = get_num_gpus()
DatasetCatalog = None
# train_dataset = cfg.DATASETS.TRAIN[0]
# paths_catalog = import_file(
# "maskrcnn_benchmark.config.paths_catalog", cfg.PATHS_CATALOG, True
# )
# data = json.load(open(paths_catalog.DatasetCatalog.DATASETS[train_dataset]['ann_file']))
# iters_per_epoch = len(data['images'])
# cfg.defrost()
# iters_per_epoch = math.ceil(iters_per_epoch / cfg.SOLVER.IMS_PER_BATCH)
# cfg.SOLVER.MAX_ITER = round(args.epochs * args.scale * iters_per_epoch)
# cfg.SOLVER.STEPS = (round(8 * args.scale * iters_per_epoch),
# round(11 * args.scale * iters_per_epoch),
# round(16 * args.scale * iters_per_epoch))
# cfg.SOLVER.IMS_PER_BATCH = num_gpus * 4
# cfg.TEST.IMS_PER_BATCH = num_gpus * 16
# cfg.freeze()
mkdir(cfg.OUTPUT_DIR)
if args.vis_title is None:
args.vis_title = os.path.basename(cfg.OUTPUT_DIR)
logger = setup_logger("maskrcnn_benchmark", cfg.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))
logger.info(DatasetCatalog)
model = network.train(cfg, args, DatasetCatalog)
network.test(cfg, args, model=model, DatasetCatalog=DatasetCatalog)
def load_parameters(self):
if self.distributed:
torch.cuda.set_device(self.local_rank)
torch.distributed.init_process_group(
backend="nccl", init_method="env://"
)
synchronize()
self.cfg.merge_from_file(self.config_file)
self.icwt_21_objs = True if str(21) in self.cfg.DATASETS.TRAIN[0] else False
if self.cfg.OUTPUT_DIR:
mkdir(self.cfg.OUTPUT_DIR)
logger = setup_logger("maskrcnn_benchmark", self.cfg.OUTPUT_DIR, get_rank())
logger.info("Using {} GPUs".format(self.num_gpus))
logger.info("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(self.config_file))
with open(self.config_file, "r") as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(self.cfg))
def main(args, skip_test=False):
cfg = c.clone()
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://"
)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.OUTPUT_DIR = os.path.join("output", cfg.OUTPUT_DIR, "train")
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)
if (not args.skip_test) and (not skip_test):
test(cfg, model, args.distributed)
def main():
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(local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
cfg.merge_from_file(config_file)
cfg.merge_from_list(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("Collecting env info (might take some time)")
logger.info("\n" + collect_env_info())
logger.info("Loaded configuration file {}".format(config_file))
with open(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,
local_rank,
distributed,
use_tensorboard=use_tensorboard)
if not skip_test:
test(cfg, model, distributed)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default="configs/free_anchor_R-50-FPN_8gpu_1x.yaml",
metavar="FILE",
help="path to config file",
)
parser.add_argument("--local_rank", type=int, default=0)
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://")
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
# cfg.merge_from_list(['TEST.IMS_PER_BATCH', 1])
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", 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.rpn = RetinaNetModule(cfg)
model.to(cfg.MODEL.DEVICE)
checkpointer = DetectronCheckpointer(cfg, model)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox", )
output_folders = [None] * len(cfg.DATASETS.TEST)
if cfg.OUTPUT_DIR:
dataset_names = cfg.DATASETS.TEST
for idx, dataset_name in enumerate(dataset_names):
output_folder = os.path.join(cfg.OUTPUT_DIR, "NR", 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, data_loader_val in zip(output_folders,
data_loaders_val):
inference(
model,
data_loader_val,
iou_types=iou_types,
# box_only=cfg.MODEL.RPN_ONLY,
box_only=False
if cfg.RETINANET.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,
)
synchronize()
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--use_tensorboard",
default=True,
type=bool,
help="Enable/disable tensorboard logging (enabled by default)")
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument("--log_step",
default=50,
type=int,
help='Number of iteration for each log')
parser.add_argument(
"--eval_mode",
default="test",
type=str,
help=
'Use defined test datasets for periodic evaluation or use a validation split. Default: "test", alternative "val"'
)
parser.add_argument("--eval_step",
type=int,
default=15000,
help="Number of iterations for periodic evaluation")
parser.add_argument(
"--return_best",
type=bool,
default=False,
help=
"If false (default) tests on the target the last model. If true tests on the target the model with the best performance on the validation set"
)
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))
output_config_path = os.path.join(cfg.OUTPUT_DIR, 'config.yml')
logger.info("Saving config into: {}".format(output_config_path))
# save overloaded model config in the output directory
save_config(cfg, output_config_path)
model = train(cfg, args)
if not args.skip_test:
run_test(cfg, model, args.distributed)
def main():
# apply_prior prior_mask
# 0 - -
# 1 Y -
# 2 - Y
# 3 Y Y
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default="",
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('--num_iteration',
dest='num_iteration',
help='Specify which weight to load',
default=-1,
type=int)
parser.add_argument('--object_thres',
dest='object_thres',
help='Object threshold',
default=0.4,
type=float) # used to be 0.4 or 0.05
parser.add_argument('--human_thres',
dest='human_thres',
help='Human threshold',
default=0.6,
type=float)
parser.add_argument('--prior_flag',
dest='prior_flag',
help='whether use prior_flag',
default=1,
type=int)
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 and torch.cuda.is_available()
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
print('prior flag: {}'.format(args.prior_flag))
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
# DATA_DIR = os.path.abspath(os.path.join(ROOT_DIR, 'Data'))
args.config_file = os.path.join(ROOT_DIR, args.config_file)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("DRG", 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)
device = torch.device(
"cuda") if torch.cuda.is_available() else torch.device("cpu")
model.to(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)
if args.num_iteration != -1:
args.ckpt = os.path.join(cfg.OUTPUT_DIR,
'model_%07d.pth' % args.num_iteration)
ckpt = cfg.MODEL.WEIGHT if args.ckpt is None else args.ckpt
logger.info("Testing checkpoint {}".format(ckpt))
_ = checkpointer.load(ckpt, use_latest=args.ckpt is None)
# iou_types = ("bbox",)
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
if args.num_iteration != -1:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference_ho",
dataset_name,
"model_%07d" % args.num_iteration)
else:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference_ho",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
opt = {}
opt['word_dim'] = 300
opt['use_thres_dic'] = 1
for output_folder, dataset_name in zip(output_folders, dataset_names):
data = DatasetCatalog.get(dataset_name)
data_args = data["args"]
test_detection = pickle.load(open(data_args['test_detection_file'],
"rb"),
encoding='latin1')
word_embeddings = pickle.load(open(data_args['word_embedding_file'],
"rb"),
encoding='latin1')
opt['thres_dic'] = pickle.load(open(data_args['threshold_dic'], "rb"),
encoding='latin1')
output_file = os.path.join(output_folder, 'detection_times.pkl')
output_file_human = os.path.join(output_folder, 'detection_human.pkl')
output_file_object = os.path.join(output_folder,
'detection_object.pkl')
# hico_folder = os.path.join(output_folder, 'HICO')
output_map_folder = os.path.join(output_folder, 'map')
logger.info("Output will be saved in {}".format(output_file))
logger.info("Start evaluation on {} dataset.".format(dataset_name))
run_test(model,
dataset_name=dataset_name,
test_detection=test_detection,
word_embeddings=word_embeddings,
output_file=output_file,
output_file_human=output_file_human,
output_file_object=output_file_object,
object_thres=args.object_thres,
human_thres=args.human_thres,
device=device,
cfg=cfg,
opt=opt)
# Generate_HICO_detection(output_file, hico_folder)
compute_hico_map(output_map_folder, output_file, 'test')
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
parser.add_argument(
"--skip-test",
dest="skip_test",
help="Do not test the final model",
action="store_true",
)
parser.add_argument(
"--only-test",
dest="only_test",
help="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://")
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
intact_cfg(cfg)
cfg.freeze()
if cfg.MODEL.RPN__ONLY:
args.skip_test = True
cfg['DEBUG']['eval_in_train'] = -1
#check_data(cfg)
train_example_num = get_train_example_num(cfg)
croi = '_CROI' if cfg.MODEL.CORNER_ROI else ''
cfg['OUTPUT_DIR'] = f'{cfg.OUTPUT_DIR}_Tr{train_example_num}{croi}'
if not cfg.MODEL.CLASS_SPECIFIC:
cfg['OUTPUT_DIR'] += '_CA'
if cfg.MODEL.RPN__ONLY:
cfg['OUTPUT_DIR'] += '_RpnOnly'
loss_weights = cfg.MODEL.LOSS.WEIGHTS
if loss_weights[4] > 0:
k = int(loss_weights[4] * 100)
cfg['OUTPUT_DIR'] += f'_CorGeo{k}'
if loss_weights[5] > 0:
k = int(loss_weights[5])
p = int(loss_weights[6])
cfg['OUTPUT_DIR'] += f'_CorSem{k}-{p}'
output_dir = cfg.OUTPUT_DIR
if output_dir:
mkdir(output_dir)
cfn = os.path.basename(args.config_file)
shutil.copyfile(args.config_file, f"{output_dir}/{cfn}")
default_cfn = 'maskrcnn_benchmark/config/defaults.py'
shutil.copyfile(default_cfn, f"{output_dir}/default.py")
train_fns = 'data3d/suncg_utils/SuncgTorch/train_test_splited/train.txt'
shutil.copyfile(train_fns, f"{output_dir}/train.txt")
val_fns = 'data3d/suncg_utils/SuncgTorch/train_test_splited/val.txt'
shutil.copyfile(train_fns, f"{output_dir}/val.txt")
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))
min_loss = 10000
epochs_between_test = cfg.SOLVER.EPOCHS_BETWEEN_TEST
for loop in range(cfg.SOLVER.EPOCHS // cfg.SOLVER.EPOCHS_BETWEEN_TEST):
model, min_loss = train(cfg, args.local_rank, args.distributed, loop,
args.only_test, min_loss)
if not args.skip_test:
test(
cfg,
model,
args.distributed,
epoch=(1 + loop) * epochs_between_test - 1,
)
if args.only_test:
break
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default=
"../configs/kidney/e2e_mask_rcnn_X_101_32x8d_FPN_1x_liver_using_pretrained_model.yaml",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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://")
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
if cfg.OUTPUT_SUB_DIR:
output_dir = os.path.join(cfg.OUTPUT_DIR, cfg.OUTPUT_SUB_DIR)
else:
now = time.localtime()
time_dir_name = "%04d%02d%02d-%02d%02d%02d" % (
now.tm_year, now.tm_mon, now.tm_mday, now.tm_hour, now.tm_min,
now.tm_sec)
output_dir = os.path.join(cfg.OUTPUT_DIR, time_dir_name)
cfg.merge_from_list(["OUTPUT_DIR", output_dir])
cfg.freeze()
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)
def main():
parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="/home/sgiit/disk_1T/sgiit/Pengming_Feng/GitClone/ship_detection_optical/maskrcnn-benchmark/configs/ship_detection_net/ship_detection_R_101_FPN_1x.yaml",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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))
output_config_path = os.path.join(cfg.OUTPUT_DIR, 'config.yml')
logger.info("Saving config into: {}".format(output_config_path))
# save overloaded model config in the output directory
save_config(cfg, output_config_path)
model = train(cfg, args.local_rank, args.distributed)
if not args.skip_test:
run_test(cfg, model, args.distributed)
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(
"opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER,
)
#added args for Seed detection 2 strategies
# parser.add_argument(
# "--strategy",
# default=1,
# # metavar="FILE",
# help="1 for strat 1 and 2 for strat 2",
# )
args = parser.parse_args()
num_gpus = int(
os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
distributed = num_gpus > 1
print(num_gpus)
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.merge_from_list(args.strategy)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", 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)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
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,
)
synchronize()
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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,
)
parser.add_argument(
"--build-model",
default="",
metavar="FILE",
help="path to NAS model build file",
type=str,
)
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))
output_config_path = os.path.join(cfg.OUTPUT_DIR, 'config.yml')
logger.info("Saving config into: {}".format(output_config_path))
# save overloaded model config in the output directory
save_config(cfg, output_config_path)
if cfg.NAS.TRAIN_SINGLE_MODEL:
assert len(
args.build_model) != 0, 'args.build_model should be provided'
model_config = json.load(open(args.build_model, 'r'))
if isinstance(model_config, list):
assert len(model_config) == 1
model_config = model_config[0]
print('Training single model:', model_config)
model = train(cfg, args.local_rank, args.distributed, model_config)
else:
model = train(cfg, args.local_rank, args.distributed)
if not args.skip_test:
run_test(cfg, model, 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()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", 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)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
if args.load_pth:
_ = checkpointer.load_pth_file(args.load_pth)
else:
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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()
import random
import torch.backends.cudnn as cudnn
import numpy as np
seed = 1
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed + 1)
random.seed(seed + 2)
np.random.seed(seed + 3)
print('use seed')
cudnn.deterministic = True
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 = os.path.join(
cfg.OUTPUT_DIR, cfg.SUBDIR,
'GPU' + str(num_gpus) + '_LR' + str(cfg.SOLVER.BASE_LR))
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)
if not args.skip_test:
run_test(cfg, model, args.distributed)
def main():
mlperf_log.ROOT_DIR_MASKRCNN = os.path.dirname(os.path.abspath(__file__))
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Training")
parser.add_argument(
"--config-file",
default="",
metavar="FILE",
help="path to config file",
type=str,
)
parser.add_argument("--local_rank", type=int, default=0)
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 is_main_process:
# Setting logging file parameters for compliance logging
os.environ["COMPLIANCE_FILE"] = './MASKRCNN_complVv0.5.0_' + str(
datetime.datetime.now())
mlperf_log.LOG_FILE = os.getenv("COMPLIANCE_FILE")
mlperf_log._FILE_HANDLER = logging.FileHandler(mlperf_log.LOG_FILE)
mlperf_log._FILE_HANDLER.setLevel(logging.DEBUG)
mlperf_log.LOGGER.addHandler(mlperf_log._FILE_HANDLER)
if args.distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
print_mlperf(key=mlperf_log.RUN_START)
# setting seeds - needs to be timed, so after RUN_START
if is_main_process():
master_seed = random.SystemRandom().randint(0, 2**32 - 1)
seed_tensor = torch.tensor(master_seed,
dtype=torch.float32,
device=torch.device("cuda"))
else:
seed_tensor = torch.tensor(0,
dtype=torch.float32,
device=torch.device("cuda"))
torch.distributed.broadcast(seed_tensor, 0)
master_seed = int(seed_tensor.item())
else:
print_mlperf(key=mlperf_log.RUN_START)
# random master seed, random.SystemRandom() uses /dev/urandom on Unix
master_seed = random.SystemRandom().randint(0, 2**32 - 1)
# actually use the random seed
args.seed = master_seed
# random number generator with seed set to master_seed
random_number_generator = random.Random(master_seed)
print_mlperf(key=mlperf_log.RUN_SET_RANDOM_SEED, value=master_seed)
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)
# generate worker seeds, one seed for every distributed worker
worker_seeds = generate_seeds(
random_number_generator,
torch.distributed.get_world_size()
if torch.distributed.is_initialized() else 1)
# todo sharath what if CPU
# broadcast seeds from rank=0 to other workers
worker_seeds = broadcast_seeds(worker_seeds, device='cuda')
# Setting worker seeds
logger.info("Worker {}: Setting seed {}".format(
args.local_rank, worker_seeds[args.local_rank]))
torch.manual_seed(worker_seeds[args.local_rank])
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)
print_mlperf(key=mlperf_log.RUN_FINAL)
def main():
parser = argparse.ArgumentParser(
description="PyTorch Object Detection Inference")
parser.add_argument(
"--config-file",
default="configs/e2e_faster_rcnn_R_50_FPN_1x.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('--num_iteration',
dest='num_iteration',
help='Specify which weight to load',
default=-1,
type=int)
parser.add_argument('--object_thres',
dest='object_thres',
help='Object threshold',
default=0.1,
type=float) # used to be 0.4 or 0.05
parser.add_argument('--human_thres',
dest='human_thres',
help='Human threshold',
default=0.8,
type=float)
parser.add_argument('--prior_flag',
dest='prior_flag',
help='whether use prior_flag',
default=1,
type=int)
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 and torch.cuda.is_available()
if distributed:
torch.cuda.set_device(args.local_rank)
torch.distributed.init_process_group(backend="nccl",
init_method="env://")
synchronize()
ROOT_DIR = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
# DATA_DIR = os.path.abspath(os.path.join(ROOT_DIR, 'Data'))
args.config_file = os.path.join(ROOT_DIR, args.config_file)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("DRG", 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)
device = torch.device(
"cuda") if torch.cuda.is_available() else torch.device("cpu")
model.to(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)
if args.num_iteration != -1:
args.ckpt = os.path.join(cfg.OUTPUT_DIR,
'model_%07d.pth' % args.num_iteration)
ckpt = cfg.MODEL.WEIGHT if args.ckpt is None else args.ckpt
logger.info("Testing checkpoint {}".format(ckpt))
_ = checkpointer.load(ckpt, use_latest=args.ckpt is None)
# iou_types = ("bbox",)
output_folders = [None] * len(cfg.DATASETS.TEST)
dataset_names = cfg.DATASETS.TEST
if cfg.OUTPUT_DIR:
for idx, dataset_name in enumerate(dataset_names):
if args.num_iteration != -1:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference_ho",
dataset_name,
"model_%07d" % args.num_iteration)
else:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference_ho",
dataset_name)
mkdir(output_folder)
output_folders[idx] = output_folder
opt = {}
opt['word_dim'] = 300
for output_folder, dataset_name in zip(output_folders, dataset_names):
data = DatasetCatalog.get(dataset_name)
data_args = data["args"]
im_dir = data_args['im_dir']
test_detection = pickle.load(open(data_args['test_detection_file'],
"rb"),
encoding='latin1')
prior_mask = pickle.load(open(data_args['prior_mask'], "rb"),
encoding='latin1')
action_dic = json.load(open(data_args['action_index']))
action_dic_inv = {y: x for x, y in action_dic.items()}
vcoco_test_ids = open(data_args['vcoco_test_ids_file'], 'r')
test_image_id_list = [int(line.rstrip()) for line in vcoco_test_ids]
vcocoeval = VCOCOeval(data_args['vcoco_test_file'],
data_args['ann_file'],
data_args['vcoco_test_ids_file'])
word_embeddings = pickle.load(open(data_args['word_embedding_file'],
"rb"),
encoding='latin1')
output_file = os.path.join(output_folder, 'detection.pkl')
output_dict_file = os.path.join(
output_folder, 'detection_app_{}_new.pkl'.format(dataset_name))
logger.info("Output will be saved in {}".format(output_file))
logger.info("Start evaluation on {} dataset({} images).".format(
dataset_name, len(test_image_id_list)))
run_test(model,
dataset_name=dataset_name,
im_dir=im_dir,
test_detection=test_detection,
word_embeddings=word_embeddings,
test_image_id_list=test_image_id_list,
prior_mask=prior_mask,
action_dic_inv=action_dic_inv,
output_file=output_file,
output_dict_file=output_dict_file,
object_thres=args.object_thres,
human_thres=args.human_thres,
prior_flag=args.prior_flag,
device=device,
cfg=cfg)
synchronize()
vcocoeval._do_eval(output_file, ovr_thresh=0.5)
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(
"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 = cfg.OUTPUT_DIR
logger = setup_logger("maskrcnn_benchmark", save_dir, get_rank(), filename="testlog.txt")
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)
if amp is not None:
# 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)
ignore_cls = cfg.INPUT.IGNORE_CLS
for output_folder, dataset_name, data_loader_val in zip(output_folders, dataset_names, data_loaders_val):
if not ignore_cls and 'coco' in dataset_name and cfg.WEAK.MODE and cfg.WEAK.NUM_CLASSES != 80:
logger.info(f"override ignore_cls -> True for {dataset_name}")
ignore_cls = True
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,
bbox_aug=cfg.TEST.BBOX_AUG.ENABLED,
device=cfg.MODEL.DEVICE,
expected_results=cfg.TEST.EXPECTED_RESULTS,
expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
output_folder=output_folder,
ignore_cls=ignore_cls,
)
synchronize()
def main():
args = 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://")
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.merge_from_list(["MODEL.WEIGHT", args.weight])
output_dir = os.path.dirname(cfg.MODEL.WEIGHT)
cfg.OUTPUT_DIR = output_dir
if not os.path.exists(output_dir):
os.makedirs(output_dir)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", 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)
checkpointer = DetectronCheckpointer(cfg, model, save_dir=cfg.MODEL.WEIGHT)
_ = checkpointer.load(cfg.MODEL.WEIGHT, cfg.TRAIN.IGNORE_LIST)
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
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)
# default `log_dir` is "runs" - we'll be more specific here
# tb_writer = SummaryWriter('runs/6dvnet_test_3d_1')
for output_folder, dataset_name, data_loader_val in zip(
output_folders, dataset_names, data_loaders_val):
# dataiter = iter(data_loader_val)
# images, bbox, labels = dataiter.next()
# create grid of images
# img_grid = make_grid(images.tensors)
# show images
# matplotlib_imshow(img_grid, one_channel=False)
# write to tensorboard
# tb_writer.add_image('6dvnet_test_3d_1', img_grid)
#
# tb_writer.add_graph(model, images.tensors)
# tb_writer.close()
inference(
model,
data_loader_val,
dataset_name=dataset_name,
iou_types=iou_types,
box_only=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,
cfg=cfg,
)
synchronize()
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("--cls_id", type=int, default=1)
parser.add_argument(
"--ckpt",
help=
"The path to the checkpoint for test, default is the latest checkpoint.",
default=None,
)
parser.add_argument('--patched',
action='store_true',
help='patching patterns')
parser.add_argument('--patchfile',
type=str,
default='',
help='patch to be applied')
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("maskrcnn_benchmark", 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)
patched = args.patched
patchfile = args.patchfile if patched else ""
cls_id = args.cls_id
if patched:
filename = args.ckpt.split('/')[-1][:-4] + '_' + args.patchfile.split(
'/')[-2] + '_class_' + str(cls_id)
else:
filename = ""
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):
if "physical" in dataset_name:
filename_i = dataset_name + '_' + filename
else:
filename_i = filename
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,
patched=patched,
patchfile=patchfile,
file_name=filename_i,
cls_id=cls_id,
)
synchronize()
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(
"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.deprecated.init_process_group(
backend="nccl", init_method="env://"
)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
save_dir = ""
logger = setup_logger("maskrcnn_benchmark", 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)
output_dir = cfg.OUTPUT_DIR
checkpointer = DetectronCheckpointer(cfg, model, save_dir=output_dir)
_ = checkpointer.load(cfg.MODEL.WEIGHT)
iou_types = ("bbox",)
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm",)
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=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,
)
synchronize()
def main():
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)
# add
print(model)
all_index = []
for index, item in enumerate(model.named_parameters()):
all_index.append(index)
print(index)
print(item[0])
print(item[1].size())
print("All index of the model: ", all_index)
device = torch.device(cfg.MODEL.DEVICE)
model.to(device)
optimizer = make_optimizer(cfg, model)
scheduler = make_lr_scheduler(cfg, optimizer)
if args.distributed:
model = torch.nn.parallel.DistributedDataParallel(
model,
device_ids=[args.local_rank],
output_device=args.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 = make_data_loader(
cfg,
is_train=True,
is_distributed=args.distributed,
start_iter=arguments["iteration"],
)
checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD
# run_test(cfg, model, args.distributed)
# pruning
m = Mask(model)
m.init_length()
m.init_length()
print("-" * 10 + "one epoch begin" + "-" * 10)
print("remaining ratio of pruning : Norm is %f" % args.rate_norm)
print("reducing ratio of pruning : Distance is %f" % args.rate_dist)
print("total remaining ratio is %f" % (args.rate_norm - args.rate_dist))
m.modelM = model
m.init_mask(args.rate_norm, args.rate_dist)
m.do_mask()
m.do_similar_mask()
model = m.modelM
m.if_zero()
# run_test(cfg, model, args.distributed)
# change to use straightforward function to make its easy to implement Mask
# do_train(
# model,
# data_loader,
# optimizer,
# scheduler,
# checkpointer,
# device,
# checkpoint_period,
# arguments,
# )
logger = logging.getLogger("maskrcnn_benchmark.trainer")
logger.info("Start training")
meters = MetricLogger(delimiter=" ")
max_iter = len(data_loader)
start_iter = arguments["iteration"]
model.train()
start_training_time = time.time()
end = time.time()
for iteration, (images, targets, _) in enumerate(data_loader, start_iter):
data_time = time.time() - end
iteration = iteration + 1
arguments["iteration"] = iteration
scheduler.step()
images = images.to(device)
targets = [target.to(device) for target in targets]
loss_dict = model(images, targets)
# print("Loss dict",loss_dict)
losses = sum(loss for loss in loss_dict.values())
# reduce losses over all GPUs for logging purposes
loss_dict_reduced = reduce_loss_dict(loss_dict)
losses_reduced = sum(loss for loss in loss_dict_reduced.values())
meters.update(loss=losses_reduced, **loss_dict_reduced)
optimizer.zero_grad()
losses.backward()
# prun
# Mask grad for iteration
m.do_grad_mask()
optimizer.step()
batch_time = time.time() - end
end = time.time()
meters.update(time=batch_time, data=data_time)
eta_seconds = meters.time.global_avg * (max_iter - iteration)
eta_string = str(datetime.timedelta(seconds=int(eta_seconds)))
# prun
# 7375 is number iteration to train 1 epoch with batch-size = 16 and number train dataset exam is 118K (in coco)
if iteration % args.iter_pruned == 0 or iteration == cfg.SOLVER.MAX_ITER - 5000:
m.modelM = model
m.if_zero()
m.init_mask(args.rate_norm, args.rate_dist)
m.do_mask()
m.do_similar_mask()
m.if_zero()
model = m.modelM
if args.use_cuda:
model = model.cuda()
#run_test(cfg, model, args.distributed)
if iteration % 20 == 0 or iteration == max_iter:
logger.info(
meters.delimiter.join([
"eta: {eta}",
"iter: {iter}",
"{meters}",
"lr: {lr:.6f}",
"max mem: {memory:.0f}",
]).format(
eta=eta_string,
iter=iteration,
meters=str(meters),
lr=optimizer.param_groups[0]["lr"],
memory=torch.cuda.max_memory_allocated() / 1024.0 / 1024.0,
))
if iteration % checkpoint_period == 0:
checkpointer.save("model_{:07d}".format(iteration), **arguments)
if iteration == max_iter:
checkpointer.save("model_final", **arguments)
total_training_time = time.time() - start_training_time
total_time_str = str(datetime.timedelta(seconds=total_training_time))
logger.info("Total training time: {} ({:.4f} s / it)".format(
total_time_str, total_training_time / (max_iter)))
if not args.skip_test:
run_test(cfg, model, args.distributed)
def train_maskscoring_rcnn(config_file):
import sys
sys.path.append('./detection_model/maskscoring_rcnn')
# Set up custom environment before nearly anything else is imported
# NOTE: this should be the first import (no not reorder)
import argparse
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0,1,2'
import torch
#from maskrcnn_benchmark.config import cfg
from maskrcnn_benchmark.data import make_data_loader
from maskrcnn_benchmark.solver import make_lr_scheduler
from maskrcnn_benchmark.solver import make_optimizer
from maskrcnn_benchmark.engine.inference import inference
from maskrcnn_benchmark.engine.trainer import do_train
from maskrcnn_benchmark.modeling.detector import build_detection_model
from maskrcnn_benchmark.utils.checkpoint import DetectronCheckpointer
from maskrcnn_benchmark.utils.collect_env import collect_env_info
from maskrcnn_benchmark.utils.comm import synchronize, get_rank
from maskrcnn_benchmark.utils.imports import import_file
from maskrcnn_benchmark.utils.logger import setup_logger
from maskrcnn_benchmark.utils.miscellaneous import mkdir
from yacs.config import CfgNode as CN
global total_iter
total_iter = 0
def read_config_file(config_file):
"""
read config information form yaml file
"""
f = open(config_file)
opt = CN.load_cfg(f)
return opt
opt = read_config_file(config_file)
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)
if distributed:
model = torch.nn.parallel.deprecated.DistributedDataParallel(
model,
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 = make_data_loader(
cfg,
is_train=True,
is_distributed=distributed,
start_iter=arguments["iteration"],
)
checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD
do_train(
model,
data_loader,
optimizer,
scheduler,
checkpointer,
device,
checkpoint_period,
arguments,
)
return model
def test(cfg, model, distributed):
if distributed:
model = model.module
torch.cuda.empty_cache() # TODO check if it helps
iou_types = ("bbox", )
if cfg.MODEL.MASK_ON:
iou_types = iou_types + ("segm", )
output_folders = [None] * len(cfg.DATASETS.TEST)
if cfg.OUTPUT_DIR:
dataset_names = cfg.DATASETS.TEST
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, data_loader_val in zip(output_folders,
data_loaders_val):
inference(
model,
data_loader_val,
iou_types=iou_types,
box_only=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,
maskiou_on=cfg.MODEL.MASKIOU_ON)
synchronize()
# parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
# parser.add_argument(
# "--config-file",
# default="configs/e2e_ms_rcnn_R_50_FPN_1x.yaml",
# metavar="FILE",
# help="path to config file",
# type=str,
# )
# parser.add_argument("--local_rank", type=int, default=0)
# 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
# num_gpus = 2
print('num_gpus = ', num_gpus)
opt.distributed = num_gpus > 1
if opt.distributed:
torch.cuda.set_device(opt.local_rank)
torch.distributed.deprecated.init_process_group(backend="nccl",
init_method="env://")
output_dir = opt.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(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(opt))
model = train(opt, opt.local_rank, opt.distributed)
if not opt.skip_test:
test(opt, model, opt.distributed)
