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="./configs/seq.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) checkpointer = DetectronCheckpointer(cfg, model) _ = 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) 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) model_name = cfg.MODEL.WEIGHT.split('/')[-1] 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, model_name=model_name, cfg=cfg, ) synchronize()
def main(): parser = argparse.ArgumentParser(description="PyTorch Object Detection Inference") parser.add_argument( "--config-file", default="/home/guli/Desktop/VOS_ICCV2019/maskrcnn-benchmark/configs/davis/e2e_mask_rcnn_R_50_FPN_1x_davis.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("DAVIS_MaskRCNN_baseline_test", save_dir, args.local_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 = Checkpointer(model) _ = 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) if cfg.OUTPUT_DIR: dataset_names = cfg.DATASETS.TEST exp_name = cfg.EXP.NAME for idx, dataset_name in enumerate(dataset_names): output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name + "_" + exp_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_davis( model, data_loader_val, iou_types=iou_types, box_only=False, device=cfg.MODEL.DEVICE, expected_results=cfg.TEST.EXPECTED_RESULTS, expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL, output_folder=output_folder, debug=cfg.TEST.DEBUG, generate_annotation=cfg.TEST.GENERATE_ANNOTATION, overlay_box=cfg.TEST.OVERLAY_BOX, matching=cfg.TEST.MATCHING, skip_computation_network=cfg.TEST.SKIP_NETWORK, select_top_predictions_flag=cfg.TEST.SELECT_TOP_PREDICTIONS, cfg=cfg ) synchronize()
def main(args): # 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( # "--eval-only", action="store_true", help="perform evaluation only" # ) # parser.add_argument( # "--no-color", action="store_true", help="disable colorful logging" # ) # parser.add_argument( # "--num-gpus", type=int, default=1, help="number of gpus per machine" # ) # parser.add_argument("--num-machines", type=int, default=1) # parser.add_argument( # "--machine-rank", # type=int, # default=0, # help="the rank of this machine (unique per machine)", # ) # port = 2 ** 15 + 2 ** 14 + hash(os.getuid()) % 2 ** 14 # parser.add_argument("--dist-url", default="tcp://127.0.0.1:{}".format(port)) # 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 = args.num_gpus args.distributed = num_gpus > 1 # args.distributed = get_world_size() > 1 args.local_rank = get_rank() % args.num_gpus if args.distributed: torch.cuda.set_device(args.local_rank) torch.distributed.init_process_group(backend="nccl", init_method="env://") # distributed = get_world_size() > 1 # args.distributed = distributed # if distributed: # args.local_rank = get_rank() % args.num_gpus print(args.config_file) 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(args.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)) tb_logger = Logger(cfg.OUTPUT_DIR, get_rank()) train(cfg, args.local_rank, args.distributed, tb_logger)