preprocess/humanparsing/mhp_extension/detectron2/projects/PointRend/train_net.py

#!/usr/bin/env python3
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved

"""
PointRend Training Script.

This script is a simplified version of the training script in detectron2/tools.
"""

import os
import torch

import detectron2.utils.comm as comm
from detectron2.checkpoint import DetectionCheckpointer
from detectron2.config import get_cfg
from detectron2.data import MetadataCatalog, build_detection_train_loader
from detectron2.engine import DefaultTrainer, default_argument_parser, default_setup, launch
from detectron2.evaluation import (
    CityscapesInstanceEvaluator,
    CityscapesSemSegEvaluator,
    COCOEvaluator,
    DatasetEvaluators,
    LVISEvaluator,
    SemSegEvaluator,
    verify_results,
)

from point_rend import SemSegDatasetMapper, add_pointrend_config


class Trainer(DefaultTrainer):
    """
    We use the "DefaultTrainer" which contains a number pre-defined logic for
    standard training workflow. They may not work for you, especially if you
    are working on a new research project. In that case you can use the cleaner
    "SimpleTrainer", or write your own training loop.
    """

    @classmethod
    def build_evaluator(cls, cfg, dataset_name, output_folder=None):
        """
        Create evaluator(s) for a given dataset.
        This uses the special metadata "evaluator_type" associated with each builtin dataset.
        For your own dataset, you can simply create an evaluator manually in your
        script and do not have to worry about the hacky if-else logic here.
        """
        if output_folder is None:
            output_folder = os.path.join(cfg.OUTPUT_DIR, "inference")
        evaluator_list = []
        evaluator_type = MetadataCatalog.get(dataset_name).evaluator_type
        if evaluator_type == "lvis":
            return LVISEvaluator(dataset_name, cfg, True, output_folder)
        if evaluator_type == "coco":
            return COCOEvaluator(dataset_name, cfg, True, output_folder)
        if evaluator_type == "sem_seg":
            return SemSegEvaluator(
                dataset_name,
                distributed=True,
                num_classes=cfg.MODEL.SEM_SEG_HEAD.NUM_CLASSES,
                ignore_label=cfg.MODEL.SEM_SEG_HEAD.IGNORE_VALUE,
                output_dir=output_folder,
            )
        if evaluator_type == "cityscapes_instance":
            assert (
                torch.cuda.device_count() >= comm.get_rank()
            ), "CityscapesEvaluator currently do not work with multiple machines."
            return CityscapesInstanceEvaluator(dataset_name)
        if evaluator_type == "cityscapes_sem_seg":
            assert (
                torch.cuda.device_count() >= comm.get_rank()
            ), "CityscapesEvaluator currently do not work with multiple machines."
            return CityscapesSemSegEvaluator(dataset_name)
        if len(evaluator_list) == 0:
            raise NotImplementedError(
                "no Evaluator for the dataset {} with the type {}".format(
                    dataset_name, evaluator_type
                )
            )
        if len(evaluator_list) == 1:
            return evaluator_list[0]
        return DatasetEvaluators(evaluator_list)

    @classmethod
    def build_train_loader(cls, cfg):
        if "SemanticSegmentor" in cfg.MODEL.META_ARCHITECTURE:
            mapper = SemSegDatasetMapper(cfg, True)
        else:
            mapper = None
        return build_detection_train_loader(cfg, mapper=mapper)


def setup(args):
    """
    Create configs and perform basic setups.
    """
    cfg = get_cfg()
    add_pointrend_config(cfg)
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.freeze()
    default_setup(cfg, args)
    return cfg


def main(args):
    cfg = setup(args)

    if args.eval_only:
        model = Trainer.build_model(cfg)
        DetectionCheckpointer(model, save_dir=cfg.OUTPUT_DIR).resume_or_load(
            cfg.MODEL.WEIGHTS, resume=args.resume
        )
        res = Trainer.test(cfg, model)
        if comm.is_main_process():
            verify_results(cfg, res)
        return res

    trainer = Trainer(cfg)
    trainer.resume_or_load(resume=args.resume)
    return trainer.train()


if __name__ == "__main__":
    args = default_argument_parser().parse_args()
    print("Command Line Args:", args)
    launch(
        main,
        args.num_gpus,
        num_machines=args.num_machines,
        machine_rank=args.machine_rank,
        dist_url=args.dist_url,
        args=(args,),
    )