main_detection.py

#!/usr/bin/env python

# Copyright IBM All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0

"""
A main training script.

Mostly copy-paste from https://github.com/facebookresearch/detectron2/blob/master/tools/train_net.py
"""

import logging
import os
from collections import OrderedDict
import torch

import detectron2.utils.comm as comm
from detectron2.checkpoint import DetectionCheckpointer
from detectron2.config import get_cfg
from detectron2.data import MetadataCatalog
from detectron2.engine import DefaultTrainer, default_argument_parser, default_setup, hooks, launch
from detectron2.evaluation import (
    CityscapesInstanceEvaluator,
    CityscapesSemSegEvaluator,
    COCOEvaluator,
    COCOPanopticEvaluator,
    DatasetEvaluators,
    LVISEvaluator,
    PascalVOCDetectionEvaluator,
    SemSegEvaluator,
    verify_results,
)
from detectron2.modeling import GeneralizedRCNNWithTTA
from detectron2.solver.build import get_default_optimizer_params, maybe_add_gradient_clipping

import regionvit
from detection.detector_wrapper import build_regionvit_backbone, build_retinanet_regionvit_fpn_backbone

from detection.config import add_config


class Trainer(DefaultTrainer):
    """
    We use the "DefaultTrainer" which contains pre-defined default 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 write your
    own training loop. You can use "tools/plain_train_net.py" as an example.
    """

    @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 in ["sem_seg", "coco_panoptic_seg"]:
            evaluator_list.append(
                SemSegEvaluator(
                    dataset_name,
                    distributed=True,
                    output_dir=output_folder,
                )
            )
        if evaluator_type in ["coco", "coco_panoptic_seg"]:
            evaluator_list.append(COCOEvaluator(dataset_name, output_dir=output_folder))
        if evaluator_type == "coco_panoptic_seg":
            evaluator_list.append(COCOPanopticEvaluator(dataset_name, 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)
        elif evaluator_type == "pascal_voc":
            return PascalVOCDetectionEvaluator(dataset_name)
        elif evaluator_type == "lvis":
            return LVISEvaluator(dataset_name, output_dir=output_folder)
        if len(evaluator_list) == 0:
            raise NotImplementedError(
                "no Evaluator for the dataset {} with the type {}".format(
                    dataset_name, evaluator_type
                )
            )
        elif len(evaluator_list) == 1:
            return evaluator_list[0]
        return DatasetEvaluators(evaluator_list)

    @classmethod
    def test_with_TTA(cls, cfg, model):
        logger = logging.getLogger("detectron2.trainer")
        # In the end of training, run an evaluation with TTA
        # Only support some R-CNN models.
        logger.info("Running inference with test-time augmentation ...")
        model = GeneralizedRCNNWithTTA(cfg, model)
        evaluators = [
            cls.build_evaluator(
                cfg, name, output_folder=os.path.join(cfg.OUTPUT_DIR, "inference_TTA")
            )
            for name in cfg.DATASETS.TEST
        ]
        res = cls.test(cfg, model, evaluators)
        res = OrderedDict({k + "_TTA": v for k, v in res.items()})
        return res

    @classmethod
    def build_optimizer(cls, cfg, model):
        """
        Returns:
            torch.optim.Optimizer:

        It now calls :func:`detectron2.solver.build_optimizer`.
        Overwrite it if you'd like a different optimizer.
        """

        params = get_default_optimizer_params(
            model,
            base_lr=cfg.SOLVER.BASE_LR,
            weight_decay_norm=cfg.SOLVER.WEIGHT_DECAY_NORM,
            bias_lr_factor=cfg.SOLVER.BIAS_LR_FACTOR,
            weight_decay_bias=cfg.SOLVER.WEIGHT_DECAY_BIAS,
        )

        if cfg.SOLVER.OPTIMIZER == 'SGD':
            return maybe_add_gradient_clipping(cfg, torch.optim.SGD)(
                params,
                lr=cfg.SOLVER.BASE_LR,
                momentum=cfg.SOLVER.MOMENTUM,
                nesterov=cfg.SOLVER.NESTEROV,
                weight_decay=cfg.SOLVER.WEIGHT_DECAY,
            )
        elif cfg.SOLVER.OPTIMIZER == 'ADAMW':

            """
                Build an optimizer from config.
                """
            return maybe_add_gradient_clipping(cfg, torch.optim.AdamW)(
                params,
                lr=cfg.SOLVER.BASE_LR,
                weight_decay=cfg.SOLVER.WEIGHT_DECAY,
            )


def setup(args):
    """
    Create configs and perform basic setups.
    """
    cfg = get_cfg()
    add_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 cfg.TEST.AUG.ENABLED:
            res.update(Trainer.test_with_TTA(cfg, model))
        if comm.is_main_process():
            verify_results(cfg, res)
        return res

    """
    If you'd like to do anything fancier than the standard training logic,
    consider writing your own training loop (see plain_train_net.py) or
    subclassing the trainer.
    """
    trainer = Trainer(cfg)
    trainer.resume_or_load(resume=args.resume)
    if cfg.TEST.AUG.ENABLED:
        trainer.register_hooks(
            [hooks.EvalHook(0, lambda: trainer.test_with_TTA(cfg, trainer.model))]
        )
    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,),
    )