Maskrcnn-benchmark 训练过程中使用TensorBoard

   继续上篇改的代码有点多,不足之处大佬指出

运行命令： 

 python tools/train_net.py --use-tensorboard --config-file experiments/cfgs/e2e_faster_rcnn_R_50_FPN_1x.yaml

1、修改maskrcnn_benchmark/config/defaults.py在最后添加

_C.TENSORBOARD_EXPERIMENT = "logs/maskrcnn-benchmark"  # tensorboard experiment location

2、修改maskrcnn_benchmark/engine/trainer.py更改如下

from maskrcnn_benchmark.utils.comm import get_world_size
#from maskrcnn_benchmark.utils.metric_logger import MetricLogger   #注释掉
.........

def do_train(
    model,
    data_loader,
    optimizer,
    scheduler,
    checkpointer,
    device,
    checkpoint_period,
    arguments,
    meters  #添加的参数
):
    logger = logging.getLogger("maskrcnn_benchmark.trainer")
    logger.info("Start training")
    #meters = MetricLogger(delimiter="  ")     #注释掉

    

3、修改maskrcnn_benchmark/utils/metric_logger.py

import time           #添加
from collections import defaultdict
from collections import deque
from datetime import datetime #添加

import torch

from .comm import is_main_process #添加

    def __str__(self):
        loss_str = []
        for name, meter in self.meters.items():
            loss_str.append(
                "{}: {:.4f} ({:.4f})".format(name, meter.median, meter.global_avg)
            )
        return self.delimiter.join(loss_str)
############添加以下代码
class TensorboardLogger(MetricLogger):
    def __init__(self,
                 log_dir,
                 start_iter=0,
                 delimiter='\t'):

        super(TensorboardLogger, self).__init__(delimiter)
        self.iteration = start_iter
        self.writer = self._get_tensorboard_writer(log_dir)

    @staticmethod
    def _get_tensorboard_writer(log_dir):
        try:
            from tensorboardX import SummaryWriter
        except ImportError:
            raise ImportError(
                'To use tensorboard please install tensorboardX '
                '[ pip install tensorflow tensorboardX ].'
            )

        if is_main_process():
            timestamp = datetime.fromtimestamp(time.time()).strftime('%Y%m%d-%H:%M')
            tb_logger = SummaryWriter('{}-{}'.format(log_dir, timestamp))
            return tb_logger
        else:
            return None

    def update(self, ** kwargs):
        super(TensorboardLogger, self).update(**kwargs)
        if self.writer:
            for k, v in kwargs.items():
                if isinstance(v, torch.Tensor):
                    v = v.item()
                assert isinstance(v, (float, int))
                self.writer.add_scalar(k, v, self.iteration)
            self.iteration += 1

4、修改tools/train_net.py

import os

import torch

from maskrcnn_benchmark.config import cfg
from maskrcnn_benchmark.data import make_data_loader
#from maskrcnn_benchmark.solver import make_lr_scheduler  #注释掉
#from maskrcnn_benchmark.solver import make_optimizer     #注释掉
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.solver import make_lr_scheduler   #添加
from maskrcnn_benchmark.solver import make_optimizer      #添加
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.metric_logger import (
    MetricLogger, TensorboardLogger)                       #添加

from maskrcnn_benchmark.utils.miscellaneous import mkdir

#def train(cfg, local_rank, distributed):   #  注释掉换成下面的定义方式
def train(cfg, local_rank, distributed, use_tensorboard=False):
    model = build_detection_model(cfg)
    device = torch.device(cfg.MODEL.DEVICE)
    model.to(device)

   checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD #在checkpoint_period  添加以下函数
    if use_tensorboard:
        meters = TensorboardLogger(
            log_dir=cfg.TENSORBOARD_EXPERIMENT,
            start_iter=arguments['iteration'],
            delimiter="  ")
    else:
        meters = MetricLogger(delimiter="  ")

    do_train(
        model,
        data_loader,
        optimizer,
        scheduler,
        checkpointer,
        device,
        checkpoint_period,
        arguments,
        meters                   #添加meters
    )

        help="Do not test the final model",
        action="store_true",
    )#添加下面的函数
    parser.add_argument(
        "--use-tensorboard",
        dest="use_tensorboard",
        help="Use tensorboardX logger (Requires tensorboardX installed)",
        action="store_true",
        default=False
    )

   # model = train(cfg, args.local_rank, args.distributed)  注释掉换成以下函数
    model = train(
        cfg=cfg,
        local_rank=args.local_rank,
        distributed=args.distributed,
        use_tensorboard=args.use_tensorboard
    )

train_net.py整体代码：

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
r"""
Basic training script for PyTorch
"""

# Set up custom environment before nearly anything else is imported
# NOTE: this should be the first import (no not reorder)
from maskrcnn_benchmark.utils.env import setup_environment  # noqa F401 isort:skip

import argparse
import os

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.solver import make_lr_scheduler
from maskrcnn_benchmark.solver import make_optimizer
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.metric_logger import (
    MetricLogger, TensorboardLogger)
from maskrcnn_benchmark.utils.miscellaneous import mkdir


#def train(cfg, local_rank, distributed):
def train(cfg, local_rank, distributed, use_tensorboard=False):
    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.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
    if use_tensorboard:
        meters = TensorboardLogger(
            log_dir=cfg.TENSORBOARD_EXPERIMENT,
            start_iter=arguments['iteration'],
            delimiter="  ")
    else:
        meters = MetricLogger(delimiter="  ")

    do_train(
        model,
        data_loader,
        optimizer,
        scheduler,
        checkpointer,
        device,
        checkpoint_period,
        arguments,
        meters
    )

    return model


def run_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",)
    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(
        "--use-tensorboard",
        dest="use_tensorboard",
        help="Use tensorboardX logger (Requires tensorboardX installed)",
        action="store_true",
        default=False
    )
    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 = train(
        cfg=cfg,
        local_rank=args.local_rank,
        distributed=args.distributed,
        use_tensorboard=args.use_tensorboard
    )
    if not args.skip_test:
        run_test(cfg, model, args.distributed)


if __name__ == "__main__":
    main()