CenterNet代码之总体结构

CenterNet（Objects as points）开源代码：https://github.com/xingyizhou/CenterNet

代码结构：

CenterNer-master
    |
    |--data  # 数据存放
    |
    |--models   # 训练好的模型
    |
    |--src   # 源码

我们主要看源码结构： 

src # 源码结构
  |
  |-- lib    # 本项目的lib
  |
  |-- tools  # 使用的工具
  |
  |-- _init_path.py  # 将lib加入sys.path, 使得调用库的第一顺位目录为本项目的lib
  |
  |-- demo.py # 给出的方便实用的demo
  |
  |-- main.py # 整体流程
  |
  |-- test.py # 显然，是test

lib结构：

lib  # 本部分是作者自己写的模块
  | 
  |-- datasets  # 构建dataset
  |
  |-- detectors # 构建detector
  | 
  |-- external  # 引入的外部库，如nms
  |
  |-- models    # 网络模型
  |
  |-- trains    # 训练过程
  | 
  |-- utils     # 工具：如image_augumentation
  |
  |-- logger.py # 日志记录
  |
  |-- opt.py    # 定义和处理命令行参数

tools结构

tools  # 大部分是各数据集的验证模块以及处理工具
  |
  |-- kitti_aval  # kitti数据集的验证
  |
  |-- voc_eval_lib 
  |
  |-- _init_path # 将lib加入sys.path
  |
  |-- calc_coco_overlap.py # 计算IoU相关
  |
  |-- convert_hourglass_weight.py
  |
  |-- convert_kitti_to_coco.py
  |
  |-- eval_coco.py
  |
  |-- eval_coco_hp.py
  |
  |-- merge_pascal_json.py
  |
  |-- reval.py 
  |
  |-- vis_pred.py 

 

我们跟着main.py熟悉整个CenterNet的运行逻辑：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import _init_paths

import os

import torch
import torch.utils.data
from opts import opts
from models.model import create_model, load_model, save_model
from models.data_parallel import DataParallel
from logger import Logger
from datasets.dataset_factory import get_dataset
from trains.train_factory import train_factory


def main(opt):
    torch.manual_seed(opt.seed)
    torch.backends.cudnn.benchmark = not opt.not_cuda_benchmark and not opt.test
    Dataset = get_dataset(opt.dataset, opt.task)
    opt = opts().update_dataset_info_and_set_heads(opt, Dataset)
    print(opt)

    logger = Logger(opt)

    os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpus_str
    opt.device = torch.device('cuda' if opt.gpus[0] >= 0 else 'cpu')

    print('Creating model...')
    model = create_model(opt.arch, opt.heads, opt.head_conv)
    optimizer = torch.optim.Adam(model.parameters(), opt.lr)
    start_epoch = 0
    if opt.load_model != '':
        model, optimizer, start_epoch = load_model(
            model, opt.load_model, optimizer, opt.resume, opt.lr, opt.lr_step)

    Trainer = train_factory[opt.task]
    trainer = Trainer(opt, model, optimizer)
    trainer.set_device(opt.gpus, opt.chunk_sizes, opt.device)

    print('Setting up data...')
    val_loader = torch.utils.data.DataLoader(
        Dataset(opt, 'val'),
        batch_size=1,
        shuffle=False,
        num_workers=1,
        pin_memory=True
    )

    if opt.test:
        _, preds = trainer.val(0, val_loader)
        val_loader.dataset.run_eval(preds, opt.save_dir)
        return

    train_loader = torch.utils.data.DataLoader(
        Dataset(opt, 'train'),
        batch_size=opt.batch_size,
        shuffle=True,
        num_workers=opt.num_workers,
        pin_memory=True,
        drop_last=True
    )

    print('Starting training...')
    best = 1e10
    for epoch in range(start_epoch + 1, opt.num_epochs + 1):
        mark = epoch if opt.save_all else 'last'
        log_dict_train, _ = trainer.train(epoch, train_loader)
        logger.write('epoch: {} |'.format(epoch))
        for k, v in log_dict_train.items():
            logger.scalar_summary('train_{}'.format(k), v, epoch)
            logger.write('{} {:8f} | '.format(k, v))
        if opt.val_intervals > 0 and epoch % opt.val_intervals == 0:
            save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(mark)),
                       epoch, model, optimizer)
            with torch.no_grad():
                log_dict_val, preds = trainer.val(epoch, val_loader)
            for k, v in log_dict_val.items():
                logger.scalar_summary('val_{}'.format(k), v, epoch)
                logger.write('{} {:8f} | '.format(k, v))
            if log_dict_val[opt.metric] < best:
                best = log_dict_val[opt.metric]
                save_model(os.path.join(opt.save_dir, 'model_best.pth'),
                           epoch, model)
        else:
            save_model(os.path.join(opt.save_dir, 'model_last.pth'),
                       epoch, model, optimizer)
        logger.write('\n')
        if epoch in opt.lr_step:
            save_model(os.path.join(opt.save_dir, 'model_{}.pth'.format(epoch)),
                       epoch, model, optimizer)
            lr = opt.lr * (0.1 ** (opt.lr_step.index(epoch) + 1))
            print('Drop LR to', lr)
            for param_group in optimizer.param_groups:
                param_group['lr'] = lr
    logger.close()


if __name__ == '__main__':
    opt = opts().parse()
    main(opt)