yolov3实现之模型训练，测试，检测

前面几篇博客已经对yolov3的具体实现模块已经做了大致的讲解，基于pytorch进行模型训练，测试，检测只是对前面的模块进行组合实现，主要的还是数据的准备，加载，模型搭建，代价函数的求解。

train.py

from __future__ import division

from models import *
from utils.logger import *
from utils.utils import *
from utils.datasets import *
from utils.parse_config import *
from test import evaluate

from terminaltables import AsciiTable

import os
import sys
import time
import datetime
import argparse

import torch
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision import transforms
from torch.autograd import Variable
import torch.optim as optim

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--epochs", type=int, default=100, help="number of epochs")
    parser.add_argument("--batch_size", type=int, default=8, help="size of each image batch")
    parser.add_argument("--gradient_accumulations", type=int, default=2, help="number of gradient accums before step")
    parser.add_argument("--model_def", type=str, default="config/yolov3.cfg", help="path to model definition file")
    parser.add_argument("--data_config", type=str, default="config/coco.data", help="path to data config file")
    parser.add_argument("--pretrained_weights", type=str, help="if specified starts from checkpoint model")
    parser.add_argument("--n_cpu", type=int, default=8, help="number of cpu threads to use during batch generation")
    parser.add_argument("--img_size", type=int, default=416, help="size of each image dimension")
    parser.add_argument("--checkpoint_interval", type=int, default=1, help="interval between saving model weights")
    parser.add_argument("--evaluation_interval", type=int, default=1, help="interval evaluations on validation set")
    parser.add_argument("--compute_map", default=False, help="if True computes mAP every tenth batch")
    parser.add_argument("--multiscale_training", default=True, help="allow for multi-scale training")
    opt = parser.parse_args()
    print(opt)

    logger = Logger("logs")

    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

    os.makedirs("output", exist_ok=True)
    os.makedirs("checkpoints", exist_ok=True)

    # Get data configuration
    data_config = parse_data_config(opt.data_config)
    train_path = data_config["train"]
    valid_path = data_config["valid"]
    class_names = load_classes(data_config["names"])

    # Initiate model
    model = Darknet(opt.model_def).to(device)
    model.apply(weights_init_normal)

    # If specified we start from checkpoint
    if opt.pretrained_weights:
        if opt.pretrained_weights.endswith(".pth"):
            model.load_state_dict(torch.load(opt.pretrained_weights))
        else:
            model.load_darknet_weights(opt.pretrained_weights)

    # Get dataloader
    #加载数据
    dataset = ListDataset(train_path, augment=True, multiscale=opt.multiscale_training)
    #整合为torch批量处理格式
    dataloader = torch.utils.data.DataLoader(
        dataset,
        batch_size=opt.batch_size,
        shuffle=True,
        num_workers=opt.n_cpu,
        pin_memory=True,
        collate_fn=dataset.collate_fn,
    )

    #网络优化器
    optimizer = torch.optim.Adam(model.parameters())

    metrics = [
        "grid_size",
        "loss",
        "x",
        "y",
        "w",
        "h",
        "conf",
        "cls",
        "cls_acc",
        "recall50",
        "recall75",
        "precision",
        "conf_obj",
        "conf_noobj",
    ]

    #迭代实现模型训练
    for epoch in range(opt.epochs):
        model.train()
        start_time = time.time()
        for batch_i, (_, imgs, targets) in enumerate(dataloader):
            batches_done = len(dataloader) * epoch + batch_i