481 lines
25 KiB
Python
481 lines
25 KiB
Python
# -------------------------------------#
|
||
# 对数据集进行训练
|
||
# -------------------------------------#
|
||
import datetime
|
||
import os
|
||
import random
|
||
|
||
import numpy as np
|
||
import torch
|
||
import torch.backends.cudnn as cudnn
|
||
import torch.distributed as dist
|
||
import torch.nn as nn
|
||
import torch.optim as optim
|
||
from torch.utils.data import DataLoader
|
||
|
||
from data.dataloader_for_IRSTD_UAV import seqDataset, dataset_collate
|
||
from model.TDCNet.TDCNetwork import TDCNetwork
|
||
from model.nets.yolo_training import (ModelEMA, YOLOLoss, get_lr_scheduler, set_optimizer_lr, weights_init)
|
||
from utils.callbacks import EvalCallback, LossHistory
|
||
from utils.utils import get_classes, show_config
|
||
from utils.utils_fit import fit_one_epoch
|
||
|
||
if __name__ == "__main__":
|
||
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
|
||
# ---------------------------------#
|
||
# num_frame 输入帧数
|
||
# ---------------------------------#
|
||
num_frame = 5
|
||
# ---------------------------------#
|
||
# Cuda 是否使用Cuda
|
||
# 没有GPU可以设置成False
|
||
# ---------------------------------#
|
||
Cuda = True
|
||
# ---------------------------------------------------------------------#
|
||
# distributed 用于指定是否使用单机多卡分布式运行
|
||
# 终端指令仅支持Ubuntu。CUDA_VISIBLE_DEVICES用于在Ubuntu下指定显卡。
|
||
# Windows系统下默认使用DP模式调用所有显卡，不支持DDP。
|
||
# DP模式：
|
||
# 设置 distributed = False
|
||
# 在终端中输入 CUDA_VISIBLE_DEVICES=0,1 python train.py
|
||
# DDP模式：
|
||
# 设置 distributed = True
|
||
# 在终端中输入 CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 train.py
|
||
# ---------------------------------------------------------------------#
|
||
distributed = False
|
||
# ---------------------------------------------------------------------#
|
||
# sync_bn 是否使用sync_bn，DDP模式多卡可用
|
||
# ---------------------------------------------------------------------#
|
||
sync_bn = False
|
||
# ---------------------------------------------------------------------#
|
||
# fp16 是否使用混合精度训练
|
||
# 可减少约一半的显存、需要pytorch1.7.1以上
|
||
# ---------------------------------------------------------------------#
|
||
fp16 = False
|
||
# ---------------------------------------------------------------------#
|
||
# classes_path 指向model_data下的txt，与自己训练的数据集相关
|
||
# 训练前一定要修改classes_path，使其对应自己的数据集
|
||
# ---------------------------------------------------------------------#
|
||
classes_path = 'model_data/classes.txt'
|
||
model_path = ''
|
||
input_shape = [640, 640]
|
||
# ----------------------------------------------------------------------------------------------------------------------------#
|
||
# 训练分为两个阶段，分别是冻结阶段和解冻阶段。设置冻结阶段是为了满足机器性能不足的同学的训练需求。
|
||
# 冻结训练需要的显存较小，显卡非常差的情况下，可设置Freeze_Epoch等于UnFreeze_Epoch，Freeze_Train = True，此时仅仅进行冻结训练。
|
||
#
|
||
# 在此提供若干参数设置建议，各位训练者根据自己的需求进行灵活调整：
|
||
# （一）从整个模型的预训练权重开始训练：
|
||
# Adam：
|
||
# Init_Epoch = 0，Freeze_Epoch = 50，UnFreeze_Epoch = 100，Freeze_Train = True，optimizer_type = 'adam'，Init_lr = 1e-3，weight_decay = 0。（冻结）
|
||
# Init_Epoch = 0，UnFreeze_Epoch = 100，Freeze_Train = False，optimizer_type = 'adam'，Init_lr = 1e-3，weight_decay = 0。（不冻结）
|
||
# SGD：
|
||
# Init_Epoch = 0，Freeze_Epoch = 50，UnFreeze_Epoch = 300，Freeze_Train = True，optimizer_type = 'sgd'，Init_lr = 1e-2，weight_decay = 5e-4。（冻结）
|
||
# Init_Epoch = 0，UnFreeze_Epoch = 300，Freeze_Train = False，optimizer_type = 'sgd'，Init_lr = 1e-2，weight_decay = 5e-4。（不冻结）
|
||
# 其中：UnFreeze_Epoch可以在100-300之间调整。
|
||
# （二）从0开始训练：
|
||
# Init_Epoch = 0，UnFreeze_Epoch >= 300，Unfreeze_batch_size >= 16，Freeze_Train = False（不冻结训练）
|
||
# 其中：UnFreeze_Epoch尽量不小于300。optimizer_type = 'sgd'，Init_lr = 1e-2，mosaic = True。
|
||
# （三）batch_size的设置：
|
||
# 在显卡能够接受的范围内，以大为好。显存不足与数据集大小无关，提示显存不足（OOM或者CUDA out of memory）请调小batch_size。
|
||
# 受到BatchNorm层影响，batch_size最小为2，不能为1。
|
||
# 正常情况下Freeze_batch_size建议为Unfreeze_batch_size的1-2倍。不建议设置的差距过大，因为关系到学习率的自动调整。
|
||
# ----------------------------------------------------------------------------------------------------------------------------#
|
||
# ------------------------------------------------------------------#
|
||
# 冻结阶段训练参数
|
||
# 此时模型的主干被冻结了，特征提取网络不发生改变
|
||
# 占用的显存较小，仅对网络进行微调
|
||
# Init_Epoch 模型当前开始的训练世代，其值可以大于Freeze_Epoch，如设置：
|
||
# Init_Epoch = 60、Freeze_Epoch = 50、UnFreeze_Epoch = 100
|
||
# 会跳过冻结阶段，直接从60代开始，并调整对应的学习率。
|
||
# （断点续练时使用）
|
||
# Freeze_Epoch 模型冻结训练的Freeze_Epoch
|
||
# (当Freeze_Train=False时失效)
|
||
# Freeze_batch_size 模型冻结训练的batch_size
|
||
# (当Freeze_Train=False时失效)
|
||
# ------------------------------------------------------------------#
|
||
Init_Epoch = 0
|
||
Freeze_Epoch = 100
|
||
Freeze_batch_size = 4
|
||
# ------------------------------------------------------------------#
|
||
# 解冻阶段训练参数
|
||
# 此时模型的主干不被冻结了，特征提取网络会发生改变
|
||
# 占用的显存较大，网络所有的参数都会发生改变
|
||
# UnFreeze_Epoch 模型总共训练的epoch
|
||
# SGD需要更长的时间收敛，因此设置较大的UnFreeze_Epoch
|
||
# Adam可以使用相对较小的UnFreeze_Epoch
|
||
# Unfreeze_batch_size 模型在解冻后的batch_size
|
||
# ------------------------------------------------------------------#
|
||
UnFreeze_Epoch = 100
|
||
Unfreeze_batch_size = 4
|
||
# ------------------------------------------------------------------#
|
||
# Freeze_Train 是否进行冻结训练
|
||
# 默认先冻结主干训练后解冻训练。
|
||
# ------------------------------------------------------------------#
|
||
Freeze_Train = False
|
||
|
||
# ------------------------------------------------------------------#
|
||
# 其它训练参数：学习率、优化器、学习率下降有关
|
||
# ------------------------------------------------------------------#
|
||
# ------------------------------------------------------------------#
|
||
# Init_lr 模型的最大学习率
|
||
# Min_lr 模型的最小学习率，默认为最大学习率的0.01
|
||
# ------------------------------------------------------------------#
|
||
Init_lr = 1e-3
|
||
Min_lr = Init_lr * 0.01
|
||
# ------------------------------------------------------------------#
|
||
# optimizer_type 使用到的优化器种类，可选的有adam、sgd
|
||
# 当使用Adam优化器时建议设置 Init_lr=1e-3
|
||
# 当使用SGD优化器时建议设置 Init_lr=1e-2
|
||
# momentum 优化器内部使用到的momentum参数
|
||
# weight_decay 权值衰减，可防止过拟合
|
||
# adam会导致weight_decay错误，使用adam时建议设置为0。
|
||
# ------------------------------------------------------------------#
|
||
optimizer_type = "adam"
|
||
momentum = 0.937
|
||
weight_decay = 1e-4
|
||
# ------------------------------------------------------------------#
|
||
# lr_decay_type 使用到的学习率下降方式，可选的有step、cos
|
||
# ------------------------------------------------------------------#
|
||
lr_decay_type = "cos"
|
||
# ------------------------------------------------------------------#
|
||
# save_period 多少个epoch保存一次权值
|
||
# ------------------------------------------------------------------#
|
||
save_period = 10
|
||
# ------------------------------------------------------------------#
|
||
# save_dir 权值与日志文件保存的文件夹
|
||
# ------------------------------------------------------------------#
|
||
save_dir = f'logs/TDCNet_epoch_{UnFreeze_Epoch}_batch_{Unfreeze_batch_size}_optim_{optimizer_type}_lr_{Init_lr}_T_{num_frame}'
|
||
# ------------------------------------------------------------------#
|
||
# eval_flag 是否在训练时进行评估，评估对象为验证集
|
||
# 安装pycocotools库后，评估体验更佳。
|
||
# eval_period 代表多少个epoch评估一次，不建议频繁的评估
|
||
# 评估需要消耗较多的时间，频繁评估会导致训练非常慢
|
||
# 此处获得的mAP会与get_map.py获得的会有所不同，原因有二：
|
||
# （一）此处获得的mAP为验证集的mAP。
|
||
# （二）此处设置评估参数较为保守，目的是加快评估速度。
|
||
# ------------------------------------------------------------------#
|
||
eval_flag = True
|
||
eval_period = 200
|
||
# ------------------------------------------------------------------#
|
||
# num_workers 用于设置是否使用多线程读取数据
|
||
# 开启后会加快数据读取速度，但是会占用更多内存
|
||
# 内存较小的电脑可以设置为2或者0
|
||
# ------------------------------------------------------------------#
|
||
num_workers = 8
|
||
|
||
# ----------------------------------------------------#
|
||
# 获得图片路径和标签
|
||
# ----------------------------------------------------#
|
||
|
||
DATA_PATH = "/Dataset/IRSTD-UAV/"
|
||
train_annotation_path = "/Dataset/IRSTD-UAV/train.txt"
|
||
val_annotation_path = "/Dataset/IRSTD-UAV/val.txt"
|
||
|
||
# ------------------------------------------------------#
|
||
# 设置用到的显卡
|
||
# ------------------------------------------------------#
|
||
ngpus_per_node = torch.cuda.device_count()
|
||
if distributed:
|
||
dist.init_process_group(backend="nccl")
|
||
local_rank = int(os.environ["LOCAL_RANK"])
|
||
rank = int(os.environ["RANK"])
|
||
device = torch.device("cuda", local_rank)
|
||
if local_rank == 0:
|
||
print(f"[{os.getpid()}] (rank = {rank}, local_rank = {local_rank}) training...")
|
||
print("Gpu Device Count : ", ngpus_per_node)
|
||
else:
|
||
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
||
local_rank = 0
|
||
rank = 0
|
||
|
||
# ------------------------------------------------------#
|
||
# 设置随机种子
|
||
# ------------------------------------------------------#
|
||
seed = 42
|
||
torch.manual_seed(seed)
|
||
torch.cuda.manual_seed_all(seed)
|
||
np.random.seed(seed)
|
||
random.seed(seed)
|
||
torch.backends.cudnn.deterministic = True
|
||
|
||
class_names, num_classes = get_classes(classes_path)
|
||
|
||
model = TDCNetwork(num_classes=1, num_frame=num_frame)
|
||
|
||
weights_init(model)
|
||
if model_path != '':
|
||
if local_rank == 0:
|
||
print('Load weights {}.'.format(model_path))
|
||
|
||
# ------------------------------------------------------#
|
||
# 根据预训练权重的Key和模型的Key进行加载
|
||
# ------------------------------------------------------#
|
||
model_dict = model.state_dict()
|
||
# pdb.set_trace()
|
||
pretrained_dict = torch.load(model_path, map_location=device)
|
||
load_key, no_load_key, temp_dict = [], [], {}
|
||
for k, v in pretrained_dict.items():
|
||
if k in model_dict.keys() and np.shape(model_dict[k]) == np.shape(v):
|
||
temp_dict[k] = v
|
||
load_key.append(k)
|
||
else:
|
||
no_load_key.append(k)
|
||
model_dict.update(temp_dict)
|
||
model.load_state_dict(model_dict)
|
||
# ------------------------------------------------------#
|
||
# 显示没有匹配上的Key
|
||
# ------------------------------------------------------#
|
||
if local_rank == 0:
|
||
print("\nSuccessful Load Key:", str(load_key)[:500], "……\nSuccessful Load Key Num:", len(load_key))
|
||
print("\nFail To Load Key:", str(no_load_key)[:500], "……\nFail To Load Key num:", len(no_load_key))
|
||
print("\n\033[1;33;44m温馨提示，head部分没有载入是正常现象，Backbone部分没有载入是错误的。\033[0m")
|
||
|
||
# ----------------------#
|
||
# 获得损失函数
|
||
# ----------------------#
|
||
|
||
yolo_loss = YOLOLoss(num_classes, fp16, strides=[8])
|
||
# ----------------------#
|
||
# 记录Loss
|
||
# ----------------------#
|
||
if local_rank == 0:
|
||
time_str = datetime.datetime.strftime(datetime.datetime.now(), '%Y_%m_%d_%H_%M_%S')
|
||
log_dir = os.path.join(save_dir, "loss_" + str(time_str))
|
||
|
||
loss_history = LossHistory(log_dir, model, input_shape=input_shape)
|
||
|
||
# pdb.set_trace()
|
||
else:
|
||
loss_history = None
|
||
|
||
# ------------------------------------------------------------------#
|
||
# torch 1.2不支持amp，建议使用torch 1.7.1及以上正确使用fp16
|
||
# 因此torch1.2这里显示"could not be resolve"
|
||
# ------------------------------------------------------------------#
|
||
if fp16:
|
||
from torch.cuda.amp import GradScaler as GradScaler
|
||
|
||
scaler = GradScaler()
|
||
else:
|
||
scaler = None
|
||
|
||
model_train = model.train()
|
||
# ----------------------------#
|
||
# 多卡同步Bn
|
||
# ----------------------------#
|
||
if sync_bn and ngpus_per_node > 1 and distributed:
|
||
model_train = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model_train)
|
||
elif sync_bn:
|
||
print("Sync_bn is not support in one gpu or not distributed.")
|
||
|
||
if Cuda:
|
||
if distributed:
|
||
# ----------------------------#
|
||
# 多卡平行运行
|
||
# ----------------------------#
|
||
model_train = model_train.cuda(local_rank)
|
||
model_train = torch.nn.parallel.DistributedDataParallel(model_train, device_ids=[local_rank], find_unused_parameters=True)
|
||
else:
|
||
model_train = torch.nn.DataParallel(model)
|
||
cudnn.benchmark = True
|
||
model_train = model_train.cuda()
|
||
|
||
# ----------------------------#
|
||
# 权值平滑
|
||
# ----------------------------#
|
||
# pdb.set_trace()
|
||
ema = ModelEMA(model_train)
|
||
|
||
# ---------------------------#
|
||
# 读取数据集对应的txt
|
||
# ---------------------------#
|
||
with open(train_annotation_path, encoding='utf-8') as f:
|
||
train_lines = f.readlines()
|
||
with open(val_annotation_path, encoding='utf-8') as f:
|
||
val_lines = f.readlines()
|
||
num_train = len(train_lines)
|
||
num_val = len(val_lines)
|
||
|
||
if local_rank == 0:
|
||
show_config(
|
||
classes_path=classes_path, model_path=model_path, input_shape=input_shape, \
|
||
Init_Epoch=Init_Epoch, Freeze_Epoch=Freeze_Epoch, UnFreeze_Epoch=UnFreeze_Epoch, Freeze_batch_size=Freeze_batch_size, Unfreeze_batch_size=Unfreeze_batch_size, Freeze_Train=Freeze_Train, \
|
||
Init_lr=Init_lr, Min_lr=Min_lr, optimizer_type=optimizer_type, momentum=momentum, lr_decay_type=lr_decay_type, \
|
||
save_period=save_period, save_dir=log_dir, num_workers=num_workers, num_train=num_train, num_val=num_val
|
||
)
|
||
# ---------------------------------------------------------#
|
||
# 总训练世代指的是遍历全部数据的总次数
|
||
# 总训练步长指的是梯度下降的总次数
|
||
# 每个训练世代包含若干训练步长，每个训练步长进行一次梯度下降。
|
||
# 此处仅建议最低训练世代，上不封顶，计算时只考虑了解冻部分
|
||
# ----------------------------------------------------------#
|
||
wanted_step = 5e4 if optimizer_type == "sgd" else 1.5e4
|
||
total_step = num_train // Unfreeze_batch_size * UnFreeze_Epoch
|
||
if total_step <= wanted_step:
|
||
if num_train // Unfreeze_batch_size == 0:
|
||
raise ValueError('数据集过小，无法进行训练，请扩充数据集。')
|
||
wanted_epoch = wanted_step // (num_train // Unfreeze_batch_size) + 1
|
||
print("\n\033[1;33;44m[Warning] 使用%s优化器时，建议将训练总步长设置到%d以上。\033[0m" % (optimizer_type, wanted_step))
|
||
print("\033[1;33;44m[Warning] 本次运行的总训练数据量为%d，Unfreeze_batch_size为%d，共训练%d个Epoch，计算出总训练步长为%d。\033[0m" % (num_train, Unfreeze_batch_size, UnFreeze_Epoch, total_step))
|
||
print("\033[1;33;44m[Warning] 由于总训练步长为%d，小于建议总步长%d，建议设置总世代为%d。\033[0m" % (total_step, wanted_step, wanted_epoch))
|
||
|
||
# ------------------------------------------------------#
|
||
# 主干特征提取网络特征通用，冻结训练可以加快训练速度
|
||
# 也可以在训练初期防止权值被破坏。
|
||
# Init_Epoch为起始世代
|
||
# Freeze_Epoch为冻结训练的世代
|
||
# UnFreeze_Epoch总训练世代
|
||
# 提示OOM或者显存不足请调小Batch_size
|
||
# ------------------------------------------------------#
|
||
if True:
|
||
UnFreeze_flag = False
|
||
# ------------------------------------#
|
||
# 冻结一定部分训练
|
||
# ------------------------------------#
|
||
if Freeze_Train:
|
||
for param in model.backbone.parameters():
|
||
param.requires_grad = False
|
||
for param in model.backbone_3d.parameters():
|
||
param.requires_grad = False
|
||
|
||
# -------------------------------------------------------------------#
|
||
# 如果不冻结训练的话，直接设置batch_size为Unfreeze_batch_size
|
||
# -------------------------------------------------------------------#
|
||
batch_size = Freeze_batch_size if Freeze_Train else Unfreeze_batch_size
|
||
|
||
# -------------------------------------------------------------------#
|
||
# 判断当前batch_size，自适应调整学习率
|
||
# -------------------------------------------------------------------#
|
||
nbs = 64
|
||
lr_limit_max = 1e-3 if optimizer_type == 'adam' else 5e-2
|
||
lr_limit_min = 1e-5 if optimizer_type == 'adam' else 5e-4
|
||
Init_lr_fit = min(max(batch_size / nbs * Init_lr, lr_limit_min), lr_limit_max)
|
||
Min_lr_fit = min(max(batch_size / nbs * Min_lr, lr_limit_min * 1e-2), lr_limit_max * 1e-2)
|
||
|
||
# ---------------------------------------#
|
||
# 根据optimizer_type选择优化器
|
||
# ---------------------------------------#
|
||
pg0, pg1, pg2 = [], [], []
|
||
for k, v in model.named_modules():
|
||
if hasattr(v, "bias") and isinstance(v.bias, nn.Parameter):
|
||
pg2.append(v.bias)
|
||
if isinstance(v, nn.BatchNorm2d) or "bn" in k:
|
||
pg0.append(v.weight)
|
||
elif hasattr(v, "weight") and isinstance(v.weight, nn.Parameter):
|
||
pg1.append(v.weight)
|
||
optimizer = {
|
||
'adam': optim.Adam(pg0, Init_lr_fit, betas=(momentum, 0.999)),
|
||
'sgd': optim.SGD(pg0, Init_lr_fit, momentum=momentum, nesterov=True)
|
||
}[optimizer_type]
|
||
optimizer.add_param_group({"params": pg1, "weight_decay": weight_decay})
|
||
optimizer.add_param_group({"params": pg2})
|
||
|
||
# ---------------------------------------#
|
||
# 获得学习率下降的公式
|
||
# ---------------------------------------#
|
||
lr_scheduler_func = get_lr_scheduler(lr_decay_type, Init_lr_fit, Min_lr_fit, UnFreeze_Epoch)
|
||
|
||
# ---------------------------------------#
|
||
# 判断每一个世代的长度
|
||
# ---------------------------------------#
|
||
epoch_step = num_train // batch_size
|
||
epoch_step_val = num_val // batch_size
|
||
|
||
if epoch_step == 0 or epoch_step_val == 0:
|
||
raise ValueError("数据集过小，无法继续进行训练，请扩充数据集。")
|
||
|
||
if ema:
|
||
ema.updates = epoch_step * Init_Epoch
|
||
|
||
train_dataset = seqDataset(train_annotation_path, input_shape[0], num_frame, 'train') # 5
|
||
val_dataset = seqDataset(val_annotation_path, input_shape[0], num_frame, 'val') # 5
|
||
|
||
if distributed:
|
||
train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset, shuffle=True, )
|
||
val_sampler = torch.utils.data.distributed.DistributedSampler(val_dataset, shuffle=False, )
|
||
batch_size = batch_size // ngpus_per_node
|
||
shuffle = False
|
||
else:
|
||
train_sampler = None
|
||
val_sampler = None
|
||
shuffle = True
|
||
|
||
gen = DataLoader(train_dataset, shuffle=shuffle, batch_size=batch_size, num_workers=num_workers, pin_memory=True,
|
||
drop_last=True, collate_fn=dataset_collate, sampler=train_sampler)
|
||
gen_val = DataLoader(val_dataset, shuffle=shuffle, batch_size=batch_size, num_workers=num_workers, pin_memory=True,
|
||
drop_last=True, collate_fn=dataset_collate, sampler=val_sampler)
|
||
|
||
# ----------------------#
|
||
# 记录eval的map曲线
|
||
# ----------------------#
|
||
if local_rank == 0:
|
||
eval_callback = EvalCallback(model, input_shape, class_names, num_classes, val_lines, log_dir, Cuda, \
|
||
eval_flag=eval_flag, period=eval_period)
|
||
else:
|
||
eval_callback = None
|
||
|
||
# ---------------------------------------#
|
||
# 开始模型训练
|
||
# ---------------------------------------#
|
||
for epoch in range(Init_Epoch, UnFreeze_Epoch):
|
||
# ---------------------------------------#
|
||
# 如果模型有冻结学习部分
|
||
# 则解冻，并设置参数
|
||
# ---------------------------------------#
|
||
if epoch >= Freeze_Epoch and not UnFreeze_flag and Freeze_Train:
|
||
batch_size = Unfreeze_batch_size
|
||
|
||
# -------------------------------------------------------------------#
|
||
# 判断当前batch_size，自适应调整学习率
|
||
# -------------------------------------------------------------------#
|
||
nbs = 64
|
||
lr_limit_max = 1e-3 if optimizer_type == 'adam' else 5e-2
|
||
lr_limit_min = 1e-5 if optimizer_type == 'adam' else 5e-4
|
||
Init_lr_fit = min(max(batch_size / nbs * Init_lr, lr_limit_min), lr_limit_max)
|
||
Min_lr_fit = min(max(batch_size / nbs * Min_lr, lr_limit_min * 1e-2), lr_limit_max * 1e-2)
|
||
# ---------------------------------------#
|
||
# 获得学习率下降的公式
|
||
# ---------------------------------------#
|
||
lr_scheduler_func = get_lr_scheduler(lr_decay_type, Init_lr_fit, Min_lr_fit, UnFreeze_Epoch)
|
||
|
||
for param in model.backbone.parameters():
|
||
param.requires_grad = True
|
||
for param in model.backbone_3d.parameters():
|
||
param.requires_grad = True
|
||
|
||
epoch_step = num_train // batch_size
|
||
epoch_step_val = num_val // batch_size
|
||
|
||
if epoch_step == 0 or epoch_step_val == 0:
|
||
raise ValueError("数据集过小，无法继续进行训练，请扩充数据集。")
|
||
|
||
if distributed:
|
||
batch_size = batch_size // ngpus_per_node
|
||
|
||
if ema:
|
||
ema.updates = epoch_step * epoch
|
||
|
||
gen = DataLoader(train_dataset, shuffle=shuffle, batch_size=batch_size, num_workers=num_workers, pin_memory=True,
|
||
drop_last=True, collate_fn=dataset_collate, sampler=train_sampler)
|
||
gen_val = DataLoader(val_dataset, shuffle=shuffle, batch_size=batch_size, num_workers=num_workers, pin_memory=True,
|
||
drop_last=True, collate_fn=dataset_collate, sampler=val_sampler)
|
||
|
||
UnFreeze_flag = True
|
||
|
||
gen.dataset.epoch_now = epoch
|
||
gen_val.dataset.epoch_now = epoch
|
||
|
||
if distributed:
|
||
train_sampler.set_epoch(epoch)
|
||
|
||
set_optimizer_lr(optimizer, lr_scheduler_func, epoch)
|
||
# pdb.set_trace()
|
||
|
||
fit_one_epoch(model_train, model, ema, yolo_loss, loss_history, eval_callback, optimizer, epoch, epoch_step, epoch_step_val, gen, gen_val, UnFreeze_Epoch, Cuda, fp16, scaler, save_period, log_dir, local_rank)
|
||
|
||
if distributed:
|
||
dist.barrier()
|
||
|
||
if local_rank == 0:
|
||
loss_history.writer.close()
|