YOLOv8创新改进专栏介绍

# coding:utf-8

import os
import random
import argparse

parser = argparse.ArgumentParser()
#xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='Annotations', type=str, help='input xml label path')
#数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()

trainval_percent = 0.9
train_percent = 0.8
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
    os.makedirs(txtsavepath)

num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)

file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')

for i in list_index:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        file_trainval.write(name)
        if i in train:
            file_train.write(name)
        else:
            file_val.write(name)
    else:
        file_test.write(name)

file_trainval.close()
file_train.close()
file_val.close()
file_test.close()

# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd

sets = ['trainval', 'test']
classes = ["Target"]   # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)

def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return x, y, w, h

def convert_annotation(image_id):
    in_file = open('Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('labels/%s.txt' % (image_id), 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        #difficult = obj.find('Difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()
for image_set in sets:
    if not os.path.exists('labels/'):
        os.makedirs('labels/')
    image_ids = open('ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/images/%s.png\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

# Ultralytics YOLO 🚀, GPL-3.0 license
# Default training settings and hyperparameters for medium-augmentation COCO training

task: detect  # YOLO task, i.e. detect, segment, classify, pose
mode: train  # YOLO mode, i.e. train, val, predict, export, track, benchmark

# Train settings -------------------------------------------------------------------------------------------------------
model:  # path to model file, i.e. yolov8n.pt, yolov8n.yaml
data:  # path to data file, i.e. coco128.yaml
epochs: 200  # number of epochs to train for
patience: 50  # epochs to wait for no observable improvement for early stopping of training
batch: 32  # number of images per batch (-1 for AutoBatch)
imgsz: 640  # size of input images as integer or w,h
save: True  # save train checkpoints and predict results
save_period: -1 # Save checkpoint every x epochs (disabled if < 1)
cache: False  # True/ram, disk or False. Use cache for data loading
device:  # device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
workers: 0  # number of worker threads for data loading (per RANK if DDP)
project:  # project name
name:  # experiment name, results saved to 'project/name' directory
exist_ok: False  # whether to overwrite existing experiment
pretrained: False  # whether to use a pretrained model
optimizer: SGD  # optimizer to use, choices=['SGD', 'Adam', 'AdamW', 'RMSProp']
verbose: True  # whether to print verbose output
seed: 0  # random seed for reproducibility
deterministic: True  # whether to enable deterministic mode
single_cls: False  # train multi-class data as single-class
image_weights: False  # use weighted image selection for training
rect: False  # support rectangular training if mode='train', support rectangular evaluation if mode='val'
cos_lr: False  # use cosine learning rate scheduler
close_mosaic: 10  # disable mosaic augmentation for final 10 epochs
resume: False  # resume training from last checkpoint
amp: True  # Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check
# Segmentation
overlap_mask: True  # masks should overlap during training (segment train only)
mask_ratio: 4  # mask downsample ratio (segment train only)
# Classification
dropout: 0.0  # use dropout regularization (classify train only)

# Val/Test settings ----------------------------------------------------------------------------------------------------
val: True  # validate/test during training
split: val  # dataset split to use for validation, i.e. 'val', 'test' or 'train'
save_json: False  # save results to JSON file
save_hybrid: False  # save hybrid version of labels (labels + additional predictions)
conf:  # object confidence threshold for detection (default 0.25 predict, 0.001 val)
iou: 0.7  # intersection over union (IoU) threshold for NMS
max_det: 300  # maximum number of detections per image
half: False  # use half precision (FP16)
dnn: False  # use OpenCV DNN for ONNX inference
plots: True  # save plots during train/val

# Prediction settings --------------------------------------------------------------------------------------------------
source:  # source directory for images or videos
show: False  # show results if possible
save_txt: False  # save results as .txt file
save_conf: False  # save results with confidence scores
save_crop: False  # save cropped images with results
hide_labels: False  # hide labels
hide_conf: False  # hide confidence scores
vid_stride: 1  # video frame-rate stride
line_thickness: 3  # bounding box thickness (pixels)
visualize: False  # visualize model features
augment: False  # apply image augmentation to prediction sources
agnostic_nms: False  # class-agnostic NMS
classes:  # filter results by class, i.e. class=0, or class=[0,2,3]
retina_masks: False  # use high-resolution segmentation masks
boxes: True  # Show boxes in segmentation predictions

# Export settings ------------------------------------------------------------------------------------------------------
format: torchscript  # format to export to
keras: False  # use Keras
optimize: False  # TorchScript: optimize for mobile
int8: False  # CoreML/TF INT8 quantization
dynamic: False  # ONNX/TF/TensorRT: dynamic axes
simplify: False  # ONNX: simplify model
opset:  # ONNX: opset version (optional)
workspace: 4  # TensorRT: workspace size (GB)
nms: False  # CoreML: add NMS

# Hyperparameters ------------------------------------------------------------------------------------------------------
lr0: 0.01  # initial learning rate (i.e. SGD=1E-2, Adam=1E-3)
lrf: 0.01  # final learning rate (lr0 * lrf)
momentum: 0.937  # SGD momentum/Adam beta1
weight_decay: 0.0005  # optimizer weight decay 5e-4
warmup_epochs: 3.0  # warmup epochs (fractions ok)
warmup_momentum: 0.8  # warmup initial momentum
warmup_bias_lr: 0.1  # warmup initial bias lr
box: 7.5  # box loss gain
cls: 0.5  # cls loss gain (scale with pixels)
dfl: 1.5  # dfl loss gain
fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
label_smoothing: 0.0  # label smoothing (fraction)
nbs: 64  # nominal batch size
hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4  # image HSV-Value augmentation (fraction)
degrees: 0.0  # image rotation (+/- deg)
translate: 0.1  # image translation (+/- fraction)
scale: 0.5  # image scale (+/- gain)
shear: 0.0  # image shear (+/- deg)
perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
flipud: 0.0  # image flip up-down (probability)
fliplr: 0.5  # image flip left-right (probability)
mosaic: 1.0  # image mosaic (probability)
mixup: 0.0  # image mixup (probability)
copy_paste: 0.0  # segment copy-paste (probability)

# Custom config.yaml ---------------------------------------------------------------------------------------------------
cfg:  # for overriding defaults.yaml

# Debug, do not modify -------------------------------------------------------------------------------------------------
v5loader: False  # use legacy YOLOv5 dataloader

# Tracker settings ------------------------------------------------------------------------------------------------------
tracker: botsort.yaml  # tracker type, ['botsort.yaml', 'bytetrack.yaml']

yolo detect train model=yolov8s.yaml data=ultralytics/datasets/InfraRedSmallTarget.yaml

https://blog.csdn.net/m0_63774211/article/details/131519223