人力资源公司网站模板下载,wordpress 默认字体,国内域名有哪些,外贸新三样YOLOv10: 实时端到端的目标检测。 性能 YOLOv10比最先进的YOLOv9延迟时间更低#xff0c;测试结果可以与YOLOv9媲美#xff0c;可能会成为YOLO系列模型部署的“新选择”。 目录 1 数据准备 2 配置文件 3 训练 4 验证 5 预测 6 导出模型 7 ONNX模型的使用 官方论文地址…YOLOv10: 实时端到端的目标检测。 性能 YOLOv10比最先进的YOLOv9延迟时间更低测试结果可以与YOLOv9媲美可能会成为YOLO系列模型部署的“新选择”。 目录 1 数据准备 2 配置文件 3 训练 4 验证 5 预测 6 导出模型 7 ONNX模型的使用 官方论文地址https://arxiv.org/pdf/2405.14458 官方代码地址https://github.com/THU-MIG/yolov10 安装 建议使用Conda虚拟环境。 ① 克隆YOLOv10项目 ​git clone https://github.com/THU-MIG/yolov10.git ② 安装 conda create -n yolov10 python3.9conda activate yolov10cd yolov10项目所在路径pip install -r requirements.txtpip install -e . -i https://pypi.tuna.tsinghua.edu.cn/simple 1 数据准备 可以使用开源的数据集也可以自己准备数据集。 ①标注工具 ⒈labelme 安装方法pip install labelme 使用方法终端输入labelme 标注后生成的标记文件是json文件。 ⒉labelimg 安装方法: pip install labelimg 使用方法 cd到labelImg所在路径 python3 labelImg.py 标注后生成的标记文件是xml文件。 ②数据集整理 原始数据集格式如下图所示 Annotations里面存放标签xml文件。 JPEGImage 里面存放原始图片。 labels文件夹里面存放的是标签txt文件。这个文件夹里的文件是通过脚本XmlToTxt.py生成的。 XmlToTxt.py的代码如下 import xml.etree.ElementTree as ET import os import os import random # TODO 这里按照类别去修改 classes [fire] # TODO 这里按照实际XML文件夹路径去修改 xml_filepath dataset_fire/Annotations/ # TODO 这里按照实际想要保存结果txt文件夹的路径去修改 labels_savepath dataset_fire/labels/ abs_path os.getcwd()def convert(size, box):dw 1. / (size[0])dh 1. / (size[1])x (box[0] box[1]) / 2.0 - 1y (box[2] box[3]) / 2.0 - 1w box[1] - box[0]h box[3] - box[2]x x * dww w * dwy y * dhh h * dhreturn x, y, w, hdef convert_annotation(image_id):in_file open(xml_filepath %s.xml % (image_id), encodingUTF-8)out_file open(labels_savepath %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).textcls obj.find(name).textif cls not in classes or int(difficult) 1:continuecls_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 wif b4 h:b4 hb (b1, b2, b3, b4)bb convert((w, h), b)out_file.write(str(cls_id) .join([str(a) for a in bb]) \n)def run():total_xml os.listdir(xml_filepath)num len(total_xml)names []for xml in total_xml:names.append(xml[:-4])for name in names:convert_annotation(name)passif __name__ __main__:run()pass 然后根据JPEGImage 文件夹和labels文件夹通过脚本deal_dataset.py将数据集划分为如下结构。 deal_dataset.py的代码如下 import os import random import shutil# 原数据集目录 root_dir dataset_fire/ # 划分比例 train_ratio 0.8 valid_ratio 0.1 test_ratio 0.1# 设置随机种子 random.seed(42)# TODo 这里按照实际数据集路径去修改 split_dir dataset_fire_split/ os.makedirs(os.path.join(split_dir, train/images), exist_okTrue) os.makedirs(os.path.join(split_dir, train/labels), exist_okTrue) os.makedirs(os.path.join(split_dir, val/images), exist_okTrue) os.makedirs(os.path.join(split_dir, val/labels), exist_okTrue) os.makedirs(os.path.join(split_dir, test/images), exist_okTrue) os.makedirs(os.path.join(split_dir, test/labels), exist_okTrue)# TODo 这里按照实际数据集路径去修改 imgpath JPEGImages labelpath labels image_files os.listdir(os.path.join(root_dir, imgpath)) label_files os.listdir(os.path.join(root_dir, labelpath))# 随机打乱文件列表 combined_files list(zip(image_files, label_files)) random.shuffle(combined_files) image_files_shuffled, label_files_shuffled zip(*combined_files)# 根据比例计算划分的边界索引 train_bound int(train_ratio * len(image_files_shuffled)) valid_bound int((train_ratio valid_ratio) * len(image_files_shuffled))# 将图片和标签文件移动到相应的目录 for i, (image_file, label_file) in enumerate(zip(image_files_shuffled, label_files_shuffled)):if i train_bound:shutil.move(os.path.join(root_dir, imgpath, image_file), os.path.join(split_dir, train/images, image_file))shutil.move(os.path.join(root_dir, labelpath, label_file), os.path.join(split_dir, train/labels, label_file))elif i valid_bound:shutil.move(os.path.join(root_dir, imgpath, image_file), os.path.join(split_dir, valid/images, image_file))shutil.move(os.path.join(root_dir, labelpath, label_file), os.path.join(split_dir, valid/labels, label_file))else:shutil.move(os.path.join(root_dir, imgpath, image_file), os.path.join(split_dir, test/images, image_file))shutil.move(os.path.join(root_dir, labelpath, label_file), os.path.join(split_dir, test/labels, label_file)) 至此数据集准备好啦 ❤️ ❤️ ❤️ ❤️ 2 配置文件 在YOLOv10的项目下新建fire.yaml文件内容如下 train: dataset_fire_split/train val: dataset_fire_split/val test: dataset_fire_split/test nc: 1 # classes names:0: fire 修改ultralytics/cfg/models/v10/yolov10s.yaml文件内容 3 训练 imgsz图像放缩大小resize默认是640。 device设备id可以是cpu,如果只有一张显卡则device0如果有两张则device0,1依次类推。 训练示例如下 方式一 从yaml构建全新的模型 yolo detect train datafire.yaml modelyolov10s.yaml epochs200 batch8 imgsz640 devicecpu projectyolov10 方式二 配置好ultralytics/cfg/default.yaml这个文件之后可以直接执行这个文件进行训练这样就不需要在命令行输入其它的参数。 yolo cfgultralytics/cfg/default.yaml 官方原版的default.yaml的内容如下 # Ultralytics YOLO , AGPL-3.0 license # Default training settings and hyperparameters for medium-augmentation COCO trainingtask: detect # (str) YOLO task, i.e. detect, segment, classify, pose mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark# Train settings ------------------------------------------------------------------------------------------------------- model: # (str, optional) path to model file, i.e. yolov8n.pt, yolov8n.yaml data: # (str, optional) path to data file, i.e. coco128.yaml epochs: 100 # (int) number of epochs to train for time: # (float, optional) number of hours to train for, overrides epochs if supplied patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training batch: 16 # (int) number of images per batch (-1 for AutoBatch) imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes save: True # (bool) save train checkpoints and predict results save_period: -1 # (int) Save checkpoint every x epochs (disabled if 1) val_period: 1 # (int) Validation every x epochs cache: False # (bool) True/ram, disk or False. Use cache for data loading device: # (int | str | list, optional) device to run on, i.e. cuda device0 or device0,1,2,3 or devicecpu workers: 8 # (int) number of worker threads for data loading (per RANK if DDP) project: # (str, optional) project name name: # (str, optional) experiment name, results saved to project/name directory exist_ok: False # (bool) whether to overwrite existing experiment pretrained: True # (bool | str) whether to use a pretrained model (bool) or a model to load weights from (str) optimizer: auto # (str) optimizer to use, choices[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto] verbose: True # (bool) whether to print verbose output seed: 0 # (int) random seed for reproducibility deterministic: True # (bool) whether to enable deterministic mode single_cls: False # (bool) train multi-class data as single-class rect: False # (bool) rectangular training if modetrain or rectangular validation if modeval cos_lr: False # (bool) use cosine learning rate scheduler close_mosaic: 10 # (int) disable mosaic augmentation for final epochs (0 to disable) resume: False # (bool) resume training from last checkpoint amp: True # (bool) Automatic Mixed Precision (AMP) training, choices[True, False], True runs AMP check fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set) profile: False # (bool) profile ONNX and TensorRT speeds during training for loggers freeze: None # (int | list, optional) freeze first n layers, or freeze list of layer indices during training multi_scale: False # (bool) Whether to use multiscale during training # Segmentation overlap_mask: True # (bool) masks should overlap during training (segment train only) mask_ratio: 4 # (int) mask downsample ratio (segment train only) # Classification dropout: 0.0 # (float) use dropout regularization (classify train only)# Val/Test settings ---------------------------------------------------------------------------------------------------- val: True # (bool) validate/test during training split: val # (str) dataset split to use for validation, i.e. val, test or train save_json: False # (bool) save results to JSON file save_hybrid: False # (bool) save hybrid version of labels (labels additional predictions) conf: # (float, optional) object confidence threshold for detection (default 0.25 predict, 0.001 val) iou: 0.7 # (float) intersection over union (IoU) threshold for NMS max_det: 300 # (int) maximum number of detections per image half: False # (bool) use half precision (FP16) dnn: False # (bool) use OpenCV DNN for ONNX inference plots: True # (bool) save plots and images during train/val# Predict settings ----------------------------------------------------------------------------------------------------- source: # (str, optional) source directory for images or videos vid_stride: 1 # (int) video frame-rate stride stream_buffer: False # (bool) buffer all streaming frames (True) or return the most recent frame (False) visualize: False # (bool) visualize model features augment: False # (bool) apply image augmentation to prediction sources agnostic_nms: False # (bool) class-agnostic NMS classes: # (int | list[int], optional) filter results by class, i.e. classes0, or classes[0,2,3] retina_masks: False # (bool) use high-resolution segmentation masks embed: # (list[int], optional) return feature vectors/embeddings from given layers# Visualize settings --------------------------------------------------------------------------------------------------- show: False # (bool) show predicted images and videos if environment allows save_frames: False # (bool) save predicted individual video frames save_txt: False # (bool) save results as .txt file save_conf: False # (bool) save results with confidence scores save_crop: False # (bool) save cropped images with results show_labels: True # (bool) show prediction labels, i.e. person show_conf: True # (bool) show prediction confidence, i.e. 0.99 show_boxes: True # (bool) show prediction boxes line_width: # (int, optional) line width of the bounding boxes. Scaled to image size if None.# Export settings ------------------------------------------------------------------------------------------------------ format: torchscript # (str) format to export to, choices at https://docs.ultralytics.com/modes/export/#export-formats keras: False # (bool) use Keras optimize: False # (bool) TorchScript: optimize for mobile int8: False # (bool) CoreML/TF INT8 quantization dynamic: False # (bool) ONNX/TF/TensorRT: dynamic axes simplify: False # (bool) ONNX: simplify model opset: # (int, optional) ONNX: opset version workspace: 4 # (int) TensorRT: workspace size (GB) nms: False # (bool) CoreML: add NMS# Hyperparameters ------------------------------------------------------------------------------------------------------ lr0: 0.01 # (float) initial learning rate (i.e. SGD1E-2, Adam1E-3) lrf: 0.01 # (float) final learning rate (lr0 * lrf) momentum: 0.937 # (float) SGD momentum/Adam beta1 weight_decay: 0.0005 # (float) optimizer weight decay 5e-4 warmup_epochs: 3.0 # (float) warmup epochs (fractions ok) warmup_momentum: 0.8 # (float) warmup initial momentum warmup_bias_lr: 0.1 # (float) warmup initial bias lr box: 7.5 # (float) box loss gain cls: 0.5 # (float) cls loss gain (scale with pixels) dfl: 1.5 # (float) dfl loss gain pose: 12.0 # (float) pose loss gain kobj: 1.0 # (float) keypoint obj loss gain label_smoothing: 0.0 # (float) label smoothing (fraction) nbs: 64 # (int) nominal batch size hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction) hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction) hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction) degrees: 0.0 # (float) image rotation (/- deg) translate: 0.1 # (float) image translation (/- fraction) scale: 0.5 # (float) image scale (/- gain) shear: 0.0 # (float) image shear (/- deg) perspective: 0.0 # (float) image perspective (/- fraction), range 0-0.001 flipud: 0.0 # (float) image flip up-down (probability) fliplr: 0.5 # (float) image flip left-right (probability) bgr: 0.0 # (float) image channel BGR (probability) mosaic: 1.0 # (float) image mosaic (probability) mixup: 0.0 # (float) image mixup (probability) copy_paste: 0.0 # (float) segment copy-paste (probability) auto_augment: randaugment # (str) auto augmentation policy for classification (randaugment, autoaugment, augmix) erasing: 0.4 # (float) probability of random erasing during classification training (0-1) crop_fraction: 1.0 # (float) image crop fraction for classification evaluation/inference (0-1)# Custom config.yaml --------------------------------------------------------------------------------------------------- cfg: # (str, optional) for overriding defaults.yaml# Tracker settings ------------------------------------------------------------------------------------------------------ tracker: botsort.yaml # (str) tracker type, choices[botsort.yaml, bytetrack.yaml] 方式三推荐 首先需要下载模型模型下载链接如下 yolov10n.pt yolov10s.pt yolov10m.pt yolov10b.pt yolov10l.pt yolov10x.pt 下载后的模型放在YOLOv10的工程目录下即可。 从yaml构建全新的模型将预训练权重转移到这个模型并开始训练。 # 数据配置文件最好用绝对路径哈yolo detect train datafire.yaml modelultralytics/cfg/models/v10/yolov10s.yaml pretrainedyolov10s.pt epochs50 batch8 imgsz640 devicecpu projectyolov10 训练过程的产物 训练结束后模型保存在路径yolov10/train5/weights下如下图 4 验证 验证示例如下 注意数据配置文件尽量用绝对路径。 cd yolov10项目所在的路径yolo taskdetect modeval splitval modelyolov10/train5/weights/best.pt datafire.yaml batch2 devicecpu 验证过程的产物 5 预测 预测示例如下 cd yolov10项目所在的路径yolo taskdetect modepredict modelyolov10/train5/weights/best.pt sourcetest.jpg devicecpu 预测效果如下图 说明本次训练过程只是说明过程训练轮数不够因此检测结果置信度一般。 6 导出模型 导出ONNX模型示例 # export custom trained modelyolo taskdetect modeexport modelyolov10/train5/weights/best.pt formatonnx 7 ONNX模型的使用 命令行方式 yolo detect predict modelyolov10/train5/weights/best.onnx sourcetest.jpg 检测结果如下图 到此本文分享的内容就结束啦遇见便是缘感恩遇见点个赞 关注吧哈哈哈哈 ❤️ ❤️ ❤️ ❤️ ❤️ ❤️ ❤️