探索 Ultralytics YOLOv8
概述#
Ultralytics 于 2023 年 1 月 10 日发布 YOLOv8,与先前的 YOLO 版本相比,精度和速度均有所提升。YOLOv8 在这些版本的基础上引入了新特性和优化,使其成为多种应用中执行目标检测及其他视觉任务的优选方案。对于新项目,Ultralytics 建议使用 YOLO26。

观看: Ultralytics YOLOv8 模型概览
直接在 Ultralytics Platform 上探索并运行 YOLOv8 模型。
YOLOv8 的主要特性#
- 先进的主干网络和颈部架构:YOLOv8 采用先进的主干网络和颈部架构,从而提升特征提取能力和目标检测性能。
- 无锚框的 Ultralytics 分离式检测头:YOLOv8 采用无锚框的 Ultralytics 分离式检测头,与基于锚框的方法相比,有助于提高精度并提升检测效率。
- 优化准确率与速度的权衡: YOLOv8 注重在准确率和速度之间保持最佳平衡,适用于各种应用领域的实时目标检测任务。
- 多种预训练模型: YOLOv8 提供多种预训练模型,以满足不同任务和性能需求,方便你为特定用例找到合适的模型。
支持的任务和模式#
YOLOv8 系列提供多种模型,每种模型都针对特定的计算机视觉任务进行了优化。这些模型旨在满足各种需求,涵盖从目标检测到更复杂任务的广泛范围,例如实例分割、分类、姿态/关键点检测和有向目标检测。
YOLOv8 系列的每个变体都针对相应任务进行了优化。所有变体均支持训练、验证、推理和导出模式,涵盖从开发到部署的每个阶段。
| 模型 | 文件名 | 任务 | 训练 | 验证 | 推理 | 导出 |
|---|---|---|---|---|---|---|
| YOLOv8 | yolov8n.pt yolov8s.pt yolov8m.pt yolov8l.pt yolov8x.pt | 检测 | ✅ | ✅ | ✅ | ✅ |
| YOLOv8-seg | yolov8n-seg.pt yolov8s-seg.pt yolov8m-seg.pt yolov8l-seg.pt yolov8x-seg.pt | 实例分割 | ✅ | ✅ | ✅ | ✅ |
| YOLOv8-cls | yolov8n-cls.pt yolov8s-cls.pt yolov8m-cls.pt yolov8l-cls.pt yolov8x-cls.pt | 分类 | ✅ | ✅ | ✅ | ✅ |
| YOLOv8-pose | yolov8n-pose.pt yolov8s-pose.pt yolov8m-pose.pt yolov8l-pose.pt yolov8x-pose.pt yolov8x-pose-p6.pt | 姿态/关键点 | ✅ | ✅ | ✅ | ✅ |
| YOLOv8-obb | yolov8n-obb.pt yolov8s-obb.pt yolov8m-obb.pt yolov8l-obb.pt yolov8x-obb.pt | 定向检测 | ✅ | ✅ | ✅ | ✅ |
本表汇总了 YOLOv8 模型变体、每个模型执行的任务,以及它们对训练、验证、推理和导出模式的支持情况。
性能指标#
YOLOv8 使用示例#
请注意,以下示例适用于用于目标检测的 YOLOv8 检测模型。有关其他支持的任务,请参阅分割、分类、姿态和 OBB 文档。
PyTorch 预训练的 *.pt 模型以及配置 *.yaml 文件都可以传递给 YOLO() 类,从而在 Python 中创建模型实例:
from ultralytics import YOLO
# 加载一个在 COCO 上预训练的 YOLOv8n 模型
model = YOLO("yolov8n.pt")
# 显示模型信息(可选)
model.info()
# 使用 COCO8 示例数据集训练模型 100 个 epoch
results = model.train(data="coco8.yaml", epochs=100, imgsz=640)
# 使用 YOLOv8n 模型对 'bus.jpg' 图像进行推理
results = model("path/to/bus.jpg")引用与致谢#
如果你在工作中使用此仓库中的 YOLOv8 模型或任何其他软件,请按照以下格式引用:
@software{yolov8_ultralytics,
author = {Glenn Jocher and Ayush Chaurasia and Jing Qiu},
title = {Ultralytics YOLOv8},
version = {8.0.0},
year = {2023},
url = {https://github.com/ultralytics/ultralytics},
orcid = {0000-0001-5950-6979, 0000-0002-7603-6750, 0000-0003-3783-7069},
license = {AGPL-3.0}
}YOLOv8 模型采用 AGPL-3.0 和 企业版许可证提供。
常见问题#
YOLOv8 旨在提升实时目标检测性能。与早期版本不同,YOLOv8 采用无锚框分离式 Ultralytics 头部和先进的骨干网络与颈部网络架构,并针对各种应用提供优化后的准确率-速度权衡。
YOLOv8 模型在发布时于多个基准数据集上取得了先进性能。例如,YOLOv8n 模型在 COCO 数据集上的平均精度均值(mAP)达到 37.3,在 A100 TensorRT 上的速度为 0.99 毫秒。各模型变体在不同任务和数据集上的详细性能指标,请参阅性能指标部分。
评论356
提出问题、分享结果,或帮助其他人。
Yscream(已编辑)
hey there! can you help me to handle error which i get every time when run train increasing batch and imgsz options, please? first of all, i have a powerful enough computer. RTX 3090 24gb, Ryzen 9 7950X3D 16-Core, 128gb RAM if i run train with following options
results = model.train(data=f'{database_foldername}data.yaml', cfg=cfg_filename, epochs=epochs, imgsz=640, batch=8, device=0)it works quit good, and it uses about 3-4gb GPU_MEM, but i want to change imgsz to 1280 to increase accuracy of model and when i run train with this changed option i always got different errors, like:RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILEDRuntimeError: CUDA error: device-side assert triggered Compile withTORCH_USE_CUDA_DSAto enable device-side assertions.RuntimeError: CUDA error: an illegal memory access was encountered Compile withTORCH_USE_CUDA_DSAto enable device-side assertions.RuntimeError: Pin memory thread exited unexpectedly terminate called without an active exceptionand as i wrote earlier it throw different every time. i tride run with CUDA_LAUNCH_BLOCKING=1, but nothing changed
help!!! i want to use all the power of my graphics card
2Yscream
Any solutions please thank you
Paula DerrengerUltralytics@Yscream it sounds like you're encountering memory-related issues when increasing the image size during training. Given your powerful hardware, this is likely due to the increased memory demands of larger images. Here are a few suggestions to help mitigate these errors:
-
Reduce Batch Size: Try lowering the batch size when increasing the image size. For example, if you're using
imgsz=1280, you might need to reduce the batch size to 2 or even 1 to fit within the GPU memory limits. -
Mixed Precision Training: Enable mixed precision training by setting
amp=Truein your training arguments. This can help reduce memory usage and potentially improve training speed. -
Check for Software Updates: Ensure you are using the latest versions of PyTorch, CUDA, and cuDNN. Sometimes, updating these can resolve compatibility and performance issues.
-
Debugging: Use
CUDA_LAUNCH_BLOCKING=1to get more detailed error messages, which can help pinpoint the exact cause of the issue.
If the problem persists, please try these steps and let us know if you encounter any specific errors. This will help us provide more targeted assistance.
-
rohith-aiunika
Hi YOLO Team, I have a v8 segmentation model, i need to convert my pt file to TFlite, is it possible?
1xuan2261
"# Improved YOLOv8 with BiFormer, Fusion Blocks, MS-Block, DConv, ECA, Ghost Module, and Focal Loss
Parameters
nc: 9 # number of classes scales:
[depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]Backbone (ensure specific feature sizes: 160×160×128, 80×80×256, 40×40×512, 20×20×512)
backbone:
[from, repeats, module, args]
- [-1, 1, GhostModule, [64, 3, 2]] # 0-P1/2 -> output 320×320×64, using Ghost Module to reduce computation
- [-1, 1, Conv, [128, 3, 2, Mish]] # 1-P2/4 -> output 160×160×128, using Mish activation
- [-1, 3, C2f_DM, [128, True]] # output 160×160×128
- [-1, 1, MS-Block, [128, 3, [3, 5, 7], True]] # MS-Block with residual connections for multi-scale feature extraction
- [-1, 1, Conv, [256, 3, 2, Mish]] # 3-P3/8 -> output 80×80×256, using Mish activation
- [-1, 6, C2f_DM, [256, True]] # output 80×80×256
- [-1, 1, MS-Block, [256, 3, [3, 5, 7], True]] # MS-Block for P3/8 with residual connections
- [-1, 1, Conv, [512, 3, 2, Mish]] # 5-P4/16 -> output 40×40×512, using Mish activation
- [-1, 6, C2f_DM, [512, True]] # output 40×40×512
- [-1, 1, MS-Block, [512, 3, [3, 5, 7], True]] # MS-Block for P4/16 with residual connections
- [-1, 1, Conv, [1024, 3, 2, Mish]] # 7-P5/32 -> output 20×20×512, using Mish activation
- [-1, 3, C2f_DM, [1024, True]] # output 20×20×512
- [-1, 1, MS-Block, [1024, 3, [3, 5, 7], True]] # MS-Block for P5/32 with residual connections
- [-1, 1, SPPF, [1024, 5]] # Spatial Pyramid Pooling Fast -> output 20×20×512
Neck with Fusion Blocks, MS-Block, BiFormer, DConv, and ECA (replacing Concat)
neck:
[from, repeats, module, args]
-
[-1, 1, nn.Upsample, [None, 2, 'nearest']]
-
[[-1, 6], 1, Fusion_Block, [512]] # Fusion Block replacing Concat for backbone P4
-
[-1, 3, C2f_Att, [512]] # C2F-Att with Attention Mechanism
-
[-1, 1, BiFormer, [512]] # BiFormer added for enhanced spatial relationships
-
[-1, 1, DConv, [512, 3]] # Adding Dynamic Convolution
-
[-1, 1, ECA, [512]] # Adding Efficient Channel Attention
-
[-1, 1, MS-Block, [512, 3, [3, 5, 7], True]] # MS-Block for multi-scale feature extraction in Neck
-
[-1, 1, nn.Upsample, [None, 2, 'nearest']]
-
[[-1, 4], 1, Fusion_Block, [256]] # Fusion Block replacing Concat for backbone P3
-
[-1, 3, C2f_Att, [256]] # P3/8-small
-
[-1, 1, BiFormer, [256]] # BiFormer added for P3
-
[-1, 1, DConv, [256, 3]] # Adding Dynamic Convolution for P3
-
[-1, 1, ECA, [256]] # Adding Efficient Channel Attention for P3
-
[-1, 1, MS-Block, [256, 3, [3, 5, 7], True]] # MS-Block for P3 in Neck
-
[-1, 1, Conv, [256, 3, 2, Mish]]
-
[[-1, 12], 1, Fusion_Block, [512]] # Fusion Block replacing Concat for head P4
-
[-1, 3, C2f_Att, [512]] # P4/16-medium
-
[-1, 1, BiFormer, [512]] # BiFormer added for P4
-
[-1, 1, DConv, [512, 3]] # Adding Dynamic Convolution for P4
-
[-1, 1, ECA, [512]] # Adding Efficient Channel Attention for P4
-
[-1, 1, MS-Block, [512, 3, [3, 5, 7], True]] # MS-Block for P4 in Neck
-
[-1, 1, Conv, [512, 3, 2, Mish]]
-
[[-1, 9], 1, Fusion_Block, [1024]] # Fusion Block replacing Concat for head P5
-
[-1, 3, C2f_Att, [1024]] # P5/32-large
-
[-1, 1, BiFormer, [1024]] # BiFormer added for P5
-
[-1, 1, DConv, [1024, 3]] # Adding Dynamic Convolution for P5
-
[-1, 1, ECA, [1024]] # Adding Efficient Channel Attention for P5
-
[-1, 1, MS-Block, [1024, 3, [3, 5, 7], True]] # MS-Block for P5 in Neck
Adding a fourth detecting head for improved detection at different scales
- [-1, 1, Conv, [128, 3, 2, Mish]]
- [[-1, 3], 1, Fusion_Block, [128]] # new Fusion Block for smaller objects
- [-1, 3, C2f_Att, [128]] # P6/64-smaller objects
- [-1, 1, BiFormer, [128]] # BiFormer added for P6
- [-1, 1, DConv, [128, 3]] # Adding Dynamic Convolution for P6
- [-1, 1, ECA, [128]] # Adding Efficient Channel Attention for P6
- [-1, 1, MS-Block, [128, 3, [3, 5, 7], True]] # MS-Block for P6 in Neck
Head
head:
- [[17, 21, 25, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)
Loss Function
loss: name: FocalLoss # Using Focal Loss for better handling of small object detection" If I change the new structure like this, then I can add code for new modules, blocks: GhostModule, C2f_DM, MS-Block, BiFormer, .... to which files?
1
Glenn JocherUltralytics@xuan2261 to integrate new modules like GhostModule and BiFormer, you'll need to modify the model architecture files in the Ultralytics repository. Specifically, look into the
modelsdirectory where the architecture is defined, and add your custom modules there. Ensure you also update any relevant configuration files to reflect these changes.
Wenlong914
有没有人能为我解答一下,训练数据集过程中的权重文件也能用吗?为什么训练过程中的权重文件比训练结束后的大?
1
Paula DerrengerUltralytics您好!在训练过程中保存的权重文件通常会比训练完成后的权重文件大,这是因为它们可能包含额外的信息,比如优化器状态和用于继续训练的其他元数据。完成训练后,通常只会保存用于推断的模型参数,不包含训练期间需要的额外信息。
对于在训练过程中的权重文件,您完全可以使用它们来继续训练或进行预测,这在处理意外中断的训练时特别有用。如果您想验证模型的性能,或者希望进行一些测试,加载这些权重然后运行验证或推理是非常合适的。
希望这能帮助您!如果有更多问题,欢迎随时提问。🙂
1
haolele123
作者您好,我想训练yolov8m-p2的版本,我在想能否使用yolov8的模型权重作为预训练权重,且我发现似乎没有yolov8-p2的m的版本这个怎末决解呢
1
Paula DerrengerUltralytics(已编辑)您好!😊 感谢您对 YOLOv8 模型的兴趣!
yolov8m-p2没有单独的预训练权重,但可以直接使用 P2 配置文件训练:yolov8-p2.yaml支持n/s/m/l/x各个规模,指定yolov8m-p2.yaml即可构建 m 规模的 P2 模型。同时可以用yolov8m.pt作为预训练权重,形状匹配的层会被加载,P2 新增的层则随机初始化:yolo train model=yolov8m-p2.yaml pretrained=yolov8m.pt data=your_dataset.yaml epochs=100 imgsz=640如果直接使用
model=yolov8m.pt,训练的是标准 YOLOv8m,没有 P2 检测头。如需新的项目,也建议考虑 YOLO26。希望这有所帮助!如果还有其他问题,欢迎随时提问。祝您训练顺利!🚀
chaobao
作者你好,请问海滩或者足球场,怎么才能提高对人的识别率?
Glenn JocherUltralytics可以,提升这类场景下
person识别率最有效的方法通常是用海滩/球场相似数据做微调,增大imgsz(如960或1280)提升远处小目标召回,适当降低conf,并优先尝试更强的模型如 Ultralytics YOLO26;如果你愿意,也欢迎把几张样例图和当前训练配置发到 Ultralytics Discussions,这样团队更容易帮你定位具体瓶颈。
yaoyuan20000111-web
感谢yolov8让我可以研究生毕业
siddannamd
I came to know that YOLOv8 is capable of tracking objects. I am currently working on a robotics model that includes object detection and object tracking. Can YOLOv8 perform both detection and tracking simultaneously? Also, you didn’t mention the benchmark for object tracking compared to other models.
Glenn JocherUltralyticsYes—YOLOv8 can do detection and tracking in the same run via
trackmode (it detects each frame, then assigns persistent IDs with a tracker); see the Multi-Object Tracking (Track mode) docs (works with YOLOv8 Detect/Seg/Pose models listed on the YOLOv8 page).yolo track model=yolov8n.pt source=path/to/video.mp4 tracker="bytetrack.yaml"We don’t publish a single “tracking benchmark vs other models” on the YOLOv8 model page because results vary a lot with tracker choice (
botsort.yamlvsbytetrack.yaml), input FPS/resolution, and the evaluation set; if you share your target objects + a short sample video (or which MOT-style benchmark you’re using) here in the discussion, we can suggest a solid baseline config to compare fairly.
AniruddhaAi
I am trying to use yolov8m.pt's backbone for feature extractor. Why does it force download the coco dataset? Is there a way I could just load the weights rather downloading the data? I need to extract the features from custom dataset
Glenn JocherUltralyticsLoading
yolov8m.ptshould only download the weights; the COCO download is triggered when you runtrain()/val()(or anything that uses a COCOdata=...YAML, including defaults). For feature extraction on your own images, use embeddings directly (no dataset download) viaModel.embed()on your custom image folder/file:from ultralytics import YOLO model = YOLO("yolov8m.pt") # weights only embeddings = model.embed(source="path/to/images") # your custom data
liuna471658955
Hi,dears, i'm new of YoLoV8, can you help see is there any thing can be improved of my below code?
from PIL import Image from ultralytics import YOLO import glob import os import numpy as np from tqdm import tqdm import torch from concurrent.futures import ThreadPoolExecutor
class Predict def init(self, batch_size=8, imgsz=640, conf_thres=0.25, iou_thres=0.45, half=True, device=cuda0)
初始化优化后的推理类 param batch_size 批量推理大小(根据GPU显存调整) param imgsz 推理图片尺寸(建议为32的倍数) param conf_thres 置信度阈值(过滤低置信度预测) param iou_thres NMS的IOU阈值(控制重复框) param half 是否使用半精度推理(FP16,提速且不损失精度) param device 推理设备(cudacpumps) self.model_path = homejovyanworkstudentmodelsyolo_train4weightsbest.pt self.device = torch.device(device if torch.cuda.is_available() else cpu) self.model = YOLO(self.model_path).to(self.device) # 核心推理参数 self.batch_size = batch_size self.imgsz = imgsz self.conf_thres = conf_thres self.iou_thres = iou_thres self.half = half and torch.cuda.is_available() # 仅GPU支持半精度 # 预热模型(首次推理加速) self._warmup_model() def _warmup_model(self) 模型预热:首次推理避免初始化耗时 dummy_img = torch.randn(1, 3, self.imgsz, self.imgsz).to(self.device) if self.half dummy_img = dummy_img.half() self.model.predict(dummy_img, verbose=False, conf=self.conf_thres, iou=self.iou_thres, half=self.half) def _load_image(self, img_path) 单张图片加载(封装为线程池调用) try with Image.open(img_path) as img img = img.convert(RGB) return img_path, img, None except Exception as e return img_path, None, str(e) def _batch_load_images(self, image_paths) 批量加载图片(多线程提速) images = [] valid_paths = [] error_logs = [] # 多线程加载图片(CPU密集型任务提速) with ThreadPoolExecutor(max_workers=4) as executor results = list(tqdm(executor.map(self._load_image, image_paths), total=len(image_paths), desc=Loading images)) for path, img, err in results if err error_logs.append(fSkipping {path} {err}) continue valid_paths.append(path) images.append(img) # 打印加载错误 if error_logs for err in error_logs[5] # 只打印前5个错误 print(err) return valid_paths, images def detect(self, image_dir) 优化后的推理主函数 param image_dir 图片目录 param use_tta 是否启用TTA(测试时增强,提升准确率,小幅增加耗时) return 推理结果列表 # 1. 获取所有图片路径 exts = [.jpg, .jpeg, .png, .JPG, .JPEG, .PNG] image_paths = [] for ext in exts image_paths.extend(glob.glob(os.path.join(image_dir, ext))) if not image_paths print(No images found in directory!) return [] # 2. 批量加载图片(多线程) valid_paths, images = self._batch_load_images(image_paths) if not valid_paths return [] # 3. 分批次推理 all_results = [] num_batches = (len(valid_paths) + self.batch_size - 1) self.batch_size for batch_idx in tqdm(range(num_batches), desc=Inferencing batches) # 切分批次 start = batch_idx self.batch_size end = min((batch_idx + 1) self.batch_size, len(valid_paths)) batch_paths = valid_paths[startend] batch_imgs = images[startend] # 4. 执行推理(核心优化) try results = self.model.predict( source=batch_imgs, imgsz=self.imgsz, # 统一推理尺寸 conf=self.conf_thres, # 置信度过滤 iou=self.iou_thres, # NMS阈值 half=self.half, # 半精度推理 device=self.device, # 指定设备 verbose=False, # 关闭日志 batch=self.batch_size, # 批量大小 # tta=use_tta, # 测试时增强(可选) max_det=100, # 单图最大检测数 vid_stride=1, # 视频步长(图片无效) retina_masks=False # 掩码细化(无掩码时关闭) ) except Exception as e print(fBatch {batch_idx} inference failed {e}) continue # 5. 解析结果(减少CPUGPU数据拷贝) for idx, result in enumerate(results) img_path = batch_paths[idx] image_name = os.path.basename(img_path) detections = [] if result.boxes is not None and len(result.boxes) 0 # 批量转换数据(避免逐框循环拷贝) cls = result.boxes.cls.cpu().numpy().astype(int).tolist() boxes = result.boxes.xyxy.cpu().numpy().tolist() scores = result.boxes.conf.cpu().numpy().astype(float).tolist() # 生成检测结果 for c, b, s in zip(cls, boxes, scores) detections.append({ cls int(c), box [float(x) for x in b], score round(float(s), 3) # 保留3位小数,减少存储 }) all_results.append({ image_name image_name, detections detections, image_path img_path }) return all_results使用示例
if name == main # 初始化优化后的推理器(根据GPU显存调整参数) pre = Predict( batch_size=16, # 批量大小(1080Ti建议8-16,A100建议32-64) imgsz=640, # 推理尺寸(训练时用640则保持一致) conf_thres=0.3, # 提高置信度阈值,过滤假阳性 iou_thres=0.4, # 降低IOU阈值,减少重复框 half=True, # 启用半精度推理 device=cuda0 # 指定GPU )
# 执行推理(use_tta=True 提升准确率,耗时增加~30%) results = pre.detect(image_dir=homejovyanworkstudenttest) # 打印结果 for idx, result in enumerate(results[3]) # 只打印前3个 print(fImage {result['image_name']}) print(fDetections {len(result['detections'])} objects) for det in result[detections] print(f - Class {det['cls']}, Box {det['box']}, Score {det['score']}) print(- 50) print(fTotal processed images {len(results)})
Glenn JocherUltralyticsNice work putting this together; you can simplify it a lot by letting YOLO handle most of what you’re doing manually.
A few concrete suggestions:
- Use the built‑in directory + batch inference instead of your own loader and batching. YOLO already scans a folder, loads images in parallel and batches them:
from ultralytics import YOLO model = YOLO("best.pt") results = model.predict( source="path/to/images_dir", # folder with images imgsz=640, conf=0.3, iou=0.4, device="cuda:0", # or "cpu" batch=16, # batched inference half=True, # FP16 on GPU verbose=False )This gives you essentially the same effect as your
Predict.detect()without the customThreadPoolExecutor, manual slicing, or warmup.-
Don’t call
.to(self.device)on theYOLOobject; instead, just passdevice="cuda:0"(or"cpu") topredict()as above. That’s the supported pattern in the Python API. -
If you want to keep a small wrapper class, keep it thin and delegate everything to
model.predict():
class Predictor: def __init__(self, weights, device="cuda:0", imgsz=640, conf=0.3, iou=0.4, batch=16, half=True): self.model = YOLO(weights) self.device = device self.imgsz = imgsz self.conf = conf self.iou = iou self.batch = batch self.half = half and "cuda" in str(device) def __call__(self, image_dir): return self.model.predict( source=image_dir, imgsz=self.imgsz, conf=self.conf, iou=self.iou, device=self.device, batch=self.batch, half=self.half, verbose=False, )If you share what problem you’re trying to optimize (speed, memory, or result format), I can suggest more targeted tweaks; in the meantime, the built‑in batch directory inference in the Predict mode docs will usually be both faster and simpler than a custom pipeline.