在 GitHub 上编辑页面 (EN)

YOLOv5 的超参数进化

📚 This guide explains hyperparameter evolution for YOLOv5 🚀. Hyperparameter evolution is a method of Hyperparameter Optimization using a Genetic Algorithm (GA) for optimization.

机器学习中的超参数控制着训练的各个方面，寻找其最佳值可能是一项挑战。传统的网格搜索等方法很快会因为以下原因变得难以处理：

  1. 高维搜索空间
  2. 各维度间未知的相关性
  3. 在每个点评估适应度的高昂代价

这使得遗传算法成为超参数搜索的合适选择。

在你开始之前

Clone repo and install requirements.txt in a Python>=3.8.0 environment, including PyTorch>=1.8. Models and datasets download automatically from the latest YOLOv5 release.

git clone https://github.com/ultralytics/yolov5 # clone
cd yolov5
pip install -r requirements.txt # install

初始化超参数

YOLOv5 has about 30 hyperparameters used for various training settings. These are defined in *.yaml files in the /data/hyps directory. Better initial guesses will produce better final results, so it is important to initialize these values properly before evolving. If in doubt, simply use the default values, which are optimized for YOLOv5 COCO training from scratch.

# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
# Hyperparameters for low-augmentation COCO training from scratch
# python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear
# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials

lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.01 # final OneCycleLR 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: 0.05 # box loss gain
cls: 0.5 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
obj: 1.0 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
iou_t: 0.20 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3  # anchors per output layer (0 to ignore)
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
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)

定义适应度

适应度是我们试图最大化的值。在 YOLOv5 中，我们定义了一个默认的适应度函数，它是指标的加权组合：mAP@0.5 权重占 10%，mAP@0.5:0.95 占剩余 90%，精确率 (P) 和 召回率 (R) 不参与计算。你可以根据需要进行调整，或者使用 utils/metrics.py 中的默认适应度定义（推荐）。

def fitness(x):
    """Return model fitness as the sum of weighted metrics [P, R, mAP@0.5, mAP@0.5:0.95]."""
    w = [0.0, 0.0, 0.1, 0.9]  # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
    return (x[:, :4] * w).sum(1)

进化

Evolution is performed about a base scenario which we seek to improve upon. The base scenario in this example is fine-tuning COCO128 for 10 epochs using pretrained YOLOv5s. The base scenario training command is:

python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache

要进化特定于此场景的超参数，从第 1 节定义的初始值开始，并最大化第 2 节中定义的适应度，请添加 --evolve 参数：

# Single-GPU
python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache --evolve

# Multi-GPU with delay
for i in {0..7}; do
  sleep $((30 * i)) # 30-second delay (optional)
  echo "Starting GPU $i..."
  nohup python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache --device $i --evolve > "evolve_gpu_$i.log" &
done

# Continuous training (use with caution)
# for i in {0..7}; do
#   sleep $((30 * i))  # 30-second delay (optional)
#   echo "Starting continuous training on GPU $i..."
#   (
#     while true; do
#       python train.py --epochs 10 --data coco128.yaml --weights yolov5s.pt --cache --device $i --evolve > "evolve_gpu_$i.log"
#     done
#   ) &
# done

默认进化设置将运行基础场景 300 次，即 300 代。你可以通过 --evolve 参数修改代数，例如 python train.py --evolve 1000。

主要的遗传算子是交叉和变异。本项工作使用了变异，概率为 80%，方差为 0.04，旨在基于历代最佳父代的组合创造新的后代。结果会被记录到 runs/evolve/exp/evolve.csv 中，每一代适应度最高的后代会被保存为 runs/evolve/hyp_evolved.yaml：

# YOLOv5 Hyperparameter Evolution Results
# Best generation: 287
# Last generation: 300
#    metrics/precision,       metrics/recall,      metrics/mAP_0.5, metrics/mAP_0.5:0.95,         val/box_loss,         val/obj_loss,         val/cls_loss
#              0.54634,              0.55625,              0.58201,              0.33665,             0.056451,             0.042892,             0.013441

lr0: 0.01 # initial learning rate (SGD=1E-2, Adam=1E-3)
lrf: 0.2 # final OneCycleLR 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: 0.05 # box loss gain
cls: 0.5 # cls loss gain
cls_pw: 1.0 # cls BCELoss positive_weight
obj: 1.0 # obj loss gain (scale with pixels)
obj_pw: 1.0 # obj BCELoss positive_weight
iou_t: 0.20 # IoU training threshold
anchor_t: 4.0 # anchor-multiple threshold
# anchors: 3  # anchors per output layer (0 to ignore)
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
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)

我们建议至少进行 300 代进化以获得最佳结果。请注意，进化通常既昂贵又耗时，因为基础场景会被训练数百次，可能需要数百甚至数千个 GPU 小时。

进化完成后，通过指定保存的文件来重用发现的设置，例如 python train.py --hyp runs/evolve/hyp_evolved.yaml --data your.yaml --weights yolov5s.pt。

可视化

evolve.csv is plotted as evolve.png by utils.plots.plot_evolve() after evolution finishes with one subplot per hyperparameter showing fitness (y-axis) vs hyperparameter values (x-axis). Yellow indicates higher concentrations. Vertical distributions indicate that a parameter has been disabled and does not mutate. This is user selectable in the meta dictionary in train.py, and is useful for fixing parameters and preventing them from evolving.

YOLOv5 超参数进化适应度结果

支持的环境

Ultralytics 提供了一系列开箱即用的环境，每个环境都预装了 CUDA、CUDNN、Python 和 PyTorch 等关键依赖项，助你快速启动项目。

项目状态

YOLOv5 CI

此徽章表示所有 YOLOv5 GitHub Actions 持续集成 (CI) 测试均成功通过。这些 CI 测试严格检查 YOLOv5 在各个关键方面的功能和性能：训练、验证、推理、导出和基准测试。它们确保了在 macOS、Windows 和 Ubuntu 上的一致且可靠的运行，测试每 24 小时以及在每次新提交时进行。

Contributors
在 GitHub 上编辑页面 (EN)
GLglenn-jocher12RIRizwanMunawar1AMambitious-octopus1

评论