# Ultralytics YOLO ����, GPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args] repeats: the num of conv conv: conv.png
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2 0:layer index P1:"level" of feature extraction in backbone /2: This denotes the downsampling factor
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4 [128, 3, 2]: 128 filters, 3x3 kernel, stride 2
- [-1, 3, C2f, [128, True]] # 2 True: residual connection enabled
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]] # 4
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]] # 6
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]] # 8
- [-1, 1, SPPF, [1024, 5]] # 9
# find the corresponding illustration on the netron. e.g. model.9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] # resize
- [[-1, 6], 1, Concat, [1]] # cat backbone P4 # 6-->focus on the final conv block
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]] # 16
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]] # 19
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # 22 Detect(P3, P4, P5)
没有合适的资源?快使用搜索试试~ 我知道了~
yolov8s模型进行剪枝源码
共7个文件
png:4个
yaml:1个
md:1个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 18 下载量 174 浏览量
2023-05-13
11:10:10
上传
评论 18
收藏 15.63MB RAR 举报
温馨提示
实现步骤: 1. yolov8s模型预训练 2. 模型稀疏化sparsity 3.剪枝 4. finetune 经过键枝后,finetune60个epoch达到原模型迭代52个epoch的mAP值0.78,模型的大小减少了2/5。
资源推荐
资源详情
资源评论
收起资源包目录
yolov8-prune.rar (7个子文件)
yolov8-prune
yolov8.yaml 2KB
ultralytics-main.tar.gz 15.54MB
tutorial.md 28KB
fig
bottleneck.png 29KB
pipeline.png 10KB
sppf.png 100KB
conv.png 10KB
共 7 条
- 1
@BangBang
- 粉丝: 9495
- 资源: 76
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
- 1
- 2
- 3
- 4
- 5
- 6
前往页