Comments (3)
又试了以下
原anchor[10,14, 23,27, 37,58, 81,82, 135,169, 344,319],acc:62%,
设置五个聚类中心, [37,44, 53,152, 68,60, 98,113, 194,260],聚类后anchor [37,44, 37,44, 53,152, 68,60, 98,113, 194,260],acc:69%,acc提升,但map还是掉了两个点
from yolov4-tiny-pytorch.
我使用训练集的anchor
测试集聚类[41,78, 43,36, 83,117, 197,257, 413,409]
训练集聚类[37,44, 53,152, 68,60, 98,113, 194,260]
原anchor [23,27, 37,58, 81,82, 135,169, 344,319]
大神请问,我可不可在硕士论文里写:经过对比原版anchor和聚类后anchor的效果,选择原版anchor作为模型的anchor。
from yolov4-tiny-pytorch.
可以这样写,因为原版的anchor大中小配置非常合理,所以他的map会高一些。
修改后分布就不是那么合理了
from yolov4-tiny-pytorch.
Related Issues (20)
- 大佬你好,我在阅读代码中有一个疑问。 HOT 2
- 關於測試圖像
- DDP init_process_group 配置问题 HOT 2
- 解码bbox问题 HOT 4
- 如何使用COCO格式的数据集训练 HOT 1
- 关于CA预训练权重文件
- get_map问题 HOT 2
- 配置环境 HOT 1
- 导,我有一个自己的数据集,请问什么指令生成预训练权重呢
- 导,你的heatmap用的是cam吗?
- 导,你的heatmap生成原理是什么?
- 增加head
- Map和预测无框 HOT 1
- nets文件夹下的yolo.pu
- 训练过程资源记载缓慢
- voc数据集训练未检测到任何目标 Val Loss: nan
- 支持多尺度训练吗?
- 如何得到参数以及GFLOPs HOT 1
- ValueError: Expected a symbolic Tensors or a callable for the loss value. Please wrap your loss computation in a zero argument `lambda`. HOT 1
- 关于混淆矩阵的生成问题 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from yolov4-tiny-pytorch.