Comments (4)
所有的算法都是自己重新配置在同一个环境下跑的, 当时在VOT上SiamAPN, SiamTPN的EAO的值的确比较低,我也不太相信,不过我使用的都是同一套参数, 它们在DTB和GOT上数值就比较高了, 可能是我测试的时候配置参数有问题. 另外我在results里面也提供了所有算法的评估结果. 或者你可以重新跑一个SiamTPN来验证一下;
from siamtrackers.
顺便再问您一个模型训练的问题,我自己的模型在训练之后,最后一段他的loss都会在0.20.3之间徘徊,还是波动还是挺大的,因为我跟着您的nano track进行训练的时候,发现最后的它都能降到0.1左右,这一点我在另一个issue也跟您说了。您说这个loss和最后的表现没有太大关系,但是我现在怀疑的是会不会说我最后接这一阶段它的波动有点大,它还没有完全收敛。您有什么建议吗?现在我的模型一阶段训练2018 的eao有0.16左右。呃,我在训练您的nanotrack的时候,第一阶段差不多也能是也是一点几。但是第二阶段您的nanotrack,它是能够往上涨挺多的,大概一倍左右。但是我的模型呃就还是第二阶段finetune时候,他还是在这一阶就是0.20.3之间波动,涨点也几乎停滞了,您能给点建议吗😭😭
from siamtrackers.
把每个epoch对应的loss值画出来看看,如果后面稳定了就是正常的.
from siamtrackers.
好的,我看看,感谢您的建议
from siamtrackers.
Related Issues (20)
- Pretrained model of Updatenet Resnet256 HOT 1
- 关于Siamese tracker的搜参 HOT 1
- nanotrackv3.pth HOT 1
- 博主您好,请问我自己转出来的nanotrackv1版本的onnx文件backbone部分的大小900多kb可能是什么原因呢 HOT 1
- Lighttrack代码 HOT 1
- COCO百度云链接失效 HOT 1
- 求TrTr预训练模型,给的下载链接打不开了 HOT 1
- How the nanotrack onnx files works without opencv HOT 1
- Nanotrack应用到了lighttrack那里?有应用到一次性NAS么? HOT 1
- 可否提供更多实验的backbone的预训练权重? HOT 3
- 重新训练NanoTrackV3时,报错:NaN or Inf found in input tensor. HOT 6
- baidu Datasets Access HOT 1
- ValueError HOT 10
- AttributeError: 'list' object has no attribute 'items' HOT 1
- nanotrackv3 转 ncnn模型,pth转pt,head的推理结果异常nan HOT 11
- Training regiment? HOT 4
- NanoTrack训练代码问题
- NanoTrack模型代码中没有找到使用颈部网络的地方 HOT 2
- nanotrack HOT 2
- 关于nanotrack训练的一些问题
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 siamtrackers.