Comments (8)
输入的热力图都进行了检查,都是正确的
是centernet对位置信息不敏感?因为牙齿编号的分布相对固定
from centernet-pytorch.
我也是,置信度只有0.00几,好诡异
from centernet-pytorch.
这个区分的不强力,因为用的focal和热力图,建议换一个
from centernet-pytorch.
大佬你是指换个检测网络,不用centernet吗
from centernet-pytorch.
是
from centernet-pytorch.
想着anchor-free试试效果,没想到分类不行==大佬有啥推荐的吗?
from centernet-pytorch.
不是想着anchor-free的问题,是centernet的问题,用yolox或者8吧
from centernet-pytorch.
我也是,训练单个样本,置信度只有0.00几
from centernet-pytorch.
Related Issues (20)
- 结果mAP很小很小,也就1%,这是什么原因啊 HOT 3
- 请问我改mobilenetv3的时候运行到第7批次就自动停止了是怎么回事呢 HOT 3
- ResNet18权重文件 HOT 1
- 请问如何输出mAP_75和mAP_90 HOT 2
- 导儿,可以加入mosaic, mixup数据增强吗? HOT 2
- 关于summery.py中测试CenterNet_HourglassNet HOT 2
- 怎么修改做下游任务比如关键点识别 HOT 1
- 为什么用训练时用测试集验证map为67%,在get_map中用测试集验证达到81%,同一个数据集怎么差别这么大 HOT 7
- 修改input_shape后,还能使用centernet_resnet50_voc.pth预训练权重吗 HOT 4
- 关于hourglassnet
- mAP
- mAP计算过程中预测结果异常 HOT 10
- 改动centernet的head HOT 2
- 视频检测没有框 HOT 1
- 为什么训练到第六轮停止训练了 HOT 5
- 单张图片包含3000个单类别物体,检测发现map指标很低,是因为centernet算法检测数量限制吗? HOT 2
- 导,我在训练时的验证集的mAP值,与重新单独测试的mAP值差距非常大,大概10个点左右,你遇到过佬?
- total_c_loss=nan, total_r_loss=nan
- 导儿,训练时候开启map值计算之后,下一轮训练卡住,已经定位是get map_txt函数中的问题导致,程序卡在数据加载的地方 HOT 4
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 centernet-pytorch.