Comments (6)
是的 最后detectron2的数据读取格式全部转化成了统一的xyxy格式
from centerx.
from centerx.
加油💪
from centerx.
最近使用detectron2上使用balloon数据集进行单分类检测时候,
当num_classes设置为1,在json文件中将我自己的类category_id 设置为0,预测出来AP一直徘徊0-5左右
当将json里面category_id 设置为1时候,预测出来AP也在0-5左右(和coco数据集id排序一致,没有0)
当我设置num_class=80预测单分类,等多个epoch之后采取测试这样保证id预测出来是正确的测试结果为AP=50
可以问下您这里大概哪个地方有问题需要怎么改呢
from centerx.
盲猜可能是BASE_LR的问题,
num_class=80用默认的BASE_LR可能是没有问题的,
num_class=1的时候把BASE_LR调低点试试再跑吧
from centerx.
原来学习率是5e-5了 用的ADAMW的优化器,我调到5e-6 和5e-3都试了下,AP结果还是一样很小很小,就是不知道为啥分80类时候结果是正常的分1类就崩了。。。。
from centerx.
Related Issues (20)
- 导出onnx之后如何转trt HOT 1
- 请问有没有训练好的权重模型?
- 自定义数据集如何使用该工程 HOT 1
- TypeError: __init__() takes 1 positional argument but 4 were given HOT 1
- TypeError: _write_metrics() missing 1 required positional argument: 'data_time' HOT 2
- AP 大于1?
- 转caffe遇到问题 HOT 2
- 自定义数据集
- 训练问题 HOT 3
- Inference/demo.py的一个小问题 HOT 1
- ttf supported?
- issues HOT 3
- SWA in vanilla Detectron2 HOT 2
- 小白提问请问这个有人体关键点检测嘛
- whyCUDA out of memory. Tried to allocate 130.00 MiB (GPU 1; 7.80 GiB total capacity; 5.91 GiB already allocated; 33.56 MiB free; 6.09 GiB reserved in total by PyTorch)
- 自己数据训练问题
- 关于对于keypoints修改的问题
- 编译detectron2出现ninja: build stopped: subcommand failed如何解决?
- N个数据集所对应的N个教师模型,在datasets中如何摆放N个数据集(每个数据集均转成COCO格式)?
- Requests for segmentation or key point detection. 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 centerx.