Comments (8)
按我经验来看学习率需要按你调的batch size同步修改,学习率影响很大
from awesome-backbones.
按我经验来看学习率需要按你调的batch size同步修改,学习率影响很大
那请问学习率和batch-size的关系一般是怎样的呢,我的数据集大概训练集8000+张,测试集2000+张。batch-size调低则相应的lr是应该是低一点还是高一点?请问up项目里的这个*32/64是什么意思?和你原始设置的batch-size=32是否有联系?我看swin 源码里的学习率是_C.TRAIN.BASE_LR = 5e-4(batch-size=32)
from awesome-backbones.
batch-size调低则相应的lr是应该是低一点,配置文件中batch 32和公式中的32对应,你先同步替换更改学习率再测试准确率是否有提升
from awesome-backbones.
batch-size调低则相应的lr是应该是低一点,配置文件中batch 32和公式中的32对应,你先同步替换更改学习率再测试准确率是否有提升
感觉变化不大...我甚至还换了台设备,在修改batch-size的同时也修改了学习率,无论是调整公式里的32还是直接把学习率调小,结果都很惨...不知道是什么原因(如图)....另外还有个问题想问up,项目里的模型可以从checkpoint恢复训练吗?好像在设置文件里没有看见这行
from awesome-backbones.
我比较喜欢用1e-4你可以试试,调lr是个杂活。恢复训练是支持的,训练那块有教程你可以看看https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/How_to_train.md
from awesome-backbones.
我比较喜欢用1e-4你可以试试,调lr是个杂活。恢复训练是支持的,训练那块有教程你可以看看https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/How_to_train.md
好的我再调调,请问up“是否每个Epoch更新学习率”这个设置true或false会在哪方面产生不同呢...
T^T多谢
from awesome-backbones.
我在B站视频中有讲你可以看看。还有一个很重要的和提升精度有关的操作是你可以选择性的关掉一些图像增强操作,经测试有时候那些增强反而污染数据
from awesome-backbones.
你们recall都大于1吗
from awesome-backbones.
Related Issues (20)
- 代码框为空点击单张图片调试,软件会卡住并闪退 HOT 1
- 测试单张图片时报错 HOT 6
- Mobilevit: RuntimeError: mat1 and mat2 shapes cannot be multiplied (16x640 and 320x1000) HOT 1
- 运行Quick start demo出现问题
- 关于修改输入尺寸 HOT 2
- 批量图像检测结果的保存 HOT 2
- RepVGG部署模型 HOT 1
- 【已解决】No module named 'utils.history' HOT 1
- 测试单张图片时报错: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU. HOT 2
- loss
- 模型保存
- 细粒度分类算法 HOT 2
- 制作数据集信息文件时,发生ValueError:too mach values to unpack(expected 2) HOT 2
- 加载权重文件失败 HOT 1
- 训练时数据数目与数据集的数目不匹配 HOT 1
- upup,为啥只有训练loss和验证acc HOT 4
- 数据集问题 HOT 1
- 能否批量输出类激活图 HOT 2
- 是否支持训练视频分类?
- 怎么用训练好的模型批量预测呀 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 awesome-backbones.