Comments (12)
XinWangg
commented on June 12, 2024
你训练几个epoch呢？
from mobilenetv3-ssd.
CWF-999
commented on June 12, 2024
200个epoch,我的batch_size设置的32,5的话太不稳定了
…------------------ 原始邮件 ------------------
发件人: "XinWang-bip"<[email protected]>;
发送时间: 2019年11月6日(星期三) 下午3:43
收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>;
抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>;
主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11)
你训练几个epoch呢？
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
from mobilenetv3-ssd.
XinWangg
commented on June 12, 2024
我训练了120个epoch，batchsize设为64，loss到6.多就不降了。
| |
王鑫
|
|
邮箱：[email protected]
|
签名由 网易邮箱大师 定制
在2019年11月06日 19:24，winfred 写道：
200个epoch,我的batch_size设置的32,5的话太不稳定了
…------------------ 原始邮件 ------------------
发件人: "XinWang-bip"<[email protected]>;
发送时间: 2019年11月6日(星期三) 下午3:43
收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>;
抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>;
主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11)
你训练几个epoch呢？
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
from mobilenetv3-ssd.
CWF-999
commented on June 12, 2024
我到3.62就开始跳动了，下不去了。给更小的学习率也没用
from mobilenetv3-ssd.
XinWangg
commented on June 12, 2024
Loss3.62的效果怎样，我用loss6的模型测试了voc2007效果很差
| |
王鑫
|
|
邮箱：[email protected]
|
签名由 网易邮箱大师 定制
在2019年11月06日 19:32，winfred 写道：
我到3.62就开始跳动了，下不去了。给更小的学习率也没用
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
from mobilenetv3-ssd.
CWF-999
commented on June 12, 2024
也很差mAp0.52
…------------------ 原始邮件 ------------------
发件人: "XinWang-bip"<[email protected]>;
发送时间: 2019年11月6日(星期三) 晚上10:09
收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>;
抄送: "陈文峰"<[email protected]>; "Author"<[email protected]>;
主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11)
Loss3.62的效果怎样，我用loss6的模型测试了voc2007效果很差
| |
王鑫
|
|
邮箱：[email protected]
|
签名由 网易邮箱大师 定制
在2019年11月06日 19:32，winfred 写道：
我到3.62就开始跳动了，下不去了。给更小的学习率也没用
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
from mobilenetv3-ssd.
liukaigua
commented on June 12, 2024
请问您给的训练策略能把模型loss收敛到多小？我顶天了到3.7左右就再也降不下去了，不管是加epoch,调整学习率，还是调整batch_size都无法降低了？请问这是什么原因呢？
请问你训练的是哪个数据集？我训练的VOC数据集，在VOC2007_test上的Loss最低也就降到4.36。
from mobilenetv3-ssd.
CWF-999
commented on June 12, 2024
VOC2007 和VOC2012一起训练
…------------------ 原始邮件 ------------------
发件人: "lsccccc"<[email protected]>;
发送时间: 2019年11月18日(星期一) 中午11:48
收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>;
抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>;
主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11)
请问您给的训练策略能把模型loss收敛到多小？我顶天了到3.7左右就再也降不下去了，不管是加epoch,调整学习率，还是调整batch_size都无法降低了？请问这是什么原因呢？
请问你训练的是哪个数据集？我训练的VOC数据集，在VOC2007_test上的Loss最低也就降到4.36。
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
from mobilenetv3-ssd.
liukaigua
commented on June 12, 2024
VOC2007 和VOC2012一起训练
…
------------------ 原始邮件 ------------------ 发件人: "lsccccc"<[email protected]>; 发送时间: 2019年11月18日(星期一) 中午11:48 收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>; 抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>; 主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11) 请问您给的训练策略能把模型loss收敛到多小？我顶天了到3.7左右就再也降不下去了，不管是加epoch,调整学习率，还是调整batch_size都无法降低了？请问这是什么原因呢？ 请问你训练的是哪个数据集？我训练的VOC数据集，在VOC2007_test上的Loss最低也就降到4.36。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
还想请问一下您训练的学习率是多少，训练多少个epoch？不胜感激！
from mobilenetv3-ssd.
CWF-999
commented on June 12, 2024
用的余弦退火学习率调整策略，300epoch,初始0.01
…------------------ 原始邮件 ------------------
发件人: "lsccccc"<[email protected]>;
发送时间: 2019年11月18日(星期一) 下午3:59
收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>;
抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>;
主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11)
VOC2007 和VOC2012一起训练
…
------------------ 原始邮件 ------------------ 发件人: "lsccccc"<[email protected]>; 发送时间: 2019年11月18日(星期一) 中午11:48 收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>; 抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>; 主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11) 请问您给的训练策略能把模型loss收敛到多小？我顶天了到3.7左右就再也降不下去了，不管是加epoch,调整学习率，还是调整batch_size都无法降低了？请问这是什么原因呢？ 请问你训练的是哪个数据集？我训练的VOC数据集，在VOC2007_test上的Loss最低也就降到4.36。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
还想请问一下您训练的学习率是多少，训练多少个epoch？不胜感激！
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
from mobilenetv3-ssd.
liukaigua
commented on June 12, 2024
用的余弦退火学习率调整策略，300epoch,初始0.01
…
------------------ 原始邮件 ------------------ 发件人: "lsccccc"<[email protected]>; 发送时间: 2019年11月18日(星期一) 下午3:59 收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>; 抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>; 主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11) VOC2007 和VOC2012一起训练 … ------------------ 原始邮件 ------------------ 发件人: "lsccccc"<[email protected]>; 发送时间: 2019年11月18日(星期一) 中午11:48 收件人: "shaoshengsong/MobileNetV3-SSD"<[email protected]>; 抄送: "陈文峰"<[email protected]>;"Author"<[email protected]>; 主题: Re: [shaoshengsong/MobileNetV3-SSD] 请问您给的训练策略能把模型loss收敛到多小？ (#11) 请问您给的训练策略能把模型loss收敛到多小？我顶天了到3.7左右就再也降不下去了，不管是加epoch,调整学习率，还是调整batch_size都无法降低了？请问这是什么原因呢？ 请问你训练的是哪个数据集？我训练的VOC数据集，在VOC2007_test上的Loss最低也就降到4.36。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. 还想请问一下您训练的学习率是多少，训练多少个epoch？不胜感激！ — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.
感谢，我再去试试。
from mobilenetv3-ssd.
shaoshengsong
commented on June 12, 2024
It is recommended that git clone this version
https://github.com/shaoshengsong/MobileNetV3-SSD-Compact-Version
loss =1.8,1,9
from mobilenetv3-ssd.
Related Issues (20)
- Error Message
- can not recognize the label which is the capital letters. HOT 1
- pretrained model links HOT 1
- 在VOC数据集上训练遇见报错 HOT 6
- 在自己的数据集上训练出错
- 请问导出onnx模型，可以使用opencv-dnn模块加载吗
- Loss does not go down HOT 1
- Mobilenetv3_py is outdated
- V3是否有在imagenet预训练过？没有预训练的效果很差 HOT 1
- MobilenetV3SSD vs YOLOV3
- seek help! TypeError: expected str, bytes or os.PathLike object, not NoneType HOT 2
- code style
- **预加载之前训练的模型**
- 请问我可以将SSD300改成SSD640吗？就是直接将utils.py里的缩放代码那里改变一下
- 为什么使用mbv3_small的预训练会出现乱码
- 利用COCO训练出现问题 HOT 1
- Please share weights outside mainland China HOT 2
- where to download mb3-ssd-lite-Epoch-99-Loss-2.5194434596402613.pth ??? HOT 1
- 请问视频实时识别FPS帧率是多少？
- 有windows版本吗？
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 mobilenetv3-ssd.