Comments (7)
yangxue0827
commented on June 1, 2024
1
随便设置只要你的显存足够，这两个参数是为了控制显存的。 @Tangzixia
from r2cnn_faster-rcnn_tensorflow.
Tangzixia
commented on June 1, 2024
谢谢你的回复，收到了，不过还有一个问题，就是在训练的过程中训练loss一直不收敛，请问有什么解决办法吗？可以讲一下你怎么训练的吗？
from r2cnn_faster-rcnn_tensorflow.
yangxue0827
commented on June 1, 2024
你这样是正常的 @Tangzixia
from r2cnn_faster-rcnn_tensorflow.
Tangzixia
commented on June 1, 2024
主要是这样训练到最后算出来的mAP只有60多，效果不怎么好，请问一下有什么方法可以让loss到后期降下来吗？
from r2cnn_faster-rcnn_tensorflow.
yangxue0827
commented on June 1, 2024
这个代码就只有60多的性能，它是用来做baseline的，没有任何trick。 @Tangzixia
from r2cnn_faster-rcnn_tensorflow.
Tangzixia
commented on June 1, 2024
好的，谢谢啦，那我理解一下代码啦，非常感谢
from r2cnn_faster-rcnn_tensorflow.
zdgithub
commented on June 1, 2024
我在自己的数据集上训练的，loss一直没收敛，请问是迭代次数不够，还是学习率太大了吗（学习率参数我没有改）？
@yangxue0827 @Tangzixia 麻烦两位了
from r2cnn_faster-rcnn_tensorflow.
Related Issues (20)
- resizing of images
- Use with CPU HOT 1
- Error in export libs/export_pbs/exportPb.py and test_exportpb.py
- Try to run "python setup.py build_ext --inplace" in Windows 10 HOT 3
- Try to run "python setup.py build_ext --inplace" in Windows 10
- Performance on DOTA_v1.0 val set
- 关于数据标注的问题 HOT 1
- linux no GPU，how to Compile， HOT 1
- 您好，我在运行train.py后，一直显示 restore model HOT 1
- 运行emo_rh时，结果restore model 不显示结果
- 关于训练结果的问题 HOT 5
- @wangning7149 老哥你解决了么？
- Error pop outs when adjusting parameter in cfgs.py.
- The inference result is very different from what you expected. Which part should be modified?. HOT 1
- Does it run on windows ?
- upgrade to TF2
- ValueError: could not convert string to float: imagesource:GoogleEarth
- Cannot use train.crop.py
- CPU inference using pre-trained weights
- [[{{node get_batch/batch}}]]
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 r2cnn_faster-rcnn_tensorflow.