Comments (7)
This is not normal. In my experiments, the loss decreased to less than 1.0 after about 10000 iterations when batchsize = 32. Are you using the given training data or your own dataset?
from drbox.
I using the given data and coverted the airplane dataset into LMDB, then starting the training. However the training loss change from 7.0+ up to 300.0+! after about 70000 iterations. I still not clear why this happened. The training setting keep same as the repository provided, just modified the dataset path.
from drbox.
What do you see in src/caffe/util/? rbox_util.cpp and rbox_util.cpp.ship are used in different tasks. I renamed them 19 days ago after I uploaded all the code 21 days ago. So I want to know your code is downloaded before or after this date. If your code is the newest version, I will re-training my network and reply you soon.
from drbox.
@liulei01 My training loss of ship task doesn't decrease and keeps 8.0 ~ 9.0 between iterations of 5000 ~ 20000. I do as the README instruction and used the rbox_util.cpp.ship and set batchsize = 32, use only 1 GPU. Is this loss normal?
@gitUserGoodLeaner Have you figured out the problem?
from drbox.
@gitUserGoodLeaner I encounter the same problem and changing the "base_lr" from 0.001 to 0.0001 works for me.
from drbox.
from drbox.
@liulei01 My training loss of ship task doesn't decrease and keeps 8.0 ~ 9.0 between iterations of 5000 ~ 20000. I do as the README instruction and used the rbox_util.cpp.ship and set batchsize = 32, use only 1 GPU. Is this loss normal?
@gitUserGoodLeaner Have you figured out the problem?
I am facing the same problem. The loss remains at around 7.1.
Have you found a solution meanwhile?
from drbox.
Related Issues (20)
- The Use of Functions SelectRotatedTarget.m HOT 4
- make error /usr/bin/ld: cannot find -l boost_thread
- Deployment problem HOT 3
- make error ---Headache problem ina long time HOT 5
- Why loss is close to 0.1, but the effect is very poor? HOT 2
- coding missing
- cannot find trainval.txt
- Not able to run deployment
- Does there any altnertive source to download the data? HOT 4
- Question on GPU build with GFORCE RTX 2080 HOT 1
- more instruction for labeling tool HOT 2
- Wrong Code
- Database Annotation
- python.h no such file HOT 1
- what‘s the impact of resolution
- librbox.so的源码
- IndexError: index 1 is out of bounds for axis 0 with size 1
- Custom datasets to train the model, but predictive deployment has no results
- The model was trained with a custom dataset and found that nothing was learned
- Can be used on X-ray images
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 drbox.