Comments (9)
Hey,
Can you try lowering the value of lambda? Since we experimented mostly with problems of up to 500 classes, lambda was never higher than 50. Perhaps for 3k classes it doesn't need such a high value of lambda. This in turn would probably lead to very large gradients somewhere in the training (after cross-entropy is sufficiently small) that moves the outputs to nan
.
I'd say start with lambda=10
and then increase/decrease to see how performance varies. What network are you using and which codebase (caffe or pytorch), and with which optimizer (adam or SGD)?
from confusion.
ok. I would try to decay lambda.
I finetune resnet-50 on pretrained model in caffe.
from confusion.
I increase/decay lambda. Both go into NAN finally after different iterations. I try to add gradient clipping but cause a terrible accuracy.
from confusion.
Can you share your prototxt?
from confusion.
Train_val prototxt is as follows:
train_val.txt
from confusion.
Thanks. Can you also share the prototxt you generate while using confusion loss? Also, does this go to NaN even without the loss?
from confusion.
I have updated the train_val prototxt with confusion loss(the last uploaded prototxt is a mistake ). Without confusion loss, the training process acts normally.
from confusion.
Just took a look at your prototxt. Since I don't have this dataset, I can't test it myself, but I'd give 2 suggestions - i) try with a larger batch-size (32, 64 or 128 if possible), and ii) try with \lambda = 0.01, 0.1, 1 and so on.
from confusion.
For limited gpu memory, I set batch-size to 24 and set iter_size to 4(so batch size is 24 * 4 actually). That lambda is less than 1 is what I have not tried. Thanks!
from confusion.
Related Issues (12)
- Implementation issue for bilinear VGG HOT 1
- How to reproduce the result of densenet161 HOT 6
- about train problems HOT 2
- How to avoid log zero in EntropicConfusion ?
- Logits or softmax probabilities HOT 3
- About the training process HOT 3
- [HELP] : The loss_train is always 5.3833 HOT 7
- is RPN_PRE_NMS_TOP_N per image?
- Wish HOT 1
- pytorch loss HOT 1
- Ask for help๏ผ Compile error! HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from confusion.