Comments (6)
Could you post the model? This may be a hyperparameter issue.
from keras.
Yes, could you post a script to repro this (I assume you used the Kaggle Otto challenge data). It looks like an exploding gradient, and there are many things that could trigger one (most likely a learning rate issue?).
In general when faced with this type of problem, you should try different learning rates and learning rate decay, different optimizers, and try to introduce regularization techniques such as L1 regularization (supported by all optimizers in Keras), gradient clipping, BatchNormalization, etc.
from keras.
model = Sequential()
model.add(Dense(20, 64, init='uniform', activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, 64, init='uniform', activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(64, 1, init='uniform', activation='softmax')
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd)
I cannt post whole the script since I overwrote it but this is the same model you give as an example. Only I use the data from some where else.
However, the strange thing is, it goes smoothly to some degree but suddenly it diverges. It is the first time I observed such a thing. I also used Adagrad and it works nice but this is strange anyway.
from keras.
Also I see that time to time for Adagrad , model stucks to very high loss from the beginning but it goes well for different runs.
from keras.
I guess the learning rate becomes negative.
https://github.com/fchollet/keras/blob/master/keras/optimizers.py#L48
from keras.
yeah perfectly rational then it should be corrected.
from keras.
Related Issues (20)
- no `select` in keras.ops HOT 2
- Support for jax.scipy? HOT 1
- Support for np.vectorize? HOT 3
- Pickle support via __reduce__ API HOT 1
- Cannot load nested model / model with sub-model HOT 1
- RuntimeError when using keras 3 with pytorch backend in example of VAE model HOT 2
- Possibly unintended regression (though maybe intended?) HOT 3
- Run validation every N batches HOT 6
- Round trip keras saving changes model's output format with dict inputs => single output HOT 3
- CategoryEncoding layer with output_mode count as part of a model no longer working in TensorFlow 2.16.1 HOT 1
- MLX Backend HOT 4
- `keras.ops.nan_to_num` doesn't have a `nan` argument HOT 2
- batch_normalization issue when trying to load model HOT 2
- Need help to understand the logic here HOT 1
- [BUG] Conflicting `loss_weights` implementation in Keras3 for single output case. HOT 6
- CategoryEncoding layer one hot indices cast to float in graph execution HOT 3
- Any method to get formulation of functions without seeking into source? HOT 2
- There seem some differences between the source code from PyPI and that tagged with v3.2.1 in GitHub. HOT 3
- Rescaling layer on input problems / ValueError: Layer node index out of bounds. inbound_layer = <InputLayer name=keras_tensorCLONE, built=True> HOT 1
- Conv3D crash when the data_format is 'channels_first' and using Tensorflow backend HOT 3
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 keras.