Comments (9)
@t-kalinowski , I just updated the latest release tag in the landing page
from keras.
Any advice on what may be causing the issue? Let me know if there is any information that I can provide to help troubleshoot the issue.
This code is known to work, so it's likely a bad initialization. Some common steps you can take:
- Just restart and try again (with a different random seed)
- Lower the learning rate by 2x
- Lower dropout rate (0.5 -> 0.25)
from keras.
@fchollet I am able to reproduce this. I haven't had a chance to dig into the root cause yet, but I can confirm that this is a bug in Keras 3; the same code produces a model that trains just fine w/ TF 2.15 + Keras 2.
from keras.
Looking into it.
from keras.
I have fixed a related issue with dataset shuffling. Can you try installing v3.3.3 and checking if your code works with that version?
from keras.
Thanks! Looks like it's fixed now. I can confirm the model trains fine with Keras v3.3.3
from keras.
Looks like v3.3.3 fixed the issue. Thanks for all of your help!
from keras.
Are you satisfied with the resolution of your issue?
Yes
No
from keras.
By the way, just noticed that github release tagged v3.3.3 has a typo in the title (Kears
vs Keras
): Kears 3.3.3
Maybe this is the reason v3.3.2 is still listed as the "latest release" on the repo landing page?
from keras.
Related Issues (20)
- Compatible with .ogg format HOT 2
- keras autocast casts numpy int types to float HOT 2
- bug in TF _keepdims? HOT 3
- keras.ops.cross doesn't propagate input sizes HOT 1
- GSOC '24 Project? HOT 1
- Dice loss - incorrect HOT 2
- The loss becomes neagative from positive values dring taining loop HOT 4
- Unusual behavior of `predict` for JAX backend HOT 19
- Layernorm not supporting axis [-2, 3] HOT 2
- LSTM layer with dropout does not use fast CuDNN implementation in Keras 3 HOT 1
- RaggedTensor HOT 4
- [Proposal] API tuning for use_cudnn in LSTM/other layers HOT 5
- The torch backend for jnp.cholesky should use torch.linalg.cholesky, not torch.cholesky HOT 1
- Numeric diff of BatchNormalization layer when migrate from Keras2 to keras3 HOT 5
- How to save Scikit-Learn-Keras Model into a Persistence File (pickle/hd5/json/yaml) with Keras 3 HOT 13
- loss and val_loss decreasing HOT 1
- StringLookup does not return expected dtype for multi_hot HOT 1
- TypeError: Could not locate class 'adam'. Make sure custom classes are decorated with `@keras.saving.register_keras_serializable()` HOT 1
- Shape error for some use cases of `binary_crossentropy`. HOT 3
- ops.copy makes object (arrays only?) immutable HOT 1
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.