Comments (7)
Replacing AlphaDropout
with Dropout
works. Also training with tf.GradientTape
and AlphaDropout
works.
from keras.
@sachinprasadhs Thank you for indicating this issue for further investigation. I formatted code in a better way so it can be used formally. Feel free to let me know if i need to run some test or to contribute in some other way to get this resolved.
from keras.
Your code snippet works fine with the latest versions of Keras and TensorFlow: https://colab.research.google.com/drive/10y6whIDDy8tDJZ9EOprIYEyM-Nq7REbv?usp=sharing
I suppose it may be a Windows specific issue, but that's not what the stack trace suggests. Just try updating Keras and TensorFlow.
from keras.
@fchollet Confirmed that the issue has disappeared with tf==2.16.1 and Keras==3.1.1 even on Windows 11.
from keras.
@markodjordjic , Thanks for confirming that the issue is resolved with the latest package, could you please close the issue as well if you don't have any questions.
from keras.
@sachinprasadhs Done.
from keras.
Are you satisfied with the resolution of your issue?
Yes
No
from keras.
Related Issues (20)
- Inconsistent results from distributed training of models containing `SeparableConv2D`
- hasattr() raising ValueError when used with input and output attributes of a keras layer
- Tensorboard callback is blocking process HOT 2
- I'm afraid that the Bidirectional Wrapper will not work in Keras Functional Api. HOT 4
- Subclassing a model, writing a custom train_step, and distributed training in Tensorflow
- Possible JIT compilation bug with JAX HOT 3
- This works in keras 2.15 with TensorFlow 2.15 but does not 3.5 with TensorFlow 2.17: multiple lookup layer types in inputs HOT 1
- Keras model deserialization issue HOT 5
- How to make dynamic assetions in Keras v3? HOT 3
- Is there a keras 3 equivalent to serialization.DisableSharedObjectScope()? HOT 4
- layers.GRU returns wrong shaped output with GPU HOT 3
- Obscure validation failure due to `_use_cached_eval_dataset` HOT 5
- Wrong binary accuracy with Jax HOT 4
- tf.keras.datasets.cifar10.load_data - FileNotFoundError: [Errno 2] No such file or directory HOT 15
- fix: Densenet Documentation HOT 1
- Cannot get result() since the metric has not yet been built HOT 1
- Keras different versions have numerical deviations when using pretrain model HOT 1
- ops.image.affine_transform() does not work as a layer in GPU HOT 5
- Use Keras to load dataset HOT 3
- Nested sequentials broken in 3.5 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.