Pinned issues
Issues
- 3
batch_normalization issue when trying to load model
#19577 opened by aman977381 - 5
Getting Wrong output even though vgg16 model showing 95% val_accuracy
#19612 opened by novabyte-games - 6
Need help to understand the logic here
#19579 opened by IshanRattan - 7
MLX Backend
#19571 opened by lkarthee - 4
- 6
🗺️ Keras Development Roadmap
#19519 opened by fchollet - 6
Unable to create model with Keras=3.2.1 and jax[cpu]=0.4.26
#19539 opened by veb-101 - 16
Custom loss defined as a class instance vs function
#19601 opened by mthiboust - 4
MeanIoU and its child classes throwing error when used with `ignore_class`
#19524 opened by savindi-wijenayaka - 8
Run validation every N batches
#19562 opened by mpetteno - 9
Model fails to train with Linux and Keras 3.3.2
#19623 opened by jonbry - 4
Conv3D crash when the data_format is 'channels_first' and using Tensorflow backend
#19591 opened by AGFACBNNR - 3
bug in TF _keepdims?
#19630 opened by jonbarron - 2
no `argpartition` op in keras.ops
#19547 opened by jonbarron - 2
keras autocast casts numpy int types to float
#19629 opened by roebel - 4
Returning backend.set_learning_phase
#19597 opened by NikitaShubin - 2
Compatible with .ogg format
#19627 opened by jrobbl - 4
Keras 3 with Pytorch backend ERROR - Layer 'lstm_cell' expected 3 variables, but received 0 variables during loading. Expected: ['kernel', 'recurrent_kernel', 'bias']
#19615 opened by sunilsarolkarcds - 3
Support Infinite PyDataset
#19528 opened by LarsKue - 1
The source code URL in the documentation leads to a non-existent page.
#19620 opened by shadi-danhash-elte - 1
keras.ops.linalg.cholesky can't JIT
#19622 opened by jonbarron - 2
- 3
- 1
import keras error (V3.3.2) (kaggle Notebook)
#19614 opened by suede299 - 2
Add support for jnp.linalg.slogdet
#19605 opened by jonbarron - 3
There seem some differences between the source code from PyPI and that tagged with v3.2.1 in GitHub.
#19587 opened by Zhaopudark - 1
keras.layers.Layer.call method fails when building keras model with functional API
#19607 opened by pma-pmot - 0
Torch 2.3.0 (next ver) fails with AttributeError: 'Parameter' object has no attribute 'fget'
#19602 opened by sampathweb - 1
Misspelled link.
#19593 opened by albert-github - 2
imdb.load_data function returns a python list instead of ndarray object
#19596 opened by amletodisalle - 6
[BUG] Conflicting `loss_weights` implementation in Keras3 for single output case.
#19582 opened by proneetsharma - 1
Rescaling layer on input problems / ValueError: Layer node index out of bounds. inbound_layer = <InputLayer name=keras_tensorCLONE, built=True>
#19589 opened by AmmarkoV - 3
Support for np.vectorize?
#19550 opened by jonbarron - 2
`keras.ops.nan_to_num` doesn't have a `nan` argument
#19573 opened by jonbarron - 1
Support for jax.scipy?
#19549 opened by jonbarron - 3
- 2
RuntimeError when using keras 3 with pytorch backend in example of VAE model
#19560 opened by OnlyBelter - 1
CategoryEncoding layer with output_mode count as part of a model no longer working in TensorFlow 2.16.1
#19567 opened by Dobiasd - 3
Round trip keras saving changes model's output format with dict inputs => single output
#19565 opened by LukeWood - 1
Pickle support via __reduce__ API
#19554 opened by LukeWood - 3
Possibly unintended regression (though maybe intended?)
#19561 opened by LukeWood - 2
no `select` in keras.ops
#19548 opened by jonbarron - 1
Cannot load nested model / model with sub-model
#19559 opened by a-mch - 5
- 1
Try to change backend to ‘torch’, but still 'tensorflow'.
#19542 opened by ranck626 - 1
it is no longer possible to see the input shape of a layer with keras.utils.plot_model when setting `show_shapes=True`
#19536 opened by Rygone - 10
Spectral Normalization failure in Torch backend.
#19527 opened by dryglicki - 2
- 2
IntegerLookup with XLA Compilation Fails to Enable JIT in TensorFlow 2.16.1 and Keras 3.2.1
#19521 opened by jacob-talroo - 3