keras-team keras issues

keras-team / keras

Deep Learning for humans

http://keras.io/

Apache License 2.0

61k stars 19.34k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Progress bar crash when empty dataset

#19687 stridge-cruxml opened 4 hours ago
0
Fix dtype test for `trace`

#19686 james77777778 closed 2 hours ago
2
Fix masking in merge layers.

#19685 hertschuh closed 3 hours ago
0
More Customisation in utils.ProgBar

#19684 stellarpower opened 10 hours ago
0
Example Doubt

#19683 emi-dm opened 12 hours ago
0
Add `training=False` behavior for float8-trained `Dense` and `EinsumDense`

#19682 james77777778 closed 10 hours ago
1
Add `scan` op

#19681 james77777778 opened 21 hours ago
1
mlx - add argpartition to numpy

#19680 lkarthee closed 10 hours ago
1
Fix for rendering issues with Keras Layers API Documentation (Convolution and Pooling layers)

#19679 pranshupant closed 10 hours ago
2
Feature request: keras.ops.linalg.lstsq

#19678 jonbarron opened 1 day ago
1
No module named 'keras.src.engine'

#19677 UmerElsaharty opened 1 day ago
6
To Keras community: What interpretations do you have for these curves?

#19676 sondosaabed closed 1 day ago
3
On JAX, Keras replaces any exception inside `call` method of `keras.Model` subclass with misleading error

#19675 burnpanck closed 1 day ago
2
JAX array conversion failure in Keras model prediction

#19674 Qazalbash closed 8 hours ago
3
Add axis parameter to dice loss

#19673 td-jakubl opened 1 day ago
2
Update python example dtype in string_lookup.py

#19672 SuryanarayanaY closed 1 day ago
1
Have the plan to support fp8 inference?

#19671 lingzhi98 opened 1 day ago
6
TypeError when loading Keras 2 legacy models with nested outputs in Keras 3

#19670 torzdf closed 1 day ago
2
Bugfix: Flatten nested outputs in legacy keras2 .h5 models

#19669 torzdf closed 1 day ago
6
TextVectorization does not convert Cyrillic characters to lowercase

#19668 Ybisalt opened 2 days ago
2
Regression: Cannot export model with bilinear UpSampling2D and dynamic inputs

#19667 pwuertz closed 2 days ago
1
mlx - handle int64 and uint64 for scatter and cum*

#19666 lkarthee closed 1 day ago
1
ops.copy makes object (arrays only?) immutable

#19665 Mrutyunjay01 closed 3 days ago
1
switch tensorflow for macOS

#19664 lkarthee closed 3 days ago
1
Fix bug in `model.export()` when inputs in a structure.

#19663 hertschuh closed 4 days ago
1
Shape error for some use cases of `binary_crossentropy`.

#19662 albertaillet opened 4 days ago
3
TypeError: Could not locate class 'adam'. Make sure custom classes are decorated with `@keras.saving.register_keras_serializable()`

#19661 mpetteno closed 3 days ago
1
StringLookup does not return expected dtype for multi_hot

#19660 Toku11 closed 1 day ago
1
add packaging requirement

#19659 albertaillet closed 4 days ago
1
loss and val_loss decreasing

#19658 ayatirfann opened 5 days ago
1
mlx - merge master into mlx

#19657 lkarthee closed 4 days ago
1
Fix static shape for `take_along_axis` with Tensorflow.

#19656 hertschuh closed 5 days ago
1
Revert "Bump the python group with 2 updates"

#19655 fchollet closed 6 days ago
0
Bump the python group with 2 updates

#19654 dependabot[bot] closed 6 days ago
0
Bump the github-actions group with 2 updates

#19653 dependabot[bot] closed 6 days ago
0
mlx - implement segment_sum and segment_max

#19652 lkarthee opened 6 days ago
3
Fix plot_model

#19651 fchollet closed 1 week ago
0
How to save Scikit-Learn-Keras Model into a Persistence File (pickle/hd5/json/yaml) with Keras 3

#19650 CAW9 opened 1 week ago
12
Numeric diff of BatchNormalization layer when migrate from Keras2 to keras3

#19649 cliu-nuro closed 6 days ago
5
The torch backend for jnp.cholesky should use torch.linalg.cholesky, not torch.cholesky

#19648 jonbarron closed 6 days ago
1
[Proposal] API tuning for use_cudnn in LSTM/other layers

#19647 LukeWood opened 1 week ago
5
RaggedTensor

#19646 markub3327 opened 1 week ago
4
Enable cudnn rnns when dropout is set

#19645 fchollet closed 1 week ago
1
LSTM layer with dropout does not use fast CuDNN implementation in Keras 3

#19644 giulatona closed 1 week ago
1
Fix bug in layernorm with rms_scaling=True

#19643 SuryanarayanaY closed 3 days ago
1
Layernorm not supporting axis [-2, 3]

#19642 lllllllllaa closed 3 days ago
2
support conv3d on cpu for TF

#19641 haifeng-jin closed 1 week ago
1
Return a tuple from `ops.shape` with the Torch backend.

#19640 hertschuh closed 1 week ago
0
Unusual behavior of `predict` for JAX backend

#19639 AakashKumarNain closed 5 days ago
20
The loss becomes neagative from positive values dring taining loop

#19638 yijianSU22 opened 1 week ago
4