Skip to content

Issues: keras-team/keras

🚀 Contributing to Keras 🚀
#18442 opened Jul 14, 2023 by fchollet
Open 52
Keras 2 <> Keras 3 incompatibilities
#18467 opened May 29, 2023 by fchollet
Open 17
🗺️ Keras Development Roadmap
#19519 opened Apr 15, 2024 by fchollet
Open 12
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

237 Open 11,902 Closed
237 Open 11,902 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Floating point exception (core dumped) with onednn opt on tensorflow backend
#20335 opened Oct 9, 2024 by Shuo-Sun20
@sachinprasadhs
Custom activation functions cause TensorFlow to crash
#20333 opened Oct 8, 2024 by AtticusBeachy
@sachinprasadhs
2
[Keras Ops] einops.rearrange() Equivalent
#20332 opened Oct 8, 2024 by DavidLandup0
@mehtamansi29
Tensorflow MultiWorkerMirroredStrategy and input dictionaries keras-team-review-pending Pending review by a Keras team member. type:Bug
#20329 opened Oct 7, 2024 by dryglicki
@sachinprasadhs
1
Outdated documentation (and code?) regarding Stateful RNNs keras-team-review-pending Pending review by a Keras team member. type:docs Need to modify the documentation
#20327 opened Oct 5, 2024 by ageron
@sachinprasadhs
3
Reason for the recently added shape restriction in MultiHeadAttention keras-team-review-pending Pending review by a Keras team member. type:support User is asking for help / asking an implementation question. Stackoverflow would be better suited.
#20324 opened Oct 4, 2024 by aarbabi
@mehtamansi29
3
EarlyStopping() does not return the model weights corresponding to the epoch with the best value of the monitored quantity stat:awaiting response from contributor type:Bug
#20323 opened Oct 4, 2024 by GeorgeOrfanidis
@mehtamansi29
7
Loading weights into custom LSTM layer fails: Layer 'lstm_cell' expected 3 variables, but received 0 variables during loading. Expected: ['kernel', 'recurrent_kernel', 'bias'] type:Bug
#20322 opened Oct 4, 2024 by lbortolotti
@mehtamansi29
4
Model Accuracy Degradation by 6x when Switching TF_USE_LEGACY_KERAS from "1" (Keras 2) to "0" (Keras 3) stat:awaiting response from contributor type:support User is asking for help / asking an implementation question. Stackoverflow would be better suited.
#20320 opened Oct 3, 2024 by Lw-Cui
@mehtamansi29
3
Attention layer does not accept output of previous layers in functional API type:Bug
#20318 opened Oct 2, 2024 by jorgenorena
@mehtamansi29
2
Keras fails to load TextVectorization layer from .keras file keras-team-review-pending Pending review by a Keras team member. type:Bug
#20314 opened Oct 1, 2024 by harsha7addanki
@mehtamansi29
When using exponential as the activation function, the outputs of the CPU and GPU have large differences stat:awaiting response from contributor type:Bug
#20310 opened Oct 1, 2024 by PhyllisJi
@mehtamansi29
1
Keras SpectralNormalization and stop_gradient type:Bug
#20309 opened Oct 1, 2024 by dryglicki
@sachinprasadhs
2
ValueError when loading models that reuse weights type:Bug
#20307 opened Sep 30, 2024 by K1521
@mehtamansi29
2
loss_weights depending on epoch number type:Bug
#20294 opened Sep 26, 2024 by LucaSCostanzo
1
@mehtamansi29
2
Training performance degradation after switching from Keras 2 mode to Keras 3 using Tensorflow stat:awaiting keras-eng Awaiting response from Keras engineer type:bug/performance
#20283 opened Sep 24, 2024 by DavidHidde
@sachinprasadhs
2
Custom Pooling Layer for CNN stat:awaiting response from contributor type:Bug
#20282 opened Sep 24, 2024 by Rivilyo-Sitanggang
@mehtamansi29
3
Image Pooling Layer stat:awaiting response from contributor
#20281 opened Sep 24, 2024 by Rivilyo-Sitanggang
@sachinprasadhs
1
Using keras model with torch.func.jacrev gives zero gradients
#20279 opened Sep 23, 2024 by smartArancina
@sachinprasadhs
4
Incompatibility of compute_dtype with complex-valued inputs type:feature The user is asking for a new feature.
#20278 opened Sep 23, 2024 by jhoydis
@mehtamansi29
1
GRU + Large recurrent_dropout Bug keras-team-review-pending Pending review by a Keras team member. type:Bug
#20276 opened Sep 21, 2024 by nokados
@mehtamansi29
4
Incompatibility in 'tf.GradientTape.watch' of TensorFlow 2.17 in Keras 3.4.1 stale stat:awaiting response from contributor type:Bug
#20274 opened Sep 20, 2024 by yajuna
@mehtamansi29
2
A local file was found, but it seems to be incomplete or outdated because the auto file hash does not match the original value of ... type:Bug
#20271 opened Sep 19, 2024 by edge7Lux
@VarunS1997
Keras v3 equivalent for get_output_at(num) layers stat:contributions welcome A pull request to fix this issue would be welcome. type:support User is asking for help / asking an implementation question. Stackoverflow would be better suited.
#20267 opened Sep 18, 2024 by felixdittrich92
@sachinprasadhs
4
Model weights not saved if a custom layer class contains a list of layers named self._layers type:Bug
#20260 opened Sep 16, 2024 by mpetteno
@mehtamansi29
2
ProTip! no:milestone will show everything without a milestone.