Skip to content

/ keras

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.

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

Clear current search query, filters, and sorts
38 Open 50 Closed
38 Open 50 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
Making a bot which posts the documentation page in htlm if a pull request changed it Enhancement stat:contributions welcome
#12382 opened Mar 2, 2019 by gabrieldemarmiesse
1
Do not re-seed NumPy's global RNG whenever possible (NEP-19) backend:tensorflow stat:contributions welcome type:bug/performance
#12258 opened Feb 12, 2019 by YuriyGuts 3 of 3
2
Support for mixed precision training stat:contributions welcome type:docs
#12249 opened Feb 10, 2019 by lminer
5
Convert the docstrings of examples in `examples/*` to use Markdown formatting Good first issue stat:contributions welcome type:docs
#12219 opened Feb 6, 2019 by gabrieldemarmiesse
13
Implement K.foldl and K.foldr for the cntk backend. stat:contributions welcome type:feature
#12168 opened Jan 29, 2019 by gabrieldemarmiesse
Implement K.ctc_decode for the cntk backend. stat:contributions welcome type:feature
#12167 opened Jan 29, 2019 by gabrieldemarmiesse
Implement K.ctc_batch_cost for the cntk backend. stat:contributions welcome type:feature
#12166 opened Jan 29, 2019 by gabrieldemarmiesse
implement K.ctc_label_dense_to_sparse for the cntk backend. stat:contributions welcome type:feature
#12165 opened Jan 29, 2019 by gabrieldemarmiesse
Implement K.arange for the cntk backend. Good first issue stat:contributions welcome type:feature
#12164 opened Jan 29, 2019 by gabrieldemarmiesse
5
implement K.cumsum and K.cumprod for the cntk backend. Good first issue stat:contributions welcome type:feature
#12163 opened Jan 29, 2019 by gabrieldemarmiesse
5
Support tuple/list as `axis` argument in `BatchNormalization` layer (see implementation in `tf.keras.layers.BatchNormalization`). stat:contributions welcome type:feature
#12126 opened Jan 24, 2019 by gabrieldemarmiesse
1
Add automated check for import style. Enhancement stat:contributions welcome
#12110 opened Jan 23, 2019 by gabrieldemarmiesse
16
__getitem__ gets called too many times Enhancement Good first issue stat:contributions welcome
#12082 opened Jan 20, 2019 by kdx2
14
TypeError: unsupported operand type(s) for +: 'NoneType' and 'int' in new version Tensorflow backend backend:tensorflow stat:contributions welcome type:bug/performance
#12067 opened Jan 18, 2019 by frozenxia
4
Bug when loading a KerasClassifier from a h5py file stat:contributions welcome type:bug/performance
#12032 opened Jan 13, 2019 by PhilipMay
4
Tensorboard histogram_freq switching from GPU to CPU to write logs backend:tensorflow stat:contributions welcome type:bug/performance
#11957 opened Dec 31, 2018 by mcguile
1
Is there any way to set different learning rates for different different layers of a CNN model in Keras? stat:contributions welcome type:feature
#11934 opened Dec 26, 2018 by gyheart
5
Making tensorboard find embedding layers in sub-models. Enhancement stat:contributions welcome
#11831 opened Dec 9, 2018 by gabrieldemarmiesse
Set up versioning of the docs. Enhancement stat:contributions welcome
#11783 opened Dec 2, 2018 by gabrieldemarmiesse
3
Write a test to check for absence of API changes, and enforce validation by API owners in case of changes. Enhancement stat:contributions welcome
#11781 opened Dec 2, 2018 by gabrieldemarmiesse
Add a canonical sequence-to-sequence example 1D convnets. Enhancement stat:contributions welcome
#11780 opened Dec 2, 2018 by gabrieldemarmiesse
1
Add masking support to convolution layers (or at least determine whether it is feasible). Enhancement stat:contributions welcome
#11779 opened Dec 2, 2018 by gabrieldemarmiesse
1
Create tutorial on how to deploy Keras models to Android. Enhancement stat:contributions welcome
#11778 opened Dec 2, 2018 by gabrieldemarmiesse
4
Write a cross-backend way (backend method) to check whether a certain tensor depends on a certain other tensor. Enhancement stat:contributions welcome
#11777 opened Dec 2, 2018 by gabrieldemarmiesse
Improve performance (GPU utilization) of `multi_gpu_model` for small models. Enhancement stat:contributions welcome
#11776 opened Dec 2, 2018 by gabrieldemarmiesse
1
ProTip! Adding no:label will show everything without a label.
You can’t perform that action at this time.