keras

Deep Learning for humans

APACHE-2.0 License

Downloads
14M
Stars
60.9K
Committers
1.3K
View Code on GitHub Visit Website
Ecosystems: Tensorflow, Python, Keras, PyTorch

Bot releases are hidden (Show)

keras - Keras Release 2.11.0 RC2

Published by qlzh727 almost 2 years ago

What's Changed

Full Changelog: https://github.com/keras-team/keras/compare/v2.11.0-rc1...v2.11.0-rc2

keras - Keras Release 2.11.0 RC1

Published by qlzh727 almost 2 years ago

Please see the release history at https://github.com/tensorflow/tensorflow/releases/tag/v2.11.0-rc1 for more details.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras/compare/v2.10.0...v2.11.0-rc1

keras - Keras Release 2.10.0

Published by qlzh727 about 2 years ago

Please see the release history at https://github.com/tensorflow/tensorflow/releases/tag/v2.10.0 for more details.

Full Changelog: https://github.com/keras-team/keras/compare/v2.9.0...v2.10.0

keras - Keras Release 2.10.0 RC1

Published by qlzh727 about 2 years ago

Please see the release history at https://github.com/tensorflow/tensorflow/releases/tag/v2.10.0-rc3 for more details.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras/compare/v2.9.0-rc0...v2.10.0-rc1

keras - Keras Release 2.9.0

Published by qlzh727 over 2 years ago

Please see the release history at https://github.com/tensorflow/tensorflow/releases/tag/v2.9.0 for more details.

Full Changelog: https://github.com/keras-team/keras/compare/v2.8.0...v2.9.0

keras - Keras Release 2.9.0 RC2

Published by qlzh727 over 2 years ago

What's Changed

Full Changelog: https://github.com/keras-team/keras/compare/v2.9.0-rc1...v2.9.0-rc2

keras - Keras Release 2.9.0 RC1

Published by qlzh727 over 2 years ago

What's Changed

Full Changelog: https://github.com/keras-team/keras/compare/v2.9.0-rc0...v2.9.0-rc1

keras - Keras Release 2.9.0 RC0

Published by qlzh727 over 2 years ago

Please see https://github.com/tensorflow/tensorflow/blob/r2.9/RELEASE.md for Keras release notes.

Major Features and Improvements

  • tf.keras:
    • Added tf.keras.applications.resnet_rs models. This includes the ResNetRS50, ResNetRS101, ResNetRS152, ResNetRS200, ResNetRS270, ResNetRS350 and ResNetRS420 model architectures. The ResNetRS models are based on the architecture described in Revisiting ResNets: Improved Training and Scaling Strategies
    • Added tf.keras.optimizers.experimental.Optimizer. The reworked optimizer gives more control over different phases of optimizer calls, and is easier to customize. We provide Adam, SGD, Adadelta, AdaGrad and RMSprop optimizers based on tf.keras.optimizers.experimental.Optimizer. Generally the new optimizers work in the same way as the old ones, but support new constructor arguments. In the future, the symbols tf.keras.optimizers.Optimizer/Adam/etc will point to the new optimizers, and the previous generation of optimizers will be moved to tf.keras.optimizers.legacy.Optimizer/Adam/etc.
    • Added L2 unit normalization layer tf.keras.layers.UnitNormalization.
    • Added tf.keras.regularizers.OrthogonalRegularizer, a new regularizer that encourages orthogonality between the rows (or columns) or a weight matrix.
    • Added tf.keras.layers.RandomBrightness layer for image preprocessing.
    • Added APIs for switching between interactive logging and absl logging. By default, Keras always writes the logs to stdout. However, this is not optimal in a non-interactive environment, where you don't have access to stdout, but can only view the logs. You can use tf.keras.utils.disable_interactive_logging() to write the logs to ABSL logging. You can also use tf.keras.utils.enable_interactive_logging() to change it back to stdout, or tf.keras.utils.is_interactive_logging_enabled() to check if interactive logging is enabled.
    • Changed default value for the verbose argument of Model.evaluate() and Model.predict() to "auto", which defaults to verbose=1 for most cases and defaults to verbose=2 when used with ParameterServerStrategy or with interactive logging disabled.
    • Argument jit_compile in Model.compile() now applies to Model.evaluate() and Model.predict(). Setting jit_compile=True in compile() compiles the model's training, evaluation, and inference steps to XLA. Note that jit_compile=True may not necessarily work for all models.
    • Added DTensor-related Keras APIs under tf.keras.dtensor namespace. The APIs are still classified as experimental. You are welcome to try it out. Please check the tutoral and guide on https://www.tensorflow.org/ for more details about DTensor.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras/compare/v2.8.0-rc0...v2.9.0-rc0

keras - Keras Release 2.8.0

Published by qlzh727 over 2 years ago

Please see the release history at https://github.com/tensorflow/tensorflow/releases/tag/v2.8.0 for more details.

keras - Keras Release 2.8.0 RC1

Published by qlzh727 over 2 years ago

What's Changed

Full Changelog: https://github.com/keras-team/keras/compare/v2.8.0-rc0...v2.8.0-rc1

keras - Keras Release 2.8.0 RC0

Published by qlzh727 almost 3 years ago

Please see https://github.com/tensorflow/tensorflow/blob/r2.8/RELEASE.md for Keras release notes.

  • tf.keras:
    • Preprocessing Layers
      • Added a tf.keras.layers.experimental.preprocessing.HashedCrossing
        layer which applies the hashing trick to the concatenation of crossed
        scalar inputs. This provides a stateless way to try adding feature crosses
        of integer or string data to a model.
      • Removed keras.layers.experimental.preprocessing.CategoryCrossing. Users
        should migrate to the HashedCrossing layer or use
        tf.sparse.cross/tf.ragged.cross directly.
      • Added additional standardize and split modes to TextVectorization.
        • standardize="lower" will lowercase inputs.
        • standardize="string_punctuation" will remove all puncuation.
        • split="character" will split on every unicode character.
      • Added an output_mode argument to the Discretization and Hashing
        layers with the same semantics as other preprocessing layers. All
        categorical preprocessing layers now support output_mode.
      • All preprocessing layer output will follow the compute dtype of a
        tf.keras.mixed_precision.Policy, unless constructed with
        output_mode="int" in which case output will be tf.int64.
        The output type of any preprocessing layer can be controlled individually
        by passing a dtype argument to the layer.
    • tf.random.Generator for keras initializers and all RNG code.
      • Added 3 new APIs for enable/disable/check the usage of
        tf.random.Generator in keras backend, which will be the new backend for
        all the RNG in Keras. We plan to switch on the new code path by default in
        tf 2.8, and the behavior change will likely to cause some breakage on user
        side (eg if the test is checking against some golden nubmer). These 3 APIs
        will allow user to disable and switch back to legacy behavior if they
        prefer. In future (eg tf 2.10), we expect to totally remove the legacy
        code path (stateful random Ops), and these 3 APIs will be removed as well.
    • tf.keras.callbacks.experimental.BackupAndRestore is now available as
      tf.keras.callbacks.BackupAndRestore. The experimental endpoint is
      deprecated and will be removed in a future release.
    • tf.keras.experimental.SidecarEvaluator is now available as
      tf.keras.utils.SidecarEvaluator. The experimental endpoint is
      deprecated and will be removed in a future release.
    • Metrics update and collection logic in default Model.train_step() is now
      customizable via overriding Model.compute_metrics().
    • Losses computation logic in default Model.train_step() is now
      customizable via overriding Model.compute_loss().
    • jit_compile added to Model.compile() on an opt-in basis to compile the
      model's training step with XLA. Note that
      jit_compile=True may not necessarily work for all models.

What's Changed

New Contributors

Full Changelog: https://github.com/keras-team/keras/compare/v2.7.0-rc0...v2.8.0-rc0

keras - Keras Release 2.7.0

Published by qlzh727 almost 3 years ago

Please see the release history at https://github.com/tensorflow/tensorflow/releases/tag/v2.7.0 for more details.

keras - Keras Release 2.7.0 RC2

Published by qlzh727 almost 3 years ago

What's Changed

Full Changelog: https://github.com/keras-team/keras/compare/v2.7.0-rc1...v2.7.0-rc2

keras - Keras Release 2.7.0 RC1

Published by qlzh727 about 3 years ago

Cherrypicked the documentation update for functional model slicing.

keras - Keras Release 2.7.0 RC0

Published by qlzh727 about 3 years ago

keras - Keras Release 2.6.0

Published by qlzh727 about 3 years ago

Keras 2.6.0 is the first release of TensorFlow implementation of Keras in the present repo.

The code under tensorflow/python/keras is considered legacy and will be removed in future releases (tf 2.7 or later). For any user who import tensorflow.python.keras, please update your code to public tf.keras instead.

The API endpoints for tf.keras stay unchanged, but are now backed by the keras PIP package. All Keras-related PRs and issues should now be directed to the GitHub repository keras-team/keras.

For the detailed release notes about tf.keras behavior changes, please take a look for tensorflow release notes.

keras - Keras Release 2.6.0 RC3

Published by qlzh727 about 3 years ago

Keras Release 2.6.0 RC3 fix a security issue for loading keras models via yaml, which could allow arbitrary code execution.

keras - Keras Release 2.6.0 RC2

Published by qlzh727 about 3 years ago

Keras 2.6.0 RC2 is a minor bug-fix release.

  1. Fix TextVectorization layer with output_sequence_length on unknown input shapes.
  2. Output int64 by default from Discretization layer.
  3. Fix serialization of Hashing layer.
  4. Add more explicit error message for instance type checking of optimizer.
keras - Keras Release 2.6.0 RC1

Published by qlzh727 about 3 years ago

Keras 2.6.0 RC1 is a minor bug-fix release

  1. Pin the Protobuf version to 3.9.2 which is same as the version used by Tensorflow.
keras - Keras Release 2.6.0 RC0

Published by qlzh727 about 3 years ago

Keras 2.6.0 is the first release of TensorFlow implementation of Keras in the present repo.

The code under tensorflow/python/keras is considered legacy and will be removed in future releases (tf 2.7 or later). For any user who import tensorflow.python.keras, please update your code to public tf.keras instead.

The API endpoints for tf.keras stay unchanged, but are now backed by the keras PIP package. All Keras-related PRs and issues should now be directed to the GitHub repository keras-team/keras.

For the detailed release notes about tf.keras behavior changes, please take a look for tensorflow release notes.

Package Rankings
Top 0.08% on Pypi.org
Top 1.06% on Conda-forge.org
Top 10.3% on Anaconda.org
Top 3.57% on Proxy.golang.org
Related Projects
DeepLearningExamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reprod...

02 May 2018 13,307
TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating poin...

20 Sep 2022 1,482
Deep-Learning-in-Production

In this repository, I will share some useful notes and references about deploying deep learning-b...

03 May 2018 4,294
TensorLayerX

TensorLayerX: A Unified Deep Learning and Reinforcement Learning Framework for All Hardwares, Bac...

03 Dec 2021 537
pytorch-styleguide

An unofficial styleguide and best practices summary for PyTorch

14 Apr 2019 1,909
Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

31 Aug 2020 9,151
Keras-OneClassAnomalyDetection

[5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresp...

06 Jan 2019 127
deepvision

PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/impleme...

31 Jan 2023 33
animus

Minimalistic framework to run machine learning experiments.

12 Jan 2022 27
rapidae

Explore, compare and develop autoencoder models with a back-end agnostic framework

21 Sep 2023 3