All Versions
14
Latest Version
Avg Release Cycle
71 days
Latest Release
494 days ago

Changelog History
Page 2

  • v2.1.5 Changes

    March 06, 2018

    Areas of improvement

    • ๐Ÿ› Bug fixes.
    • ๐Ÿ†• New APIs: sequence generation API TimeseriesGenerator, and new layer DepthwiseConv2D.
    • ๐Ÿ‘ท Unit tests / CI improvements.
    • ๐Ÿ“š Documentation improvements.

    API changes

    • โž• Add new sequence generation API keras.preprocessing.sequence.TimeseriesGenerator.
    • โž• Add new convolutional layer keras.layers.DepthwiseConv2D.
    • ๐Ÿ‘ Allow weights from keras.layers.CuDNNLSTM to be loaded into a keras.layers.LSTM layer (e.g. for inference on CPU).
    • โž• Add brightness_range data augmentation argument in keras.preprocessing.image.ImageDataGenerator.
    • Add validation_split API in keras.preprocessing.image.ImageDataGenerator. You can pass validation_split to the constructor (float), then select between training/validation subsets by passing the argument subset='validation' or subset='training' to methods flow and flow_from_directory.

    ๐Ÿ’ฅ Breaking changes

    • โ™ป๏ธ As a side effect of a refactor of ConvLSTM2D to a modular implementation, recurrent dropout support in Theano has been dropped for this layer.

    Credits

    ๐Ÿš€ Thanks to our 28 contributors whose commits are featured in this release:

    @DomHudson, @Dref360, @VitamintK, @abrad1212, @ahundt, @bojone, @brainnoise, @bzamecnik, @caisq, @cbensimon, @davinnovation, @farizrahman4u, @fchollet, @gabrieldemarmiesse, @khosravipasha, @ksindi, @lenjoy, @masstomato, @mewwts, @ozabluda, @paulpister, @sandpiturtle, @saralajew, @srjoglekar246, @stefangeneralao, @taehoonlee, @tiangolo, @treszkai

  • v2.1.4 Changes

    February 13, 2018

    Areas of improvement

    • ๐Ÿ› Bug fixes
    • ๐ŸŽ Performance improvements
    • ๐Ÿ‘Œ Improvements to example scripts

    API changes

    • Allow for stateful metrics in model.compile(..., metrics=[...]). A stateful metric inherits from Layer, and implements __call__ and reset_states.
    • ๐Ÿ‘Œ Support constants argument in StackedRNNCells.
    • Enable some TensorBoard features in the TensorBoard callback (loss and metrics plotting) with non-TensorFlow backends.
    • โž• Add reshape argument in model.load_weights(), to optionally reshape weights being loaded to the size of the target weights in the model considered.
    • โž• Add tif to supported formats in ImageDataGenerator.
    • Allow auto-GPU selection in multi_gpu_model() (set gpus=None).
    • โฑ In LearningRateScheduler callback, the scheduling function now takes an argument: lr, the current learning rate.

    ๐Ÿ’ฅ Breaking changes

    • 0๏ธโƒฃ In ImageDataGenerator, change default interpolation of image transforms from nearest to bilinear. This should probably not break any users, but it is a change of behavior.

    Credits

    ๐Ÿš€ Thanks to our 37 contributors whose commits are featured in this release:

    @DalilaSal, @Dref360, @GalaxyDream, @GarrisonJ, @Max-Pol, @May4m, @MiliasV, @MrMYHuang, @N-McA, @Vijayabhaskar96, @abrad1212, @ahundt, @angeloskath, @bbabenko, @bojone, @brainnoise, @bzamecnik, @caisq, @cclauss, @dsadulla, @fchollet, @gabrieldemarmiesse, @ghostplant, @gorogoroyasu, @icyblade, @kapsl, @kevinbache, @mendesmiguel, @mikesol, @myutwo150, @ozabluda, @sadreamer, @simra, @taehoonlee, @veniversum, @yongtang, @zhangwj618

  • v2.1.3 Changes

    January 16, 2018

    Areas of improvement

    • ๐ŸŽ Performance improvements (esp. convnets with TensorFlow backend).
    • Usability improvements.
    • ๐Ÿ“„ Docs & docstrings improvements.
    • ๐Ÿ†• New models in the applications module.
    • ๐Ÿ› Bug fixes.

    API changes

    • โšก๏ธ trainable attribute in BatchNormalization now disables the updates of the batch statistics (i.e. if trainable == False the layer will now run 100% in inference mode).
    • โž• Add amsgrad argument in Adam optimizer.
    • โž• Add new applications: NASNetMobile, NASNetLarge, DenseNet121, DenseNet169, DenseNet201.
    • โž• Add Softmax layer (removing need to use a Lambda layer in order to specify the axis argument).
    • โž• Add SeparableConv1D layer.
    • In preprocessing.image.ImageDataGenerator, allow width_shift_range and height_shift_range to take integer values (absolute number of pixels)
    • Support return_state in Bidirectional applied to RNNs (return_state should be set on the child layer).
    • The string values "crossentropy" and "ce" are now allowed in the metrics argument (in model.compile()), and are routed to either categorical_crossentropy or binary_crossentropy as needed.
    • ๐Ÿ‘ Allow steps argument in predict_* methods on the Sequential model.
    • โž• Add oov_token argument in preprocessing.text.Tokenizer.

    ๐Ÿ’ฅ Breaking changes

    • ๐Ÿ‘€ In preprocessing.image.ImageDataGenerator, shear_range has been switched to use degrees rather than radians (for consistency). This should not actually break anything (neither training nor inference), but keep this change in mind in case you see any issues with regard to your image data augmentation process.

    Credits

    ๐Ÿš€ Thanks to our 45 contributors whose commits are featured in this release:

    @Dref360, @OliPhilip, @TimZaman, @bbabenko, @bdwyer2, @berkatmaca, @caisq, @decrispell, @dmaniry, @fchollet, @fgaim, @gabrieldemarmiesse, @gklambauer, @hgaiser, @hlnull, @icyblade, @jgrnt, @kashif, @kouml, @lutzroeder, @m-mohsen, @mab4058, @manashty, @masstomato, @mihirparadkar, @myutwo150, @nickbabcock, @novotnj3, @obsproth, @ozabluda, @philferriere, @piperchester, @pstjohn, @roatienza, @souptc, @spiros, @srs70187, @sumitgouthaman, @taehoonlee, @tigerneil, @titu1994, @tobycheese, @vitaly-krumins, @yang-zhang, @ziky90

  • v2.1.2 Changes

    December 01, 2017

    Areas of improvement

    • ๐Ÿ› Bug fixes and performance improvements.
    • API improvements in Keras applications, generator methods.

    API changes

    • ๐Ÿ‘‰ Make preprocess_input in all Keras applications compatible with both Numpy arrays and symbolic tensors (previously only supported Numpy arrays).
    • ๐Ÿ‘ Allow the weights argument in all Keras applications to accept the path to a custom weights file to load (previously only supported the built-in imagenet weights file).
    • steps_per_epoch behavior change in generator training/evaluation methods:
      • If specified, the specified value will be used (previously, in the case of generator of type Sequence, the specified value was overridden by the Sequence length)
      • If unspecified and if the generator passed is a Sequence, we set it to the Sequence length.
    • ๐Ÿ‘ Allow workers=0 in generator training/evaluation methods (will run the generator in the main process, in a blocking way).
    • Add interpolation argument in ImageDataGenerator.flow_from_directory, allowing a custom interpolation method for image resizing.
    • Allow gpus argument in multi_gpu_model to be a list of specific GPU ids.

    ๐Ÿ’ฅ Breaking changes

    • The change in steps_per_epoch behavior (described above) may affect some users.

    Credits

    ๐Ÿš€ Thanks to our 26 contributors whose commits are featured in this release:

    @Alex1729, @alsrgv, @apisarek, @asos-saul, @athundt, @cherryunix, @dansbecker, @datumbox, @de-vri-es, @drauh, @evhub, @fchollet, @heath730, @hgaiser, @icyblade, @jjallaire, @knaveofdiamonds, @lance6716, @luoch, @mjacquem1, @myutwo150, @ozabluda, @raviksharma, @rh314, @yang-zhang, @zach-nervana