All Versions
10
Latest Version
Avg Release Cycle
47 days
Latest Release
229 days ago

Changelog History

  • v0.8.2

    April 04, 2019

    Main changes:

    • 👌 Improved functionality for layer/network copying
    • ➕ Added repeat function
    • 🛠 Fixed output shape for the conv layers when input is unknown
    • 🛠 Typo fixes
  • v0.8.1

    March 30, 2019

    Main changes:

    • ➕ Added Tensorflow 1.13 support
    • ➕ Added DropBlock layer
    • ➕ Added define method for all layers
  • v0.8.0

    January 28, 2019

    Main changes:

    • 🆕 New design for the layer graphs and layers
    • 🔄 Changed inline operators > (still supported) to >> and lists to| operator for parallel connections
    • Added 2 new step decay algorithms, namely exponential_decay and polynomial_decay
    • 🆕 New regularizers
    • 🆕 New signals functionality, can be extended with classes (signals attribute)
    • ⚡️ Tensorflow optimizers are used instead of self-implemented functions
    • ➕ Added GroupNorm layer
    • 🔄 Changed behavior for the the predict methods
    • ➕ Added show method to the networks
    • ➕ Added plot_errors for the optimizers with better and more accurate visualizations

    Small changes:

    • ⚡️ The error parameters for optimizers was renamed to loss
    • 🔄 Changed summary format in the logs
    • Removed training_errors and validation_errors and it were replaced with new errors attribute
    • 📇 Renamed the prediction_error method to score

    Misc:

    • ♻️ Big code refactoring
    • 👍 Better exceptions

    ✂ Removed

    • ➕ Add-ons were removed
    • 🔧 Tuple of integer as network configuration
    • ✂ Removed RBFKmeans
    • Removed train_end_signal and epoch_end_signal
    • ✂ Removed plots.error_plot function
    • ✂ Removed plots.network_structure function
  • v0.7.3

    January 17, 2019
    • 🛠 Fixed problem that occurred when GNG was loaded from pickled file. Issue #229
    • 👌 Improved representation for the GNG graph elements
    • ➕ Added extra exceptions into GNG graph methods in order to get informative fail when unexpected action was applied
  • v0.7.2

    December 13, 2018

    🔄 Changes:

    • ➕ Added missing dilation rates for ResNet-50 architecture
    • 🛠 Fixed fan computation for weight initializers
    • ➕ Added variable initializer in the predict method
    • 🔄 Change XavierNormal to HeNormal default initializer
  • v0.7.1

    December 10, 2018

    🔄 Changes:

    • Speed up network initialization via lazy parameter initialization using tensorflow's tensors instead numpy's arrays
    • Global pooling layer accepts two string arguments that point to different tensorflow functions.
    • 🛠 Fixes for the reshape layer when used with unknown input shape
    • 🛠 Fixed cross entropy loss functions for spatial inputs
    • ✂ Removed input blocker during the training
    • Combined GradientDescent and MinibatchGradientDescent into one class GradientDescent
  • v0.7.0

    December 02, 2018

    🔄 Changes:

    • 🚚 Backend was moved to Tensorflow
    • Pickle storage for the weights has been replaced with HDF5
    • 🔄 Changed order of the dimensions for the convolutional filter (channel expected to be in the last dimension)
    • 🚚 The compile method was removed
    • ➕ Added wolfe search to conjugate gradient
    • 🛠 Fixes for the training algorithms

    ✂ Removed:

    • Linear models
    • Quickprop training algorithm
    • Ensemble algorithms
  • v0.6.5

    October 12, 2018

    🐛 Bugs:

    • 🛠 Fixed iterative updates for discrete hopfield networks: #218
  • v0.6.4

    March 26, 2018

    🔋 Features:

    • ➕ Added Growing Neural Gas (GNG) algorithm
    • ➕ Added 2 new improvements to the base GNG algorithms

    🐛 Bug:

    • 0️⃣ Set up default value for epoch_time in order to prevent crashes when training was stopped on first iteration.
  • v0.6.3

    February 03, 2018

    🛠 Fixes:

    • 💅 Use old table-style, otherwise table breaks for some of the font styles and it doesn't look good in ipython notebook
    • ⚡️ Adam optimizer fix for GPU (#200)