Neupy changelog

Changelog History

• v0.8.2 Changes

  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 Changes

  March 30, 2019

  Main changes:

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

• v0.8.0 Changes

  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 Changes

  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 Changes

  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 Changes

  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 Changes

  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 Changes

  October 12, 2018

  🐛 Bugs:

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

• v0.6.4 Changes

  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 Changes

  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)