Skip to content

Releases: google/qkeras

QKeras 0.9.0

20 Feb 00:25
Compare
Choose a tag to compare

Major Features

  • qtools energy support for global_average_pooling layer.

  • Added layers for sequence model, LSTM, RNN, GRU.

  • Added activation and weight compression notebook.

  • Added QSeparableConv2D class

    • Renamed previous QSeparableConv2D layer to QMobileNetSeparableConv2D
    • It is more consistent with Keras SeparableConv2D API
  • Bugfix of QDepthwiseConv2D.

  • Added an experimental QAdaptiveActivation layer to learn quantizer integer bits from activation values.

  • Added weight sparsity calculation to model qstats.

  • Enabled AutoQKeras to use custom Keras Tuners.

  • Fixed various bugs in AutoQKeras.

Thanks to our contributors

This release contains contributions from many people at Google and CERN.

QKeras 0.8.0

19 Jun 22:57
Compare
Choose a tag to compare

Major Features

  • Automatic quantization using QKeras;

  • Stochastic behavior (including stochastic rounding) is disabled during inference;

  • LeakyReLU for quantized_relu;

  • Qtools for estimating effort to perform inference;

    • Qtools will estimate the sizes and types of operations to perform inference, with its data sizes compatible with high-level synthesis datatypes. For example, quantized_bits and quantized_relu bits and int_bits from Qtools will match exactly ac_fixed datatypes (if you rely on QKeras alone, the correct datatype should be ac_fixed<bits, int_bits+is_negative, is_negative>, where is_negative has to be inferred from the other parameters of the quantizer.
  • Other bug fixes and enhancement.

Thanks to our contributors

This release contains contributions from many people at Google and CERN.

QKeras 0.7.4

11 Apr 00:04
Compare
Choose a tag to compare

Major Features

A patch with better weight initialization for https://github.com/google/qkeras/releases/tag/v0.7.0

QKeras 0.7.0

27 Mar 00:49
Compare
Choose a tag to compare

Major Features

  • Enhancement of binary and ternary quantization as well as their stochastic counterparts for parameters and activation.
  • Add auto scaling for low-bitwidth quantization.
  • Add jupyter notebook.

Thanks to our Contributors

This release contains contributions from many people at Google.

QKeras 0.6.0

11 Mar 21:18
Compare
Choose a tag to compare

Major Features

  • Use Tensorflow 2.1+ and tf.keras.
    • QKeras does not support the standalone Keras anymore.
    • Use Python 3.
  • Support APIs of pruning and PrunableLayer from tensorflow_model_optimization for model sparsity.
  • Add QBatchNormalization layer.

Thanks to our Contributors

This release contains contributions from many people at Google and CERN.

QKeras 0.5.0

12 Jan 08:36
Compare
Choose a tag to compare

QKeras 0.5.0 uses Tensorflow version < 2 and standalone Keras as backend.

Major Features

This is the first release of QKeras.

Notes

In the next release, we will support TensorFlow 2+ and tf.keras.

Thanks to our Contributors

This release contains contributions from many people at Google.