google/qkeras

Issues

• QKeras fails due to missing modules and numpy error message with latest TensorFlow version 2.16.1

  #130 opened 7 months ago by lp247
  2

• Quantisation aware training worsens autoencoder performance when quantising the output of the encoder.

  #135 opened 3 months ago by Berk-Bilgin
  0

• How to perform inference on an hardware with alpha='auto'

  #134 opened 5 months ago by lcit
  0

• Upgrade to keras v3?

  #131 opened 7 months ago by makoeppel
  1

• TypeError: Could not locate class 'QConv2D'.

  #126 opened a year ago by OliverFaust
  4

• Get scale value after Full Integer Quantization

  #132 opened 7 months ago by torukskywalker
  5

• Can QKeras support Full integer quantization

  #111 opened 2 years ago by KaiyiZhang-uo
  8

• Unpredictable quantization with quantized_bits and an alpha value of None

  #129 opened 8 months ago by qdlmcfresh
  0

• Attribute `__name__` missing from QActivation layer

  #127 opened 9 months ago by Brainz22
  0

• Vivado HLS ap_fixed emulation

  #75 opened 3 years ago by eneriz-daniel
  1

• Adding QKeras to conda forge

  #119 opened a year ago by jmduarte
  0

• Difference between Qkeras model and Keras model

  #116 opened 2 years ago by sandeep1404
  9

• How do keras and qkeras versions correspond to each other?

  #115 opened 2 years ago by Prince5867
  0

• How can I get the scale of the QAdaptiveActivation layer

  #114 opened 2 years ago by KaiyiZhang-uo
  0

• TFLite compatibility

  #113 opened 2 years ago by WaterBoiledPizza
  0

• Add a custom layer with a bitwise operation

  #112 opened 2 years ago by AnouarITI
  0

• `pyparser` vs `pyparsing`

  #109 opened 2 years ago by jmduarte
  0

• How do I save an AutoQKeras model that a different script can load?

  #108 opened 2 years ago by alexberian
  0

• Cannot convert 6.0 to EagerTensor of dtype int64

  #107 opened 2 years ago by makoeppel
  0

• Only Qconv layer's output tensors are quantized

  #106 opened 2 years ago by laumecha
  0

• Params not quantized after model_save_quantized_weights function

  #105 opened 2 years ago by laumecha
  4

• Very low accuracy following AutoQKeras notebook and CUDA error

  #102 opened 2 years ago by laumecha
  1

• When I use QKeras: Failed to load in-memory CUBIN: CUDA_ERROR_NO_BINARY_FOR_GPU: no kernel image is available for execution on the device [Op:Abs]

  #104 opened 2 years ago by laumecha
  2

• Inference of QKeras models

  #99 opened 2 years ago by RatkoFri
  1

• qkeras.utils.clone_model is broken?

  #95 opened 2 years ago by jurevreca12
  1

• How low precision weights and biases are stored in QKeras?

  #103 opened 2 years ago by wilfredkisku
  4

• Using Auto

  #101 opened 2 years ago by laumecha
  1

• Error in energy estimation for AveragePooling2D layers

  #100 opened 2 years ago by RatkoFri
  0

• Kernel weights and activations not quantized after training

  #96 opened 2 years ago by YogaVicky
  11

• GPU Inferencing in Qkeras

  #97 opened 2 years ago by YogaVicky
  0

• Any documentation for AutoQkeras?

  #98 opened 2 years ago by YogaVicky
  0

• Recurrent networks quantized_bits with alpha

  #73 opened 4 years ago by laurilaatu
  1

• How to get Quantized weights after Model Training ?

  #94 opened 2 years ago by HumzaSami00
  3

• IndexError for AutoQKeras with hyperband mode

  #92 opened 2 years ago by apfusco
  2

• Slow training

  #93 opened 2 years ago by schmiph2
  2

• quantized_relu is not zeroing negative numbers

  #79 opened 2 years ago by LucaUrbinati44
  3

• AutoQKeras goal definition, delta_p and delta_n

  #80 opened 2 years ago by susuhu
  1

• Quantize the Model without retraining ?

  #81 opened 2 years ago by HenningCode
  3

• Model_save_quantized_weights returns 'has not been quantized'

  #82 opened 2 years ago by freddyD77
  1

• Qm.n with m<0 (very small tensor elements)

  #84 opened 3 years ago by alexbramanti
  1

• Does qkeras provide the implementation of DSQ?

  #91 opened 2 years ago by monchhichizzq
  1

• print_qstats raises ValueError with custom objects

  #90 opened 2 years ago by boubasse
  1

• QGRU Error when compiling with input features not the same as units

  #72 opened 4 years ago by laurilaatu
  2

• Deploy on microcontroller

  #86 opened 3 years ago by schmiph2
  1

• How to deploy qkeras on FPGA?

  #85 opened 3 years ago by YangNuoCheng
  2

• Unable to quantize QDepthwiseConv2DBatchnorm() and Conv2DBatchnorm()

  #87 opened 3 years ago by stbunda
  1

• QBatchNormalization with scale=False and model_save_quantized_weights

  #83 opened 3 years ago by lattuada-st
  5

• AutoQKeras define goal

  #77 opened 3 years ago by LordScarface
  1

• LSTM not quantized weights after model_save_quantized_weights

  #78 opened 3 years ago by vkoriukina
  1

• QSeparableConv2D: 'Keyword argument not understood:', 'depthwise_activation'

  #76 opened 3 years ago by EnriqueNueve
  1