Skip to content

N
ngraph
Switch branch/tag
History Find file
  • Nishant Patel's avatar
    Quantize(reorder) bias to int32 (#1933) · 296ee2cf
    Nishant Patel authored 
    * Quantize the bias to int32

* Bias scale fix

* mnist works

* Quantize Bias

* Introduce Quantize op in the graph to quantize bias & feedback

* Comments and some refactoring

* Add test case with float bias and enable int32 as quantized type in ngraph

* Change shape of scale from Shape{} to Shape{1} in the backend
    296ee2cf
Name
Last commit
 Last update
..
autobroadcast.cpp Loading commit data...
autobroadcast.hpp Loading commit data...
make_constant.hpp Loading commit data...
numpy_transpose.cpp Loading commit data...
numpy_transpose.hpp Loading commit data...
quantization.cpp Loading commit data...
quantization.hpp Loading commit data...
quantization_util.hpp Loading commit data...
reduce_ops.cpp Loading commit data...
reduce_ops.hpp Loading commit data...
tensor_mask.hpp Loading commit data...