OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 00:21:07 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity
android_fbgemm_off
pytorch/caffe2/quantization
History
Haixin Liu 7f130c8494 Expose the quantized inputs and output of dynamic quantized int8 FC operator for debugging (#23566) 
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/23566

Currently if we use dynamic quantization we don't have the access to the internally quantized inputs and output for debugging.

To make the debugging easier, this diff adds a debug feature to expose the quantized X, W and Y for debugging if debug outputs are attached to the operator and caffe2_dnnlowp_force_slow_path flag is set.

The quantized inputs and output are exposed as the extra outputs.

The example Int8FC op with debug outputs appended looks like:
```
op {
  input: "X"
  input: "W"
  input: "b"
  output: "Y"
  output: "X_q"
  output: "W_q"
  output: "Y_q"
  name: ""
  type: "Int8FC"
  arg {
    name: "axis"
    i: 1
  }
  ...
}
```

Next need to expose the quantization parameters.

Reviewed By: jspark1105

Differential Revision: D16566753

fbshipit-source-id: acd855a172ee7993ddba8808f2af81b628ff9c02
2019-08-02 21:23:43 -07:00
..
server Expose the quantized inputs and output of dynamic quantized int8 FC operator for debugging (#23566) 2019-08-02 21:23:43 -07:00
__init__.py re-enable copy of python files, but be careful that the copy is only … (#14982) 2018-12-11 16:54:08 -08:00
CMakeLists.txt operators/quantized/server -> quantization/server (#13660) 2018-11-07 22:54:13 -08:00