Name | Last commit | Last update |
---|---|---|
.. | ||
fp32_baselines | ||
post_train_quant | ||
quant_aware_train |
* Added scale factor approximation in post-training quantization using integer multiply + shift. # of bits for integer multiplier is user configurable * Updated documentation * Updated post-train quant command line examples readme file
Name | Last commit | Last update |
---|---|---|
.. | ||
fp32_baselines | ||
post_train_quant | ||
quant_aware_train |