PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
update overview img (#57)
WeiweiZhang1f55e15d2ad2c
diff --git a/README.md b/README.mdindex d1b93b183..bb0b3fe6d 100644--- a/README.md+++ b/README.md@@ -16,7 +16,7 @@ our method adopts sign gradient descent to fine-tune rounding values and minmax<div align="center">-+<div align="left">diff --git a/docs/imgs/autoround_overview.png b/docs/imgs/autoround_overview.pngnew file mode 100644index 000000000..ac13df61bBinary files /dev/null and b/docs/imgs/autoround_overview.png differ