Skip to content

P
Paddle

BaiXuePrincess / Paddle
与 Fork 源项目一致

Fork自 PaddlePaddle / Paddle

通知 1
Star 1
Fork 0
P
Paddle
未验证 提交 4ead5494 编写于 作者: C Chang Xu 提交者： GitHub
浏览文件
操作

Add Reduce Max in Quant (#44825)

上级 ef945c81
隐藏空白更改
内联 并排
Showing with 2 addition and 0 deletion
python/paddle/fluid/contrib/slim/quantization/utils.py
浏览文件 @ 4ead5494
...@@ -109,6 +109,7 @@ _act_supported_quantizable_op_type = [ ...@@ -109,6 +109,7 @@ _act_supported_quantizable_op_type = [
"square", "square",
"softplus", "softplus",
"shuffle_channel", "shuffle_channel",
"reduce_max",
] ]
_out_scale_op_list = list( _out_scale_op_list = list(
...@@ -213,6 +214,7 @@ _op_real_in_out_name = { ...@@ -213,6 +214,7 @@ _op_real_in_out_name = {
"square": [["X"], ["Out"]], "square": [["X"], ["Out"]],
"softplus": [["X"], ["Out"]], "softplus": [["X"], ["Out"]],
"shuffle_channel": [["X"], ["Out"]], "shuffle_channel": [["X"], ["Out"]],
"reduce_max": [["X"], ["Out"]],
} }
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或