未验证 提交 9058dc2c 编写于 作者: X XGZhang 提交者: GitHub

update default config of inplace (#864)

* update quant docs

* Update quantization_api.rst

* Update quantization_api.rst

* Update quantization_api.rst

* Update qat.py

与之前版本兼容:之前版本直接改动传入的model,所以这里inplace改为true
上级 2ff97018
...@@ -207,7 +207,7 @@ class QAT(object): ...@@ -207,7 +207,7 @@ class QAT(object):
weight_quantize_layer=self.weight_quantize, weight_quantize_layer=self.weight_quantize,
act_quantize_layer=self.act_quantize) act_quantize_layer=self.act_quantize)
def quantize(self, model, inplace=False): def quantize(self, model, inplace=True):
""" """
Quantize the input model. Quantize the input model.
......
Markdown is supported
0% .
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