未验证 提交 f50c8fe3 编写于 作者: G Guanghua Yu 提交者: GitHub

Update post_quant.py

上级 6d9d1df1
......@@ -83,6 +83,7 @@ def main():
batch_nums=10,
algo=FLAGS.algo,
hist_percent=0.999,
quantizable_op_type=["conv2d", "depthwise_conv2d"],
is_full_quantize=False,
bias_correction=False,
onnx_format=False,
......
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