From 17e10ffd7efe5ba7acf1eb41e26852b493ad5e55 Mon Sep 17 00:00:00 2001
From: hanjr92 <jiaronghan@outlook.com>
Date: Tue, 28 Mar 2023 17:56:40 +0800
Subject: [PATCH] update user guide

---
 USER_GUIDE.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/USER_GUIDE.md b/USER_GUIDE.md
index 9c157582..8571e516 100644
--- a/USER_GUIDE.md
+++ b/USER_GUIDE.md
@@ -305,7 +305,7 @@ ms.context.set_context(device_target="CPU")
 2. MSAdapter tensor暂不支持格式化输出，如`label = f"{class_names[labels[i]]}: {probs[i]:.2f}"`，可先转换为numpy后输出;
 3. 早期torch版本代码中调用`torch.autograd.Variable`接口，替换为`torch.tensor`即可;
 4. 输出tensor如果要输入到opencv等其他组件进行处理时需要先转为numpy后再执行;
-
+5. 保存训练结果时，目前`torch.save`接口仅支持保存网络权重，不支持保存网络结构;
 
 
 ## FAQ
-- 
2.34.1