Update 16.md

修正了一个笔误

docs/pt-tut-17/16.md

@@ -58,7 +58,7 @@ print(x_train.shape)
 
 ![../_img/sphx_glr_nn_tutorial_001.png](img/7c783def0bbe536f41ed172041b7e89e.png)
 
-出：
+输出：
 
 ```py
 (50000, 784)
@@ -968,4 +968,4 @@ fit(epochs, model, loss_func, opt, train_dl, valid_dl)
 
 [下载 Jupyter 笔记本：`nn_tutorial.ipynb`](../_downloads/5ddab57bb7482fbcc76722617dd47324/nn_tutorial.ipynb)
 
-[由 Sphinx 画廊](https://sphinx-gallery.readthedocs.io)生成的画廊
\ No newline at end of file
+[由 Sphinx 画廊](https://sphinx-gallery.readthedocs.io)生成的画廊