Update nadaraya-waston.md

Line660: Add ".detach()" into origin code in order to adapt the torch 2.0
d2l-ai · Feb 23, 2024 · 40f8a45 · 40f8a45
1 parent e6b18cc
commit 40f8a45
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/chapter_attention-mechanisms/nadaraya-waston.md b/chapter_attention-mechanisms/nadaraya-waston.md
@@ -657,7 +657,7 @@ d2l.show_heatmaps(np.expand_dims(
 
 ```{.python .input}
 #@tab pytorch
-d2l.show_heatmaps(net.attention_weights.unsqueeze(0).unsqueeze(0),
+d2l.show_heatmaps(net.attention_weights.detach().unsqueeze(0).unsqueeze(0),
                   xlabel='Sorted training inputs',
                   ylabel='Sorted testing inputs')
 ```
@@ -700,4 +700,4 @@ d2l.show_heatmaps(net.attention_weight.unsqueeze(0).unsqueeze(0),
 
 :begin_tab:`paddle`
 [Discussions](https://discuss.d2l.ai/t/11840)
-:end_tab:
+:end_tab: