We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 890f6f6 commit ab24e8eCopy full SHA for ab24e8e
docs/src/models/recurrence.md
@@ -108,6 +108,20 @@ julia> [m(x[i]) for i = 1:3]
108
[-0.34613007, -0.54565114]
109
```
110
111
+!!! warning "Use of map and broadcast"
112
+ Mapping and broadcasting operations with stateful layers such as the one we are considering are discouraged,
113
+ since the julia language doesn't guarantee a specific execution order.
114
+ Therefore, avoid
115
+ ```julia
116
+ y = m.(x)
117
+ # or
118
+ y = map(m, x)
119
+ ```
120
+ and use explicit loops
121
122
+ y = [m(x) for x in x]
123
124
+
125
If for some reason one wants to exclude the first step of the RNN chain for the computation of the loss, that can be handled with:
126
127
```julia
0 commit comments