File tree Expand file tree Collapse file tree 2 files changed +7
-7
lines changed Expand file tree Collapse file tree 2 files changed +7
-7
lines changed Original file line number Diff line number Diff line change @@ -35,7 +35,7 @@ makedocs(
35
35
" GPU Support" => " gpu.md" ,
36
36
" Model Tools" => [
37
37
" Saving & Loading" => " saving.md" ,
38
- " Size Propagation " => " outputsize.md" ,
38
+ " Shape Inference " => " outputsize.md" ,
39
39
" Weight Initialisation" => " utilities.md" ,
40
40
],
41
41
" Performance Tips" => " performance.md" ,
Original file line number Diff line number Diff line change 1
- # Size Propagation
1
+ # Shape Inference
2
2
3
- Flux provides some utility functions to help you generate models in an automated fashion.
3
+ To help you generate models in an automated fashion, [ ` Flux.outputsize ` ] ( @ref ) lets you
4
+ calculate the size returned produced by layers for a given size input.
5
+ This is especially useful for layers like [ ` Conv ` ] ( @ref ) .
4
6
5
- [ ` Flux.outputsize ` ] ( @ref ) enables you to calculate the output sizes of layers like [ ` Conv ` ] ( @ref )
6
- when applied to input samples of a given size. This is achieved by passing a "dummy" array into
7
- the model that preserves size information without running any computation.
7
+ It works by passing a "dummy" array into the model that preserves size information without running any computation.
8
8
` outputsize(f, inputsize) ` works for all layers (including custom layers) out of the box.
9
9
By default, ` inputsize ` expects the batch dimension,
10
10
but you can exclude the batch size with ` outputsize(f, inputsize; padbatch=true) ` (assuming it to be one).
44
44
45
45
``` @docs
46
46
Flux.outputsize
47
- ```
47
+ ```
You can’t perform that action at this time.
0 commit comments