Update doc for RReLU

xternalz · xternalz · commit 316a0cf6eb46 · 2016-05-30T20:21:17.000+08:00
diff --git a/doc/transfer.md b/doc/transfer.md
@@ -290,6 +290,7 @@ m=nn.ReLU(
    l,       -- minimum factor for negative inputs, default: 1/8;
    u,       -- maximum factor for negative inputs, default: 1/3;
    inplace  -- if true the result will be written to the input tensor, default: false;
+   cw       -- if true all elements of the same channel share the same `a`, default: false;
 )
 ```
 If `l == u` a RReLU effectively becomes a LeakyReLU. Regardless of operating in in-place mode a RReLU will internally allocate an input-sized `noise` tensor to store random factors for negative inputs. The backward() operation assumes that forward() has been called before.

Original file line number	Diff line number	Diff line change
`@@ -290,6 +290,7 @@ m=nn.ReLU(`
`290`	`290`	`l, -- minimum factor for negative inputs, default: 1/8;`
`291`	`291`	`u, -- maximum factor for negative inputs, default: 1/3;`
`292`	`292`	`inplace -- if true the result will be written to the input tensor, default: false;`
	`293`	+ cw -- if true all elements of the same channel share the same `a`, default: false;
`293`	`294`	`)`
`294`	`295`	```
`295`	`296`	If `l == u` a RReLU effectively becomes a LeakyReLU. Regardless of operating in in-place mode a RReLU will internally allocate an input-sized `noise` tensor to store random factors for negative inputs. The backward() operation assumes that forward() has been called before.