From dfe923ac254be93ae0a580bfd26b52fb6ea065e8 Mon Sep 17 00:00:00 2001 From: Serge Panev Date: Sat, 6 Jul 2019 03:08:33 +0900 Subject: [PATCH] Update fp16 docs: Block.cast is inplace (#15458) Signed-off-by: Serge Panev --- docs/faq/float16.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/faq/float16.md b/docs/faq/float16.md index 465668610413..22d4ef48c2f6 100644 --- a/docs/faq/float16.md +++ b/docs/faq/float16.md @@ -42,7 +42,7 @@ With Gluon API, you need to take care of three things to convert a model to supp 1. Cast Gluon `Block`'s parameters and expected input type to float16 by calling the [cast](https://mxnet.incubator.apache.org/api/python/gluon/gluon.html#mxnet.gluon.Block.cast) method of the `Block` representing the network. ```python -net = net.cast('float16') +net.cast('float16') ``` 2. Ensure the data input to the network is of float16 type. If your `DataLoader` or `Iterator` produces output in another datatype, then you would have to cast your data. There are different ways you can do this. The easiest would be to use the [astype](https://mxnet.incubator.apache.org/api/python/ndarray/ndarray.html#mxnet.ndarray.NDArray.astype) method of NDArrays.