This is an automated email from the ASF dual-hosted git repository. jxie pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/master by this push: new 46039c3 Update autograd.md (#7405) 46039c3 is described below commit 46039c34e13191c98020c6f046a197b262de9f72 Author: Zack Chase Lipton <zachary.ch...@gmail.com> AuthorDate: Wed Aug 9 20:15:19 2017 -0700 Update autograd.md (#7405) Fixing two typos that snuck into this doc. Thanks @fhieber for the careful eyes! --- docs/api/python/autograd.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/api/python/autograd.md b/docs/api/python/autograd.md index 5c84964..444e01f 100644 --- a/docs/api/python/autograd.md +++ b/docs/api/python/autograd.md @@ -34,6 +34,7 @@ and do some computation. Finally, call `backward()` on the result: >>> x.attach_grad() >>> with mx.autograd.record(): ... y = x * x + 1 +>>> y.backward() >>> print(x.grad) [ 2. 4. 6. 8.] <NDArray 4 @cpu(0)> @@ -44,7 +45,7 @@ and do some computation. Finally, call `backward()` on the result: Some operators (Dropout, BatchNorm, etc) behave differently in when training and when making predictions. -This can be controled with `train_mode` and `predict_mode` scope. +This can be controlled with `train_mode` and `predict_mode` scope. By default, MXNet is in `predict_mode`. A `with autograd.record()` block by default turns on `train_mode` -- To stop receiving notification emails like this one, please contact ['"comm...@mxnet.apache.org" <comm...@mxnet.apache.org>'].