From 9692929c1a7ede8a76f3c25bc68b125051aa794f Mon Sep 17 00:00:00 2001 From: Rinu Boney Date: Mon, 14 Dec 2015 20:33:49 +0530 Subject: [PATCH] corrected some minor typos --- doc/program_model.md | 2 +- doc/python/model.md | 2 +- example/README.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/doc/program_model.md b/doc/program_model.md index f40c73c090eb..f3a7358d815a 100644 --- a/doc/program_model.md +++ b/doc/program_model.md @@ -371,7 +371,7 @@ What we usually observe is that it is usually helpful to write parameter updates while the gradient calculations can be done more effectively in symbolic programs. The mix of programs is actually happening in existing symbolic libraries, because python itself is imperative. -For example, the following programs mixed the symbolic part together with numpy(which is imperative). +For example, the following program mixes the symbolic part together with numpy(which is imperative). ```python A = Variable('A') B = Variable('B') diff --git a/doc/python/model.md b/doc/python/model.md index 50c024b94799..331ad0187a26 100644 --- a/doc/python/model.md +++ b/doc/python/model.md @@ -1,6 +1,6 @@ MXNet Python Model API ====================== -The model API in mxnet as not really an API. +The model API in mxnet is not really an API. It is a thin wrapper build on top of [ndarray](ndarray.md) and [symbolic](symbol.md) modules to make neural network training easy. diff --git a/example/README.md b/example/README.md index 1c8900a1945c..59e561133693 100644 --- a/example/README.md +++ b/example/README.md @@ -25,7 +25,7 @@ IPython Notebooks ----------------- * [Predict with Pre-trained model](https://github.com/dmlc/mxnet/blob/master/example/notebooks/predict-with-pretrained-model.ipynb) - Notebook on how to predict with pretrained model. * [composite symbol](notebooks/composite_symbol.ipynb) - A demo of how to composite a symbolic Inception-BatchNorm Network -* [cifar-10 recipe](notebooks/cifar-recipe.ipynb) - A step by step demo of how to use MXNet +* [cifar-10 recipe](notebooks/cifar10-recipe.ipynb) - A step by step demo of how to use MXNet * [cifar-100](notebooks/cifar-100.ipynb) - A demo of how to train a 75.68% accuracy CIFAR-100 model * [simple bind](notebooks/simple_bind.ipynb) - A demo of low level training API.