From 788369b9af50a69bb7b3c21d62e9e6e343290544 Mon Sep 17 00:00:00 2001 From: Takeru Miyato Date: Mon, 7 Dec 2015 19:53:13 +0900 Subject: [PATCH] Update README.md --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index c419948..dc7d7c6 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ python 2.7, numpy 1.9, theano 0.7.0, docopt 0.6.2 ``` ./vis_model_contours.sh ``` -The coutour images will be saved in the ` ./figure ` directory +The coutour images will be saved in ` ./figure `. ## Examples for MNIST dataset ###VAT in supervised learning for MNIST dataset @@ -19,13 +19,13 @@ python train_mnist_sup.py --cost_type=VAT_finite_diff --epsilon=2.1 --layer_size ``` python train_mnist_semisup.py --cost_type=VAT_finite_diff --epsilon=0.3 --layer_sizes=784-1200-1200-10 --save_filename= ``` -After training, the trained classifer will be saved with the name of ` `. +After training, the trained classifer will be saved with the name of ` ` in ` ./trained_model `. -You can obtain the test error of the trained classifier by the following command: +You can obtain the test error of the trained classifier saved with the name of ` ` by the following command: ``` -python test_mnist.py --load_filenames= +python test_mnist.py --load_filename= ``` - +. If you find bug or problem, please report it!