From c0cb1273fd6533c43cce82aa09227beedde5e04d Mon Sep 17 00:00:00 2001
From: Amir MOHAMMADI <amir.mohammadi@idiap.ch>
Date: Tue, 29 Aug 2017 11:54:24 +0200
Subject: [PATCH] learning rate should go to optimizer
---
doc/user_guide.rst | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/user_guide.rst b/doc/user_guide.rst
index 3b15d2b6..b9b8db42 100644
--- a/doc/user_guide.rst
+++ b/doc/user_guide.rst
@@ -56,10 +56,10 @@ The example consists in training a very simple **CNN** with `MNIST` dataset in 4
>>>
>>> loss = BaseLoss(tf.nn.sparse_softmax_cross_entropy_with_logits, tf.reduce_mean)
>>>
- >>> optimizer = tf.train.GradientDescentOptimizer(0.001)
- >>>
>>> learning_rate = constant(base_learning_rate=0.001)
>>>
+ >>> optimizer = tf.train.GradientDescentOptimizer(learning_rate)
+ >>>
>>> trainer = Trainer
Now that you have defined your data, architecture, loss and training algorithm you can save this in a python file,
--
GitLab