diff options
Diffstat (limited to 'tensorflow/g3doc/tutorials/mnist/beginners/index.md')
| -rw-r--r-- | tensorflow/g3doc/tutorials/mnist/beginners/index.md | 14 |
1 files changed, 6 insertions, 8 deletions
diff --git a/tensorflow/g3doc/tutorials/mnist/beginners/index.md b/tensorflow/g3doc/tutorials/mnist/beginners/index.md index e5d3f28de6..9b6caf8358 100644 --- a/tensorflow/g3doc/tutorials/mnist/beginners/index.md +++ b/tensorflow/g3doc/tutorials/mnist/beginners/index.md @@ -376,22 +376,20 @@ to your graph which implement backpropagation and gradient descent. Then it gives you back a single operation which, when run, does a step of gradient descent training, slightly tweaking your variables to reduce the loss. -Now we have our model set up to train. One last thing before we launch it, we -have to create an operation to initialize the variables we created. Note that -this defines the operation but does not run it yet: + +We can now launch the model in an `InteractiveSession`: ```python -init = tf.global_variables_initializer() +sess = tf.InteractiveSession() ``` -We can now launch the model in a `Session`, and now we run the operation that -initializes the variables: +We first have to create an operation to initialize the variables we created: ```python -sess = tf.Session() -sess.run(init) +tf.global_variables_initializer().run() ``` + Let's train -- we'll run the training step 1000 times! ```python |