experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Small typo (#3150)

Browse Source 
* Small typo

* Previous score is 92%, not 91%.
This commit is contained in:
Simon DENEL 2016-07-01 19:56:39 +02:00 committed by Vijay Vasudevan
parent 084c915c2d
commit 4e1221f01b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tensorflow/g3doc/tutorials/mnist/pros/index.md
View File

@ -232,7 +232,7 @@ print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
## Build a Multilayer Convolutional Network ## Build a Multilayer Convolutional Network
Getting 91% accuracy on MNIST is bad. It's almost embarrassingly bad. In this Getting 92% accuracy on MNIST is bad. It's almost embarrassingly bad. In this
section, we'll fix that, jumping from a very simple model to something section, we'll fix that, jumping from a very simple model to something
moderately sophisticated: a small convolutional neural network. This will get us moderately sophisticated: a small convolutional neural network. This will get us
to around 99.2% accuracy -- not state of the art, but respectable. to around 99.2% accuracy -- not state of the art, but respectable.
@ -243,7 +243,7 @@ To create this model, we're going to need to create a lot of weights and biases.
One should generally initialize weights with a small amount of noise for One should generally initialize weights with a small amount of noise for
symmetry breaking, and to prevent 0 gradients. Since we're using ReLU neurons, symmetry breaking, and to prevent 0 gradients. Since we're using ReLU neurons,
it is also good practice to initialize them with a slightly positive initial it is also good practice to initialize them with a slightly positive initial
bias to avoid "dead neurons." Instead of doing this repeatedly while we build bias to avoid "dead neurons". Instead of doing this repeatedly while we build
the model, let's create two handy functions to do it for us. the model, let's create two handy functions to do it for us.
```python ```python