diff --git a/MNIST-CNN/index.html b/MNIST-CNN/index.html index 9e182fd..0dd82eb 100644 --- a/MNIST-CNN/index.html +++ b/MNIST-CNN/index.html @@ -12,69 +12,74 @@ #train { margin-top: 10px; } - + label { display: inline-block; width: 250px; padding: 6px 0 6px 0; } - + .canvases { display: inline-block; } - + .prediction-canvas { width: 100px; } - + .pred { font-size: 20px; line-height: 25px; width: 100px; } - + .pred-correct { background-color: #00cf1c; } - + .pred-incorrect { background-color: red; } - + .pred-container { display: inline-block; width: 100px; margin: 10px; } - + .btn:hover { background-color: #035aa6 !important; } - + + .homepage-button { + position: fixed; + right: 5%; + } + #container1 { height: 100%; width: 100%; display: flex; } - + #parameters { width: 35%; } - + #images { width: 65%; } - + #container2 { height: 100%; width: 100%; display: flex; } - + #board { width: 50%; } - + #chart { width: 50%; } @@ -85,7 +90,10 @@
+ +
+

Train a CNN to recognize handwritten digits from the MNIST database using the tf.layers api.

+

@@ -120,7 +130,9 @@ Description

- This examples lets you train a handwritten digit recognizer using either a Convolutional Neural Network (also known as a ConvNet or CNN) The CNN contains 8 layers in total. We use the softmax function as the activation for the output layer as it creates + This examples lets you train a handwritten digit recognizer using either a Convolutional Neural + Network (also known as a ConvNet or CNN) The CNN contains 8 layers in total. We use the softmax + function as the activation for the output layer as it creates a probability distribution over our 10 classes so their output values sum to 1. Go train that model!

The MNIST dataset is used as training data.

@@ -132,41 +144,41 @@
@@ -202,12 +214,14 @@
- - + +
@@ -264,7 +278,8 @@
-

You can also check out a 3D model of this CNN, and play with it.

+

You can also check out a 3D model + of this CNN, and play with it.