diff --git a/tensorflow/g3doc/tutorials/index.md b/tensorflow/g3doc/tutorials/index.md index edc1f6b5a44..505f1b42706 100644 --- a/tensorflow/g3doc/tutorials/index.md +++ b/tensorflow/g3doc/tutorials/index.md @@ -8,37 +8,33 @@ digit images. ### MNIST For ML Beginners -If you're new to machine learning, we recommend starting here. You'll learn +If you're new to machine learning, we recommend starting here. You'll learn about a classic problem, handwritten digit classification (MNIST), and get a gentle introduction to multiclass classification. [View Tutorial](../tutorials/mnist/beginners/index.md) - ### Deep MNIST for Experts If you're already familiar with other deep learning software packages, and are -already familiar with MNIST, this tutorial will give you a very brief primer -on TensorFlow. +already familiar with MNIST, this tutorial will give you a very brief primer on +TensorFlow. [View Tutorial](../tutorials/mnist/pros/index.md) ### TensorFlow Mechanics 101 This is a technical tutorial, where we walk you through the details of using -TensorFlow infrastructure to train models at scale. We use MNIST as the -example. +TensorFlow infrastructure to train models at scale. We use MNIST as the example. [View Tutorial](../tutorials/mnist/tf/index.md) - ## Easy ML with tf.contrib.learn ### tf.contrib.learn Quickstart A quick introduction to tf.contrib.learn, a high-level API for TensorFlow. -Build, train, and evaluate a neural network with just a few lines of -code. +Build, train, and evaluate a neural network with just a few lines of code. [View Tutorial](../tutorials/tflearn/index.md) @@ -73,19 +69,27 @@ Monitor API to audit the in-progress training of a neural network. ### Building Input Functions with tf.contrib.learn This tutorial introduces you to creating input functions in tf.contrib.learn, -and walks you through implementing an `input_fn` to train a neural network -for predicting median house values. +and walks you through implementing an `input_fn` to train a neural network for +predicting median house values. [View Tutorial](../tutorials/input_fn/index.md) ### Creating Estimators in tf.contrib.learn -This tutorial covers how to create your own `Estimator` using the building blocks -provided in tf.contrib.learn. You'll build a model to predict the ages of abalones -based on their physical measurements. +This tutorial covers how to create your own `Estimator` using the building +blocks provided in tf.contrib.learn. You'll build a model to predict the ages of +abalones based on their physical measurements. [View Tutorial](../tutorials/estimators/index.md) +### A Guide to TF Layers: Building a Convolutional Neural Network + +This tutorial introduces you to building neural networks in TensorFlow using the +`tf.layers` module. You'll build a convolutional neural network `Estimator` to +recognize the handwritten digits in the MNIST data set. + +[View Tutorial](../tutorials/layers/index.md) + ## TensorFlow Serving ### TensorFlow Serving @@ -95,7 +99,6 @@ serving machine learning models, designed for production environments. [View Tutorial](../tutorials/tfserve/index.md) - ## Image Processing ### Convolutional Neural Networks @@ -109,8 +112,8 @@ representations of visual content. ### Image Recognition -How to run object recognition using a convolutional neural network -trained on ImageNet Challenge data and label set. +How to run object recognition using a convolutional neural network trained on +ImageNet Challenge data and label set. [View Tutorial](../tutorials/image_recognition/index.md) @@ -120,8 +123,8 @@ Building on the Inception recognition model, we will release a TensorFlow version of the [Deep Dream](https://github.com/google/deepdream) neural network visual hallucination software. -[View Tutorial](https://nbviewer.jupyter.org/github/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/deepdream/deepdream.ipynb) - +[View +Tutorial](https://nbviewer.jupyter.org/github/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/deepdream/deepdream.ipynb) ## Language and Sequence Processing @@ -138,14 +141,14 @@ embeddings). ### Recurrent Neural Networks An introduction to RNNs, wherein we train an LSTM network to predict the next -word in an English sentence. (A task sometimes called language modeling.) +word in an English sentence. (A task sometimes called language modeling.) [View Tutorial](../tutorials/recurrent/index.md) ### Sequence-to-Sequence Models A follow on to the RNN tutorial, where we assemble a sequence-to-sequence model -for machine translation. You will learn to build your own English-to-French +for machine translation. You will learn to build your own English-to-French translator, entirely machine learned, end-to-end. [View Tutorial](../tutorials/seq2seq/index.md) @@ -157,19 +160,18 @@ TensorFlow. [View Tutorial](../tutorials/syntaxnet/index.md) - ## Non-ML Applications ### Mandelbrot Set TensorFlow can be used for computation that has nothing to do with machine -learning. Here's a naive implementation of Mandelbrot set visualization. +learning. Here's a naive implementation of Mandelbrot set visualization. [View Tutorial](../tutorials/mandelbrot/index.md) ### Partial Differential Equations -As another example of non-machine learning computation, we offer an example of -a naive PDE simulation of raindrops landing on a pond. +As another example of non-machine learning computation, we offer an example of a +naive PDE simulation of raindrops landing on a pond. [View Tutorial](../tutorials/pdes/index.md) diff --git a/tensorflow/g3doc/tutorials/layers/index.md b/tensorflow/g3doc/tutorials/layers/index.md index 2d0071a31ac..387b6e0dfa9 100644 --- a/tensorflow/g3doc/tutorials/layers/index.md +++ b/tensorflow/g3doc/tutorials/layers/index.md @@ -45,7 +45,7 @@ evaluate the convolutional neural network. The complete, final code can be here](https://www.tensorflow.org/code/tensorflow/examples/tutorials/layers/cnn_mnist.py).

NOTE: Before proceeding, make sure you've -installed the latest +installed the latest version of TensorFlow on your machine.

## Intro to Convolutional Neural Networks @@ -87,9 +87,9 @@ is equal to 1). We can interpret the softmax values for a given image as relative measurements of how likely it is that the image falls into each target class. -NOTE: For a more comprehensive walkthrough of CNN architecture, see Stanford -University's [Convolutional Neural Networks for Visual Recognition course -materials](http://cs231n.github.io/convolutional-networks/). +

NOTE: For a more comprehensive walkthrough of CNN +architecture, see Stanford University's +Convolutional Neural Networks for Visual Recognition course materials.

## Building the CNN MNIST Classifier {#building-cnn-classifier} @@ -506,7 +506,7 @@ if mode == learn.ModeKeys.TRAIN:

NOTE: For a more in-depth look at configuring training ops for Estimator model functions, see "Defining the training op for the model" in the -"Creating Estimations in tf.contrib.learn"] tutorial.

+"Creating Estimations in tf.contrib.learn" tutorial.

### Generate Predictions {#generate-predictions} @@ -541,7 +541,7 @@ using [`tf.nn.softmax()`](../../api_docs/python/nn.md#softmax): tf.nn.softmax(logits, name="softmax_tensor") ``` -

NOTE:Set Up a Logging Hook.)

+

NOTE: We use the `name` argument to explicitly name this operation `softmax_tensor`, so we can reference it later. (We'll set up logging for the softmax values in Set Up a Logging Hook.)

We compile our predictions in a dict as follows: diff --git a/tensorflow/g3doc/tutorials/leftnav_files b/tensorflow/g3doc/tutorials/leftnav_files index a75e62f5e36..77ec0a0f39f 100644 --- a/tensorflow/g3doc/tutorials/leftnav_files +++ b/tensorflow/g3doc/tutorials/leftnav_files @@ -10,6 +10,7 @@ wide_and_deep/index.md monitors/index.md input_fn/index.md estimators/index.md +layers/index.md ### TensorFlow Serving tfserve/index.md ### Image Processing