Inception V3

**TensorFlow Hands-on Tutorial**

**Outline**

Clues in TensorFlow
First Model in TensorFlow
Convolutional Neural Network (CNN) on Cifar-10
Techniques for Deep Learning in TensorFlow
** Inception V3 **
CNN for Text Classification
Hidden Markov Model in TensorFlow
Image Captioning in TensorFlow

**Imagenet in TensorFlow**

One of most succesful Deep Learning Models is ImageNet, it is presented in four version:

  -  Inception v1  
  -  Inception v2  
  -  Inception v3  
  -  Inception v4

In particular, this tutorial demonstrates how to train the Inception v3 architecture as specified in:

" Rethinking the Inception Architecture for Computer Vision "

Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Zbigniew Wojna

http://arxiv.org/abs/1512.00567

This network achieves 21.2% top-1 and 5.6% top-5 error for single frame evaluation with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. Below is a visualization of the model architecture [1].

**TensorFlow-Slim**

In this implementation TF-Slim is used. TF-Slim is a lightweight library for defining, training and evaluating complex models in TensorFlow. Components of tf-slim can be freely mixed with native tensorflow, as well as other frameworks, such as tf.contrib.learn TensorFlow-Slim

Usage:



In [ ]:

    
import tensorflow.contrib.slim as slim

Please open the ipython files located at /home/cc/tf-hands-on/slim/python/slim/nets:

Training: inception_v3.ipynb
Test: inception_v3_test.ipynb



In [ ]: