**Outline**
**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:
In [ ]: