ImageNet Tutorial

Introduction

This tutorial will guide you train your own super vision model. The default configure will take more than 3GB GPU RAM, so make batch size smaller or larger according to your GPU RAM size.

0.Before you start

Make sure you have downloaded the ImageNet training data.

1.Make the image list

After you get the data, you need to make a image list file first. In general, the program will take a list of names of all image, shuffle them, then separate them into training files name list and testing file name list. Write down the list in the image list file format.

2.Make the binary file

Although you can use image iterator now. the disk random seek will make the training process extremely slow. So you'd better generate binary file for training and use imgbin iterator .

To generate binary image, you need to use im2bin in the tool folder. The im2bin will take the path of image list file you generated just now, root path of the images and the output file path as input. This process usually take several hours, so be patient. :)

3.Set correct configuration file

Change the iterator path in the Alex.conf to point to your image list file and image binary file correctly, then just run as MNIST example. After about 20 round, you can see some reasonable result.

Acknowledgement