Happy new year for everyone. I am very excited that new year comes now. Because this year, artificial intelligence (AI) will be much closer and closer to us in our daily lives. Smartphones can answer your questions with accuracy. Self-driving car can run without human drivers. Many AI game players can compete human players, and so on. It is incredible, isn’t it!
However, in most cases, these programs of many products are developed by giant IT companies, such as Google and Microsoft. They have almost unlimited data and computer resources so it is possible to make better programs. How about us? we have small data and limited computer resources unless we have enough budget to use cloud services. Is it difficult to make good programs in our laptop computers by ourselves? I do not think so. I would like to try it by myself first.
I would like to make program to classify cats and dogs in images. To do that, I found a good tutorial (1). I use the code of this tutorial and perform my experiment. Let us start now. How can we do that? It is amazing.
For building the AI model to classify cats and dogs, we need many images of cats and dogs. Once we have many data, we should train the model so that the model can classify cats and dogs correctly. But we have two problems to do that.
1. We need massive amount of images data of cats and dogs
2. We need high-performance computer resources like GPU
To train the models of artificial intelligence, it is sometimes said ” With massive amount of data sets, it takes several days or one week to complete training the models”. In many cases, we can not do that. So what should we do?
Do not worry about that. We do not need to create the model from scratch. Many big IT companies or famous universities have already trained the AI models and make them public for everyone to use. It is sometimes called “pre-trained models”. So all we have to do is just input the results from pre-trained model and make adjustments for our own purposes. In this experiment, our purpose is to identify cats and dogs by computers.
I follow the code by François Chollet, creator of keras. I run it on my MacAir11. It is normal Mac and no additional resources are put in it. I prepared only 1000 images for cats and dogs respectively. It takes 70 minutes to train the model. The result is around 87% accuracy rate. It is great as it is done on normal laptop PC, rather than servers with GPU.
Based on the experiment, I found that Artificial intelligence models can be developed on my Mac with little data to solve our own problem. I would like to perform more tuning to obtain more accuracy rate . There are several methods to make it better.
Of course, this is the beginning of story. Not only “cats and dogs classifications’ but also many other problems can be solved in the way I experiment here. When pre-trained models are available, they can provide us great potential abilities to solve our own problems. Could you agree with that? Let us try many things with “pre-trained model” this year!
1.Building powerful image classification models using very little data
Notice: TOSHI STATS SDN. BHD. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithm or ideas contained herein, or acting or refraining from acting as a result of such use. TOSHI STATS SDN. BHD. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on TOSHI STATS SDN. BHD. and me to correct any errors or defects in the codes and the software