Image Classification: Dogs vs. Wolves


dogs vs wolves images classification age group (5-11), (12-15), (16-18)


Deploy an AI model to classify dogs vs wolves images

How to solve a classification problem

Zero prior AI knowledge is required. We’re going to design a machine learning model to classify a set of dogs and wolves’ images.  


The problem

Classification problems have always been around. Humans have at all times tried to classify the world around them. Here, we try to make a predictive model for classifying dogs’ vs wolves’ images. Although this problem sounds simple, it was only effectively addressed in the last few years using deep learning convolutional neural networks. While the dataset is effectively solved, it can be used as the basis for learning and practicing how to develop, evaluate, and use convolutional deep learning neural networks for image classification from scratch.


what is image classification? 

Classification is a supervised learning technique in which the computer uses input data (in this project, dogs and wolves images are the input data) to learn and then classify new observations. Further information can be found in the second course of Level2, Supervised Learning, in the AI Citizenship Program. 


You will learn to

After completing this project, you will understand how to:

  • Collect data and split it into training and testing datasets. 
  • Load and prepare images of dogs and wolves for modeling.
  • Develop a machine learning model to apply image classification from scratch and improve model performance.
  • Develop a model for images classification using platform learning.


The data

The dataset is comprised of images of dogs and wolves provided as a subset of photos from the dataset library. This dataset will be used to train your ML model on how to do the classification task on its own when it sees new dogs ,wolves images. You will need to make sure that your split your data into training dataset and testing dataset so that you know how to assess the performance of your ML model. 





1. Meet your AI Identity

Meet your AI Identity. You will teach your AI how complete the tasks as a human would. In due time, your AI Identity will grow more intelligent as you train it some more to take on different tasks with multiple projects. Eventually -in the future- just maybe you will be able to transfer your AI transformer’s intellect into a physical robot you can interact with in the real world.  




First, create a project and name it so you know what kind of project it is. Naming is important. A project combines all of the steps in solving a problem, from the pre-processing of datasets to model building, evaluation, and deployment. Using projects makes it easy to collaborate with others. After adding the project’s name and description, click on CREATE


3. SELECT YOUR ML MODEL In this step, you will need to select one of the ML models in order to solve your problem, that is classifying images. You will find a computer vision model (Make Me See), Natural Language Processing model (Make Me Read), Voice Recognition (Make Me Hear), and a tabular model (Make Me Count). In our case, you will need to train your AI transformer to how to see and classify dogs vs wolves images, therefore, you need to select MAKE ME SEE. More AI capabilities (models) will be added to the platform, so stay tuned! These models will help you to accelerate the process of creating a trained AI model that solves your problem, and thus export into your app to start using it!


4. COLLECT YOUR DATA This is the most important step in any ML project. In fact, data preprocessing is 70-80% of any ML project. In this section, you will need to manually collect your dogs and wolves images from reliable resources, such as Kaggle, or import the dogs vs wolves dataset from our data library



Right now, and after you completed training your model, you are ready to test it using a new sample image. You can test your model using one of dogs vs wolves images from the testing dataset (see step 4).

Just make sure that you don’t use an image from the dataset that you used in the training part, otherwise, you are cheating!

Upload or import the sample image to assess the performance in the preview section. If you like the confidence score, you can export your model. Otherwise, go back to the "collect data" step and check whether you have used sufficient number of images in the training dataset.  Click TRAIN ME to start the training. This may take a few moments.



If you are happy with the testing results, you can "Export" your ML model using our API into your own websiteapplication or even to your robot or any machine! If you are not happy with the confidence score, you will need to check your training data classes again, and make sure that you have clean and sufficient number of examples for each data class. Keep in mind the concept of GIGO (garbage in, garbage out) which means that the quality of your ML model output is determined by the quality of your input, i.e. training dataset.