Car damage assessment
Transfer learning with pretrained blocks
Save training time and create well-performing models with small datasets. Sounds good?
This tutorial will teach you how.
By using transfer learning with our pretrained blocks, you can create a well-performing model even though you have a small dataset. You will do what your insurance company does, build a model that classifies damages.
- Target audience: Beginners
You will learn to
- Build a new AI model quick and easy.
- Use a pretrained model in a classification problem.
Create project
First, click New project to create a project. 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 preprocessing of datasets to model building, evaluation, and deployment. Using projects makes it easy to collaborate with others.
Add dataset to the project
After creating the project, you will be taken to the Datasets view, where you can import data.
Click the Import free datasets button.
Look for the Car damage - tutorial data dataset in the list. Click on it to get more information.
If you agree with the license, click Accept and import.
This will import the dataset in your project, and you can now edit it.
The car damage dataset
The car damage dataset contains approximately 1,500 unique RGB images with the dimensions 224 x 224 pixels, and is split into a training- and a validation subset.
Classes
The illustration show sample images from the various classes in the dataset. Note that the unknown class contains images of cars that are in either pristine or wrecked condition.
Each collected image represents one car with one specific type of damage. This means that the dataset can be used to solve a single-label classification problem.
Keep the default values
Keep these default values that are shown here in the Datasets view. They’re all set for this project.
Later you can change the subsets split, feature encoding, and more.
If you want to dig deeper into all the things you see in this view, you should navigate to the Datasets view articles in the Knowledge center.
Click Create an experiment to open the Experiment wizard.
Build a model in the Experiment wizard
Name the experiment in the Experiment wizard.
-
Dataset tab
Make sure that the Car Damage dataset with subset is selected. -
Inputs / target tab
Select image as Input feature and class as Target feature. -
Problem type tab
Select the Single-label image classification.
Single-label image classification is when a deep learning model predicts one class for each example.
Click Create, and all blocks needed will be added to the Modeling canvas.
Run experiment
Before you run the experiment, click the Settings tab and change the Learning rate to 0.0005.
Now, everything is set up, so just click Run.
Analyze the experiment
Navigate to the Predictions inspection tab in the Datasets view.
Since the model solves a classification problem, a confusion matrix is displayed.
The top-left to bottom-right diagonal shows correct predictions.
Everything outside this diagonal are errors.
It looks good!
Note that metrics are based on the validation subset, which only consists of 10% of the original dataset.
Deploy the trained model
In the Evaluation view, click Create deployment.
Select experiment and checkpoint.
Click Enable to deploy the experiment. You can now call your deployed experiment with your own product using the Url and Token. For example, when you build your own app with Bubble.
Test with Peltarion API tester
We’ve also made it super easy for you to test the deployment.
Click on Test deployment, and you will be directed to our Image & Text Classifier - API tester.
All info from your deployment is prepopulated (token, URL, Input parameter).
You just need an image to test.
Try to download this image of a seriously damaged car or take your own photo.
Add the photo to the bottom left corner and then click the Play button.
Result? Yes, the model prediction is glass_shatter.
Tutorial recap
Using transfer learning with pretrained weights, you have saved hours of training time and created a better performance than would have been possible if you had trained the model from scratch.