The Classification of Plants
The Classification Of Plants
DEPLOY AN AI MODEL TO CLASSIFY PLANTS
SOLVING A CLASSIFICATION PROBLEM
In this project, you will classify plant species based on their life cycle.
Based on their life cycle, plant species can be categorized.
These categories are as follows:
ANNUALS It takes these plants only a single season to complete their life cycle. Examples are corn, rice, wheat, pulses, etc. These plants are usually herbaceous.
BIENNIALS These plants take 2 years to complete their life cycle. They are also usually herbaceous. Examples are carrot, cabbage, onions, beetroot, etc.
PERENNIALS These plants are either herbaceous or woody and they take more than two years to complete their lifecycle. Some examples are rose, lavender, dianthus, lilies, etc.
This project will teach you to:
- Gather data and divide it into training and testing datasets.
- Create a supervised learning model that can classify plants according to their lifecycle.
You will train your ML model to classify new plant images by using a dataset of plant images comprising 3 categories namely ANNUALS, BIENNIALS, and PERENNIALS.
Be sure to split the dataset into training and testing datasets so you can check for the accuracy of the 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.
2. DEFINE THE PROBELM. START YOUR PROJECT
Begin every project by naming the project so you can keep track of what project it is exactly. Every project involves the steps of dataset preprocessing, model building, evaluation, and deployment.
By creating projects, working with others becomes more convenient and easier.
Click CREATE once you have added a project name and description.
3. SELECT YOUR ML MODEL
Here, from the options of 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), you will select a Computer Vision model (MAKE ME SEE).
This model will enable you to train your AI transformer to categorize plant images according to their lifecycle.
Keep track of the newer models that will be added to the platform. Each one of these models will enable your AI transformer to take on and solve new problems.
4. COLLECT YOUR DATA
Your source can either be Kaggle or the Plants Classifications dataset from our data library.
Take note that data gathering is a very crucial stage of an ML project with data preprocessing taking at least 70% of the time. Therefore, you will need to carry out this stage well.
5. TRAIN YOUR MODEL
Use the data you have gathered to train your AI transformer. “Training” your model refers to teaching it to categorize plant species according to their lifecycle.
A well-trained model will be able to categorize new plant images into its corresponding category of “ANNUALS”, “BIENNIALS”, and “PERENNIALS”.
To do this, click TRAIN ME. Be patient for a moment while this process goes on.
6. TEST YOUR MODEL
With your AI model trained now, it is time to test the model by using a new set of plant images. Be sure not to use an image that was used in the training phase. You will be cheating if you do.
Use the PREVIEW section to assess the performance of your model. Just upload the plant species images from the testing dataset.
The confidence score will help you know well the model has been trained and if you are fine with it, export the model.
If you do not like the confidence score, return to step 4 and determine whether the image dataset used was sufficient in number.
EXPORT YOUR MODEL
Exporting your model is the next step after you are satisfied with the confidence score. You can export using our API into your website, application, robot, or any other machine.
Return to step 4 if you got a low confidence score. Doing this helps you review the training data class to be sure it is of high quality (clean) and quantity.
Your model is only as good as the data you feed it.