Teachable Machine is a project that enables you to easily train machine learning models using a web-based interface without requiring any coding knowledge. This repository contains the code and resources for the Teachable Machine project.
Teachable Machine provides an intuitive and user-friendly way to create machine learning models for image, sound, and pose classification tasks. It allows you to train models directly in your browser by providing examples of different classes and labeling them accordingly. The models can then be exported and used in various applications.
- Image Classification: Train a model to recognize and classify different face images.
If you are interested in exploring the source code or contributing to the project, you can clone this repository to your local machine using the following command:
git clone https://github.com/AkashHiremath856/Teachable_Machine.gitStreamlit not recognized error.
-
After opening the Teachable Machine website, click on "Web Cam" or "Upload" to start.
-
Select the type of model you want to train: Image. For example, if you choose "Image," you will be able to train a model to recognize and classify different objects or images.
-
Start collecting training data by clicking on the "Add Example" button. You will need to provide examples for each class you want to classify.
-
Label your examples accordingly. For each example you add, you can assign it to a specific class or label.
-
Continue adding examples and labels for each class you want to classify. Aim for a balanced representation of each class to improve the accuracy of your model.
-
Once you have collected enough examples, click on the "Train" button to start training your model. The training process may take some time depending on the complexity of your model and the number of examples.
-
After training, you can test your model by using the webcam, microphone, or by uploading new examples. The model will attempt to classify the input based on what it has learned during training.
-
If you are satisfied with your model's performance, you can export it for use in your own applications.