| template |
|---|
true |
Level :
In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of deep neural network, most commonly applied to analyze visual imagery. Unlike a KNN (k-nearest neighbors). CNN is not a pre-trained model and may have a custom neural structure to meet a specific need.
This template use :
It is used to train a model and classify images that can come from a camera, video, image or a canvas (works with p5js).
- webcam
You need a web server to take advantage of all the features and a compatible browser (hardware acceleration is highly recommended).
- Add data to the different class (you can add as many class as you want)
- Click on
Trainand wait - You can save your model to avoid training it every time
You can modify the source of your model (video, image ..) in cnn.js by replacing the selected element in the input variable.
The rest of the code is self-explanatory and commented.
To modify the structure of the neural networks, I invite you to watch the videos of The Coding Train and experiment.