Image Classifier (trained on CIFAR10)
The model aims to classify images from this dataset into 1 of 10 classes, in which we build a model on the training set & evaluate it on the test set. The dataset include 10 classes which are:
- airplanes, cars, birds, cats, deer, dogs, frogs, horses, ships, and trucks
with roughly 60,000 images.
CIFAR10 models exist and so the aim here is not for a model that is identical and easy to train, this model has a unique architecture which will be explained.
Model Details
- Developed by: Michael Peres
- Model type: Image Classification of CIFAR10 dataset.
- Language(s) (NLP): Michael Peres
- License: MIT
Model Architecture
This model has a more unique approach for the architecture,
Uses
This model is just intended as a learning challenge where CIFAR10 is trained on a unconventional architecture.
How to Get Started with the Model
Use the code below to get started with the model.
Look at provided main.py which contains the model and the training code, if you would like to train it.
We are using optuna, to tune the hyperparameters.
ore Information Needed]
These are the evaluation metrics being used, ideally with a description of why. -->