Overview / Usage
DoT(Dress-shirt or T-shirt) classifier is a machine learning model that can help classify between two types of shirts(dress-shirts or t-shirts). The model is trained with different datasets, which helps identify shirts in different environments, illumination and pose.
My aim was to play with the Fashion-MNIST dataset and see how in-built models from sklearn perform on clothing datasets.
The project was divided into two parts: training and testing. 80% of the dataset was used to train the model and rest was for testing purposes.
Methodology / Approach
I developed this project in python and used pandas, matplotlib, numpy, skimage and sklearn.
The frontend is under development and soon I'll be able to launch it.
Dataset: Fashion-MNIST dataset.
Technologies Used
The model is trained on Intel CPUs with a normal capacity RAM.
The model is entirely trained and tested using python.
I'm currently exploring the use of Intel's oneAPI toolkits and libraries for the model.