Welcome to our end-to-end image classification deep learning project using Pytorch, Comet ML, and Gradio! This repository contains the notebooks and resources needed to train and deploy a deep learning model for image classification. We used Pytorch as our deep learning framework, Comet ML for experiment tracking, and Gradio for model deployment. The dataset we used in this project is the Cat and Dog datasets which contains 10,000 images.
PyTorch is an open-source machine learning library for Python. It provides a wide range of tools for building and training deep learning models, including a dynamic computational graph, automatic gradient computation, and a variety of pre-built and reusable neural network modules. PyTorch also provides support for distributed training and a suite of tools for data loading and processing. This makes it a popular choice among researchers and practitioners for building and deploying deep learning models. In this repository, Pytorch will be used as the main deep learning framework for building and training the image classification model.
Comet ML is a platform for managing and tracking machine learning experiments. It allows users to track experiment parameters, code versions, metrics, and results all in one place. Additionally, it also provides functionalities like experiment comparison, version control, and collaboration. It can be easily integrated with popular deep learning frameworks like Pytorch and TensorFlow. This platform will be used in this repository to track the experiment details and performance of the image classification model. It will also allow to compare different runs of the experiment and collaborate with other contributors.
Gradio is an open-source tool that allows you to easily deploy machine learning models as web applications. It provides a simple and intuitive interface for users to interact with the model, and it supports a wide variety of models and frameworks, including Pytorch, TensorFlow, and scikit-learn. With Gradio, you can deploy your model as a web app or a command-line interface with just a few lines of code. It also allows you to customize the user interface, add explanations, and collect feedback from users. In this repository, Gradio will be used to deploy the image classification model as a web application that anyone can use to classify images. It will make the model accessible to a larger audience, and it will allow users to easily test the model with their own images.
- The app we built in this project.
- Kaggle notebook we used for experiment tracking.
- Comet ML dashboard for experiment tracking.
📌 Thanks for reading 😀 If you enjoy this repo, don't forget to give it a ✨