🤖 This repository houses a collection of image classification models for various purposes, including vehicle, object, animal, and flower classification. Each classifier is built using deep learning techniques and pre-trained models to accurately identify and categorize images based on their respective classes. Also includes a sample Flask backend!

Animal Detection and Classification using YOLO

This is an end-to-end animal face classification model with Keras, KerasTuner, Mlflow, SQLite, Streamlit, and FastAPI which can classify animal faces as either cat, dog or wildlife

🐾 Training a machine learning model to recognize 15 different animal classes and classify images accordingly.

Wild Animals Detection and Alert System

Custom trained YOLOv8 model (98.72% accuracy) to identify two wildlife species : Fishing Cat and Hyena with frontend in HTML and backend using FastAPI.

Python Flask and Streamlit web app that uses a ResNet50 PyTorch model to classify 15 animal categories with high accuracy. Upload images and get instant, real-time predictions via a clean, user-friendly interface.

The homework 2 of AI course of HUST CS. Generative method and CNN (ResNet50) method.

Animal special classification model

Animal classification using transfer learning with ResNet50

What is the name of this Animal? Just for fun:)

A basic Python project for animal classification using rule-based logic and functions. Implemented with Jupyter Notebook for educational and experimental purposes.

A Django-based web platform that hosts multiple image classification models under one unified interface. Upload an image and get the predicted result instantly.

Different pics of dogs, cats and pandas were used and applied CNN on them to find out their type.

CNN-based dog breed classifier in PyTorch with custom dataset and data augmentation.

An animal classification system developed using transfer learning with the ResNet50 convolutional neural network pre-trained on ImageNet. Designed to distinguish between three classes of animals—cats, dogs, and snakes—the system demonstrates a high accuracy of approximately 98.67% on a balanced dataset comprising 3,000 images.