Using convolutional neural networks to build and train a bird species classifier on bird song data with corresponding species labels.

Polish bird species recognition - Bird song analysis and classification with MFCC and CNNs. Trained on EfficientNets with final score 0.88 AUC. Women in Machine Learning & Data Science project.

Supervised Classification of bird species 🐦 in high resolution images, especially for, Himalayan birds, having diverse species with fairly low amount of labelled data [ICVGIPW'18]

A repo designed to convert audio-based "weak" labels to "strong" intraclip labels. Provides a pipeline to compare automated moment-to-moment labels to human labels. Methods range from DSP based foreground-background separation, cross-correlation based template matching, as well as bird presence sound event detection deep learning models!

Code for searching the www.xeno-canto.org bird sound database, and training a machine learning model to classify birds according to their sounds.

Explores jigsaw puzzles solvinig as pre-text task for fine grained classification for bird species identification (Implemented with pyTorch)

Engineered a robust deep learning model using Convolutional Neural Networks and TensorFlow to classify 114 bird species based on audio recordings. Model achieved an impressive accuracy of 93.4%, providing valuable insights for conservationists and ecologists in the wildlife & ecological research sectors.

Bird Classifier developped in tensorflow using pre-trained model from Tensorflow Hub and running on Google Colab

Computer vision website which recognizes and provides information about birds in user-uploaded photos.

Southern African Bird Call Audio Identification Challenge

ResNet-34 Model trained from scratch to classify 450 different species of birds with 98.6% accuracy.

Classifies a bird's species using a neural network in tensorflow..

New is not always better: a comparison of two image classification networks (ResNet-50 vs ConvNeXt).

Code used for my final project in Computer Vision at Texas State University, Spring 2019

Explore deep learning-powered image classification with PyTorch. Achieved 98% accuracy on Natural Images and 95% on Birds Species using AlexNet and EfficientNet-B1. Dive into the code and results!

BirdNET as a systemd service with other features.

Source code for BMBF InnoTruck demo of BirdNET.

Polish bird species recognition - Bird song analysis and classification. Women in Machine Learning & Data Science project.

Applications to identify birds based on their appearance and taxonomy

Determine the 🐦 from its 🎵