ResNet-34 Model trained from scratch to classify 450 different species of birds with 98.6% accuracy.
-
Updated
Mar 3, 2023 - Jupyter Notebook
ResNet-34 Model trained from scratch to classify 450 different species of birds with 98.6% accuracy.
Signature Work @ DKU: Large Scale Bird Sound Recognition in China Region
This is my solution for the RecVis Challenge where i ended 1st on fine-grained classification on bird dataset
Deep learning bird species classifier achieving 96.51% accuracy using PyTorch and transfer learning. Implements 5 approaches from traditional computer vision (HOG, SIFT) to CNNs (ResNet-50, VGG-16). Trained on 25 Indian bird species with 22,498 images. Comprehensive comparison of feature extraction vs deep learning.
This workspace contains a trained MobileNetV2 model for bird-species classification, the notebooks used to train and test it, and the dataset layout used for training/validation/testing.
Bird Classification application using yolov8 model trained on the CalTechBirds dataset. Segmentation was also implemented using UNet.
Bird Watching App
Fuses the BirdNET v2.4 feature extractor with a BSG regional classifier into a single end-to-end ONNX model
ML app that recognizes bird by its photo
Add a description, image, and links to the bird-classification topic page so that developers can more easily learn about it.
To associate your repository with the bird-classification topic, visit your repo's landing page and select "manage topics."