DeepAudioNet

Deep Learning-Based Spectrogram Analysis for Animal Sound Classification

Authors: Shivansh Madan, Jiamiao Zhang, Jiasen Zhang, Gordon Ta

This repository contains the implementation of a Convolutional Neural Network (CNN) for classifying animal sounds using spectrogram analysis. By converting audio signals into spectrograms and leveraging the power of deep learning, this project aims to accurately classify animal sounds into predefined categories.

Sources used for developing code in the Gordon branch: https://stackoverflow.com/questions/64574142/how-to-load-a-dataset-starting-from-list-of-images-pytorch

https://stackoverflow.com/questions/44429199/how-to-load-a-list-of-numpy-arrays-to-pytorch-dataset-loader

https://stackoverflow.com/questions/59218671/runtimeerror-output-with-shape-1-224-224-doesnt-match-the-broadcast-shape

https://stackoverflow.com/questions/65440443/runtimeerror-given-groups-1-weight-of-size-32-3-3-3-expected-input4-32

https://stackoverflow.com/questions/72741647/typeerror-cant-convert-cuda0-device-type-tensor-to-numpy-use-tensor-cpu-to