A ready-to-use pytorch dataloader for audio classification, speech classification, speaker recognition, etc. with in-GPU augmentations

This project focuses on detecting lung cancer from medical images using Convolutional Neural Networks (CNNs). It includes custom-built CNNs and fine-tuned pretrained models such as ResNet101, DenseNet121, AlexNet, and VGG16 to improve detection accuracy.

Successfully established an image classification model using PyTorch to classify the images of several distinct natural sceneries such as mountains, glaciers, forests, seas, streets and buildings with an accuracy of 86%.