Machine Learning Practical - Coursework 2: Analysing problems with the VGG deep neural network architectures (with 8 and 38 hidden layers) on the CIFAR100 dataset by monitoring gradient flow during training. And exploring solutions using batch normalization and residual connections.

A model based on CNN (Convolutional Neural Networks) in order to classify the CIFAR100 dataset, composed by 60,000 32x32 color images labeled over 100 categories.

Image classification using CNNs

Programming assignments from Deep Learning Class (CSE496/896)

Trained a multiclass classifer network using cifar100 dataset

Projects for Rice Undergraduate Data Science Summer Program

A simple image classification flask app. CNN Model trained on CISNET100 data.

ResNet for CIFAR with Estimator API and tf.keras.Model class

Implementaiton of BSC-Densenet-121 in Pytorch from research paper "Adding Binary Search Connections to Improve DenseNet Performance".

Models with variable output classes designed for CIFAR-100

Image augmentation with mixup image tag

It's a simple Convolutional Neural Network about discriminate cifar-100 datasets.

An ablation study conducted on the CIFAR-100 dataset. Three deep learning architectures are utilized: Convolutional Neural Networks (CNN), Gated Multilayer Perceptrons (gMLP), and Vision Transformers (ViT). The study is built using the PyTorch framework as well as PyTorch Lightning for clean and concise code and Optuna for hyperparameter tuning.

Code repository for the paper titled "MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning"

Classification of CIFAR 100 Images - Transfer Learning - ResNet-50

Modification of VGG19 by applying Model Compression methods: Quantization and LoRA