PyTorch implementations of image classification networks

Implementation of Residual Networks (ResNet) - Deep Residual Learning for Image Recognition '15

Neural network for object classification

El proyecto se centra en la destilación de conocimiento y técnicas de explicabilidad para mejorar el rendimiento de redes neuronales en imágenes naturales.

Pytorch based tools for experimenting with the cifar-10 and cifar-100 datasets

DeltaGrad: An adaptive deep learning optimizer utilizing dynamic reliability metrics and windowed inertia to enhance gradient stability and noise resilience.

Efficient Inference techniques implemented in PyTorch for computer vision.

Mini-silly image classifier UI with tensorflow and PyQT5.

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

this repo. contains Convulotional Neural Network implementation using Tensoreflow python

Classifiers for the CIFAR-10 and CIFAR-100 datasets

Transfer Learning to Classify CIFAR-100 images

Image recognition on CIFAR 10, CIFAR 100, Caltech 101 and Caltech 256 datasets. With the implementation of WideResNet, InceptionV3 and DenseNet neural networks.

This project aimed to determine the ideal hyperparameters to classify the CIFAR-100 dataset.

It's a project to apply convolutional neural networks to the problem of image classification from the CIFAR 100 dataset.

We implement NNCLR and a novel clustering-based technique for contrastive learning that we call KMCLR. We show that applying a clustering technique to obtain prototype embeddings and using these prototypes to form positive pairs for contrastive loss can achieve performances on par with NNCLR on CIFAR-100 while storing 0.4% of the number of vectors.

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

Code for zeta-mixup (ζ-mixup), a data augmentation technique that is an N-sample generalization of mixup.

Plug-and-play collaboration between specialized Tsetlin machines