Explore live open-source projects and AI models.

An image caption generation model using PyTorch

This is a Deep Learning model based on PyTorch. We train it for image classification on CIFAR10.

The official Pytorch implementation for the paper, Learning Brain Tumor Representation in 3D High-Resolution MR Images via Interpretable State Space Models

Designed and implemented a scalable solution for generating medical reports from chest X-ray images, leveraging PyTorch and AWS VPM. Employed BioViLT for image features extraction and developed an alignment model to align image features with text data. Fine-tuning a Large Language Model (BioGPT... Read more

A PyTorch-based multimodal classifier that fuses vision and language models (ResNet, BERT, RoBERTa, ViT) to process image-text pairs for advanced classification tasks.

A pytorch implementation of Bridging Component Learning with Degradation Modelling for Blind Image Super-Resolution.

Welcome to the "Image Generation from Scratch" repository! This project is dedicated to building image generation models from scratch using PyTorch. In this repository, you'll find both GANs (Generative Adversarial Networks) and Diffusion models implemented from the ground up.

A PyTorch Implementation of Vision-Transformers to classify the classes of CIFAR-100 dataset, the model implemented from the paper: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

This repository defines a python class that can be used to load data for the tf.keras.model.fit_generator function by using a torch.utils.data.Dataloader object for image data. This way transforms on the input image data can be transformed using the PyTorch library but still be used to fit a tf.k... Read more

Medical image classification of skin lesions using PyTorch and scikit-learn. Combines a Deep Learning pipeline (Convolutional Autoencoder + neural classifier) with a hybrid approach leveraging Vision Transformer embeddings and XGBoost for robust and efficient model comparison.