Explore live open-source projects and AI models.

A PyTorch implementation of the paper "Deep inside convolutional networks: Visualising image classification models and saliency maps"

MegaDepth_Tensorflow. Using this model, you can convert RGB image into depth map. The original version is PyTorch, here we convert it to TensorFlow version so that someone can deploy it on edge device or mobile.

Forked from https://github.com/rwightman/pytorch-image-models

Pytorch based Android app, which classifies images using MobileNet-V2 model, takes image using CameraX API

This is a warehouse for MambaVision-Pytorch-model, can be used to train your image-datasets for vision tasks.

Computer Vision Model in PyTorch that detects Brain Hemorrhage in Computed Tomography (CT) imaging

Pytorch Implementation of DCGAN as a python package. Easily train on any image datasets and generate new images. Some pertained models are available for test.

PyTorch implementation of efficient image super-resolution models, e.g. SRCNN, ESPCN, FSRCNN, DRCN, VDSR, DRRN, EDSR, LapSRN, IDN, CARN etc.

Train (fine-tune) OpenAI's CLIP-like models on custom image-caption data sets, cf. COCO dataset. PyTorch implementation.

[ACCV 2024] Official PyTorch implementation of "Diffusion Model Compression for Image-to-Image Translation"