Showing 21-29 of 29 projects
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution.
Classification models trained on ImageNet, for use in computer vision and image classification tasks.
A Tokens-to-Token Vision Transformer (T2T-ViT) model for training Vision Transformers from scratch on ImageNet.
A comprehensive Python library for evaluating object detection models using various metrics like mAP, AR, and STT-AP.
A library for studying the robustness of computer vision models to various corruptions and perturbations.
Res2Net-PretrainedModels is an official PyTorch implementation of the Res2Net multi-scale backbone architecture for computer vision tasks.
EfficientFormer is a deep learning model for efficient image segmentation and object detection.
A smaller subset of 10 easily classified classes from Imagenet, and a little more French
A high-resolution network (HRNet) model for image classification trained on the ImageNet dataset.
Get weekly updates on trending AI coding tools and projects.