AlbertoSabater
Follow
Stars
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
A playbook for systematically maximizing the performance of deep learning models.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Lightweight Stable Diffusion v 2.1 web UI: txt2img, img2img, depth2img, inpaint and upscale4x.
fast-stable-diffusion + DreamBooth
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
Over 200 figures and diagrams of the most popular deep learning architectures and layers FREE TO USE in your blog posts, slides, presentations, or papers.
Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
Experiments with supervised contrastive learning methods with different loss functions
Repositorio del Proyecto ACutStic desarrollado en los directos de Twitch del canal DotCSV. El objetivo es programar una herramienta para Adobe Premiere que permita automatizar el proceso de edición…
Awesome work on hand pose estimation/tracking
Memory Enhanced Global-Local Aggregation for Video Object Detection, CVPR2020
Visual localization made easy with hloc
Skeleton-based Action Recognition
End-to-End Object Detection with Transformers
Keras Temporal Convolutional Network. Supports Python and R.
Attention mechanism for processing sequential data that considers the context for each timestamp.
Keras Attention Layer (Luong and Bahdanau scores).
Sequence to Sequence Learning with Keras
Human Pose Estimation Related Publication
Basics of 2D and 3D Human Pose Estimation.
Official Implementation in Pytorch and Tensorflow of 3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation
A curated list of community detection research papers with implementations.
A Keras implementation of CenterNet with pre-trained model (unofficial)