Istvan Fehervari's repositories
optimizer-benchmark
Benchmark Suite for Stochastic Gradient Descent Optimization Algorithms in Pytorch
albumentations
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
AnyDoor
Official implementations for paper: Anydoor: zero-shot object-level image customization
cloth-segmentation
This repo contains code and a pre-trained model for clothes segmentation.
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
gputil
A Python module for getting the GPU status from NVIDA GPUs using nvidia-smi programmically in Python
groundedsam
Python package to run the Grounded SAM model
hearthstone-deckbuilder
Hearthstone Deck Builder Web Application
incubator-mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
latent-encoders
Repository to train and fine-tune latent encoders
llama_index
LlamaIndex is a data framework for your LLM applications
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
pytorch-openpose
pytorch implementation of openpose including Hand and Body Pose Estimation.
scikit-video
Video Processing in Python
Self-Correction-Human-Parsing
An out-of-box human parsing representation extractor.
SLiMe
1-shot image segmentation using Stable Diffusion
SparK
[ICLR'23 Spotlight] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
temporal-segment-networks
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [Arxiv'22] "ViTPose+: Vision Transformer Foundation Model for Generic Body Pose Estimation"