Reverse Dependencies of iopath
The following projects have a declared dependency on iopath:
- ammico-lavis — LAVIS - A One-stop Library for Language-Vision Intelligence
- augly — A data augmentations library for audio, image, text, & video.
- bucketed-scene-flow-eval — Bucketed Scene Flow Evaluation
- cryoSPHERE — Structural heterogeneous cryoEM reconstruction: https://github.com/Gabriel-Ducrocq/cryoSPHERE
- dinov2 — PyTorch code and models for the DINOv2 self-supervised learning method.
- drop-backend — API and Command line tools for building drop
- easyeditor — easyeditor - Editing Large Language Models
- efficient-ocr — Efficient OCR
- efficient-track-anything — Efficient Track Anything
- encoded-video — Video utilities
- EncodedUriVideo — Video utilities
- ezflow — A PyTorch library for optical flow estimation using neural networks
- fake-check — baseline deepcheck module
- featureforest — A napari plugin for segmentation using vision transformer features
- Few-Shot-Learning-NLP — This library provides tools and utilities for Few Shot Learning in Natural Language Processing (NLP).
- ft2bt — Automatic conversion from fault trees into behavior trees with formal verification capabilities
- fvbitcore — Fork of https://github.com/facebookresearch/fvcore with support for bitorch
- geoai-detectron2 — Detectron2 is FAIR's next-generation research platform for object detection and segmentation.
- groundino-samnet — A SAM model with GroundingDINO model for feet segmentation
- jj-pytorchvideo — A video understanding deep learning library.
- meddlr — Meddlr is a config-driven framework built to simplify ML-based medical image reconstruction and analysis.
- mess-benchmark — MESS – Multi-domain Evaluation of Semantic Segmentation
- mimir-ai — no summary
- modelscope — ModelScope: bring the notion of Model-as-a-Service to life.
- MovieChat — Long video understanding
- Ocrversion1 — no summary
- Ocrversion2 — no summary
- omnidocs — no summary
- parlai — Unified platform for dialogue research.
- pixellib — PixelLib is a library used for easy implementation of semantic and instance segmentation of objects in images and videos with few lines of code.PixelLib makes it possible to train a custom segmentation model using few lines of code.PixelLib supports background editing of images and videos using few lines of code.
- pl-extension — extension for pytorch-lightning
- projectaria-atek — Aria training and evaluation kits
- pytorch3d — PyTorch3D is FAIR's library of reusable components for deep Learning with 3D data.
- salesforce-lavis — LAVIS - A One-stop Library for Language-Vision Intelligence
- samv2 — fork of the official SAMv2 implementation with cpu support
- samv2-webcam — CPU compatible fork of the official SAMv2 implementation with Webcam support
- shapeaxi — Shape Analysis Exploration and Interpretability
- skm-tea — A package for interacting with, visualizing, and benchmarking the SKM-TEA dataset
- sssegmentation — SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch
- t2v-metrics — Evaluating Text-to-Visual Generation with Image-to-Text Generation.
- TMtest1 — TradeMaster - A platform for algorithmic trading
- torchmultimodal-nightly — PyTorch Multimodal Library
- torchrec — TorchRec: Pytorch library for recommendation systems
- torchrec-cpu — Pytorch domain library for recommendation systems
- torchrec-nightly — Pytorch domain library for recommendation systems
- torchrec-nightly-cpu — Pytorch domain library for recommendation systems
- TradeMaster-try — TradeMaster - A platform for algorithmic trading
- trademaster-try1 — TradeMaster - A platform for algorithmic trading
- trademaster406 — TradeMaster - A platform for algorithmic trading
- turbo-alignment — turbo-alignment repository
- unimernet — UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition
- urartu — An open-source NLP framework that offers high-level wrappers designed for effortless launch, enhanced reproducibility, superior control, and unmatched flexibility for your experiments.
- video-clip — AskVideos-VideoCLIP model
- vissl — VISSL is an extensible, modular and scalable library for SOTA Self-Supervised Learning with images.
1