Reverse Dependencies of torchvision

The following projects have a declared dependency on torchvision:

• VideoJEDi — JEPA Embedding Distance - for video distribution quality assessment.
• vila — no summary
• vis4d — Vis4D Python package for Visual 4D scene understanding
• VisCPM — VisCPM model for vision-language understanding and generation
• vish-graph — Graph processing library
• vision-aided-loss — Vision-aided GAN training
• vision-llama — Vision Llama - Pytorch
• vision-transformer — Flexible Vision Transformer (ViT) model for your needs.
• vision-xformer — Vision Xformers
• visioncube — Image Processing Tool
• VisionKan — Vision Transformers implemented using KAN layers
• visionts — Using a visual MAE for time series forecasting.
• visprompt — Repository and basic GUI for experimenting with visual prompting based on SAM and segGPT.
• vist — VisT Python Package for perception and motion understanding
• vistabnet — no summary
• vistec-ser — Speech Emotion Recognition models and training using PyTorch
• vistrans — Unofficial implementations of transfomers models for vision.
• visual-mapping-localization — ['Tools and baselines for visual localization and mapping']
• visual-search-nets — neural network models of visual search behavior
• visualfailureanalysis — Toolkit to visualize the reasoning of image classification networks.
• visualfeaturesearch — A lightweight, interactive tool for interpreting any CNN
• visualizing-training — Modelling Training Dynamics and Interpreting the dynamics
• visuallayer — Open, Clean Datasets for Computer Vision.
• visym-collector — Visym Collector
• vit-image-retrieval — A Vision Transformer based image retrieval system
• vit-pytorch — Vision Transformer (ViT) - Pytorch
• vit-pytorch-implementation — Vision Transformer (ViT) - Pytorch
• ViT-TensorRT — A re-implementation of ViT containing utilities to convert to TensorRT engines and run in Triton.
• vit4elm — Vision Transformers for Exotic Lattice Models
• viturka-nn — A client library for deep federated learning platform.
• vjepa — Moedified from the official PyTorch codebase for the video joint-embedding predictive architecture, V-JEPA, a method for self-supervised learning of visual representations from video.
• vl-datasets — Open, Clean Datasets for Computer Vision.
• VLM-Packages — no summary
• vlm-tools — Tools to work with the VLM-1 API.
• vlmvqa-python — VLmVQA tool
• vltk — The Vision-Language Toolkit (VLTK)
• vod-devkit — The official devkit of the View-of-Delft Prediction dataset.
• voltron-robotics — Voltron: Language-Driven Representation Learning for Robotics.
• voxws — Few Shot Language Agnostic Keyword Spotting (FSLAKWS) System
• vp-suite — A Framework for Training and Evaluating Video Prediction Models
• vpredicto — A library for video frame prediction using SimVP, PredRNN++, MIM, PredNet, Novel GAN and Causal LSTM.
• VPRTempo — VPRTempo: A Fast Temporally Encoded Spiking Neural Network for Visual Place Recognition
• vqa-package — Visual Question Answering (VQA) package
• vqa-python — mVQA tool
• vqvae — PyTorch implementation of VQ-VAE
• vsbasicvsrpp — BasicVSR++ function for VapourSynth
• vscodeformer — CodeFormer function for VapourSynth
• vsdkx-model-yolo-torch — no summary
• vseg-unet — U-net for vessel segmentation
• vsensebox — VSenseBox - Python toolbox for visual sensing.
• vsmidas — MiDaS function for VapourSynth
• wandb-preempt — Code and tutorial on integrating wandb with slurm pre-emption
• Wav2Lipy — Wrapper Package for LipGan Project
• wavemix — WaveMix - Pytorch
• wavpool — A network block with built in spacial and scale decomposition.
• waylay-beta — beta release of the Waylay Python SDK
• waylay-ml-adapter-torch — ML_adapter for torch.
• waypoint-extraction — research project
• wbia-orientation — wbia_orientation - A plug-in for detecting the orientation of various species in images for WBIA system
• wcfutils — Handy utils written by
• web2dataset — no summary
• wenda-gpu — Fast domain adaptation for genomic data
• wepipe — no summary
• what-the-face-classification — CNN image classification trained on FER2013 for the 7 emotion categories.
• wheresmycar — Detect vehicle license plates
• whisper-pyannote-fusion — Fuse whisper and pyannote results
• whisper-run — Whisper with speaker diarization
• whisperplus — WhisperPlus: A Python library for WhisperPlus API.
• whitebox-adversarial-toolbox — WHite-box Adversarial Toolbox (WHAT) - Python Library for Deep Learning Security
• whittle — Two-stage neural architecture search for large language models
• whorl — no summary
• wild-time-data — WILDS distribution shift data
• wildbook-ia — Wildbook IA (WBIA) - Machine learning service for the WildBook project
• wilds — WILDS distribution shift benchmark
• wildtime — WILDS distribution shift benchmark
• wildtorch — WildTorch: Leveraging GPU Acceleration for High-Fidelity, Stochastic Wildfire Simulations with PyTorch
• wk-classify — A package of tools for building deep-learning classification programs.
• wmh-seg — WMH segmentation for FLAIR images
• woollylib — This is a pytorch based utilities library which will help you for training and visualizing computer vision models.
• wow-ai-sam — Finetune segment-anything
• wpodnet-pytorch — The implementation of ECCV 2018 paper "License Plate Detection and Recognition in Unconstrained Scenarios" in PyTorch
• ws-benchmark — a weak supervision learning benchmark
• wsidata — no summary
• wsiloader — An efficient PyTorch dataloader for working with Whole-Slide Images
• wsinfer — Run patch-based classification on pathology whole slide images.
• wsinfer-mil — Run specimen-level inference on whole slide images.
• wxbs-benchmark — Code for benchmarking image matchers on WxBS dataset
• wzyFunc — My Python Package
• x-clip — X-CLIP
• x-deep — XDeep is an open-source package for Interpretable Machine Learning.
• x-segment-anything — no summary
• xai-explainer — A package for explaining deep learning models
• xaitk-jatic — Integration package to support interfacing, implementation and example needs for the JATIC.
• xaitk-saliency — Visual saliency map generation interfaces and baseline implementations for explainable AI.
• xaitk-saliency-demo — Web application demonstrating XAITK Saliency functionality
• xchem-chimp — XChem CHIMP
• XCurve — machine learning package
• XCurveLearn — machine learning package
• xn-ultralytics — This is a public fork of Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification. Free for anyone to use, for non-commercial purposes.
• xplai — xpl.ai client SDK.