Reverse Dependencies of torchvision
The following projects have a declared dependency on torchvision:
- vendi-score — A diversity metric for machine learning
- versign — Signature verification package for verifying offline signatures using writer-independent features.
- vflow — A framework for doing stability analysis with PCS.
- vformer — A modular PyTorch library for vision transformer models
- vhh-od — Object Detection and Tracking Package
- video-clip — AskVideos-VideoCLIP model
- video-dataloader-for-pytorch — A small example package
- video-diffusion-pytorch — Video Diffusion - Pytorch
- vila — no summary
- vis4d — Vis4D Python package for Visual 4D scene understanding
- VisCPM — VisCPM model for vision-language understanding and generation
- vision-aided-loss — Vision-aided GAN training
- vision-llama — Vision Llama - Pytorch
- vision-xformer — Vision Xformers
- visioncube — Image Processing Tool
- 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
- visuallayer — Open, Clean Datasets for Computer Vision.
- visym-collector — Visym Collector
- vit-pytorch — Vision Transformer (ViT) - Pytorch
- vit-pytorch-implementation — Vision Transformer (ViT) - Pytorch
- vit4elm — Vision Transformers for Exotic Lattice Models
- vl-datasets — Open, Clean Datasets for Computer Vision.
- vlmvqa-python — VLmVQA tool
- vltk — The Vision-Language Toolkit (VLTK)
- voltron-robotics — Voltron: Language-Driven Representation Learning for Robotics.
- vp-suite — A Framework for Training and Evaluating Video Prediction Models
- 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
- VWS-Python-Mock — A mock for the Vuforia Web Services (VWS) API.
- 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
- 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.
- whisper-pyannote-fusion — Fuse whisper and pyannote results
- whisperplus — WhisperPlus: A Python library for WhisperPlus API.
- whitebox-adversarial-toolbox — WHite-box Adversarial Toolbox (WHAT) - Python Library for Deep Learning Security
- 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.
- 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
- 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.
- xai-explainer — A package for explaining deep learning models
- 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.
- xregi — A package for automatic 2D/3D registration of X-ray and CT images
- xron — A deep neural network basecaller for nanopore sequencing.
- xt-cvdata — Utilities for building and working with computer vision datasets
- xt-models — Models and model utilities for common ML tasks
- xtuner — An efficient, flexible and full-featured toolkit for fine-tuning large models
- y5facegg — Packaged version of the Yolov5 facial landmark detector
- y5gg — Packaged version of the Yolov5 object detector
- yaaf — YAAF: Yet Another Agents Framework
- yann — yet another neural network library
- yolite — Yolov5-Lite: Minimal YoloV5 Implementation
- Yolo-Distribution-Distillation-Demo — Run inference on Yolo Distribution Distillation model.
- Yolo-ED2-Demo — Run inference on Yolo Distribution Distillation model.
- yolo-labeler — Remove image background and label object in yolo format
- yolo-v5-tflite — YOLO_v5 - most advanced vision AI model for object detection in TFLite.
- yolo5face — Wrapper over Yolo5Face for a more convenient inference.
- yolotest — Ultralytics YOLOv8
- yolotext — no summary