PyTorch Vision (TorchVision)PyTorch官方computer视觉库，带有数据集、变换和预训练模型

4.7 (6)

审阅者 Daniel Nikulshyn·更新 2026年7月

Computer Vision Open Source PyTorch Deep Learning Pre-Trained Models Python Research

概览

TorchVision 是 PyTorch 的计算机视觉配套库，提供精选的热门数据集、图像变换工具以及预训练模型架构。它为研究人员和开发者构建图像分类、目标检测、分割以及视频理解流程提供了基础工具包。该库包含了已可直接使用的知名架构实现，如 ResNet、EfficientNet、Vision Transformers、Faster R‑CNN 和 Mask R‑CNN，并提供在标准基准上训练好的权重。它还提供高效的 I/O 操作、GPU 加速的变换，并与更广泛的 PyTorch 生态系统无缝集成，使得原型化和部署视觉工作流更加便捷。

主要功能

预训练模型支持分类、检测和分割
可组合的图像和视频变换
载入器支持数据集如COCO、ImageNet和CIFAR
NMS、RoI池化和包围盒操作员
对图像和视频的原生支持和解码
TorchScript和ONNX导出兼容性

价格

模型: Freemium
分类: 计算机视觉
评分: 4.7 / 5 (6)

使用场景

使用预训练模型进行图像分类

利用预训练权值快速进行图像分类开发，使用预训练的架构，如ResNet、EfficientNet或视觉变换器

物体检测和分割流程

使用Faster R-CNN和Mask R-CNN等预先构建的运算符，创建检测和实例分割系统，内置NMS和RoI池化等工具

基准数据集实验

快速载入和预先处理标准数据集，如COCO、ImageNet和CIFAR，用于可复制的计算机视觉研究和原型开发

生产模型导出

将训练后的视觉模型导出到TorchScript或ONNX，为生产环境和跨平台推理运行时进行部署

优点 & 缺点

优点

紧密集成到PyTorch工作流中
预训练模型和权重的丰富选择
PyTorch团队的活跃维护
GPU加速的图像变换
内置访问到常见的视觉数据集

缺点

需要PyTorch知识才能有效使用
比社区库如timm少一些前沿模型
文档可能落后于新特性发布
对非视觉模态的有限支持

对决战绩

在万神殿中参与了 1 对决。

第1

第2

第3

Last battle

#6
Computer Vision Showdown — May 1, 2026
May 1, 2026 · #6 of 10

评测

4.7

6 个评分的平均值。

登录以留下评测。

Jamal Carter

Apr 7, 2026

Compared a few options

Evaluated this against two competitors. Where it wins: torchScript and ONNX export compatibility and active maintenance by the PyTorch team. Where it lags: limited support for non-vision modalities. On balance the feature set — especially native support for reading and decoding images and video — justifies the 4 stars for our use case.

Aisha Khan

Feb 4, 2026

Does the job

Pretty happy overall. Native support for reading and decoding images and video just works and wide selection of pre-trained models and weights. Requires PyTorch knowledge to use effectively can be annoying, but no dealbreakers — I'd recommend it to a friend without hesitating.

Margaret Whitfield

Dec 16, 2025

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on composable image and video transforms, and tight integration with PyTorch workflows caught me off guard. Requires PyTorch knowledge to use effectively is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Nadia Petrova

Nov 19, 2025

Years in this space

I've evaluated a lot of these over the years. What stands out here is loaders for datasets like COCO, ImageNet, and CIFAR — handled better than most — and active maintenance by the PyTorch team. Worth the time if this is your use case.

Tariq Aziz

Sep 18, 2025

Solid for our team

We rolled this out across the team last quarter and active maintenance by the PyTorch team. TorchScript and ONNX export compatibility fits neatly into how we already work, and loaders for datasets like COCO, ImageNet, and CIFAR removed a step we used to do by hand. but it has held up under daily use.

Diego Fernández

Jul 18, 2025

Use it every day

Honestly didn't expect to like it this much. Composable image and video transforms is exactly what I needed, and gPU-accelerated image transforms. I do wish requires PyTorch knowledge to use effectively, but I reach for it almost every day now and it just clicks.