# donnyyou/torchcv

TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision

Repository: https://github.com/donnyyou/torchcv
Canonical: https://ross.abutalabs.com/products/torchcv
Homepage: https://pytorchcv.com
Language: Shell
License: Apache-2.0
License Family: permissive
Last push: 2020-11-19T05:40:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2875, "days_push": 2113, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2251, forks 367 (observed 2026-08-28T04:06:31.030614+00:00)

## What it is
TorchCV is a PyTorch-based framework providing reimplementations of deep learning models for major computer vision tasks. It covers image classification, semantic and instance segmentation, object detection, pose estimation, and GANs with pretrained models and reproducible results.

## Use cases
- train a semantic segmentation model like DeepLabV3 or PSPNet
- run object detection with YOLOv3 or Faster R-CNN
- classify images with ResNet or DenseNet backbones
- estimate multi-person 2D pose with OpenPose
- do image-to-image translation with CycleGAN or Pix2pix
- reproduce paper results for computer vision research

## When to choose
- you need reference PyTorch implementations of classic CV models
- you want pretrained models and reproducible benchmark numbers for vision tasks
- you're doing CV research and want a unified training framework

## When to avoid
- you need a production-ready inference serving system
- you require the latest architectures or active updates, since the project hasn't released since 2020
- you want a simple pip-installable library rather than a source-based framework with compiled extensions

## Facets
- artifact type: framework
- maturity: maintenance
- function: deep-learning, machine-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python
- tags: pytorch, semantic-segmentation, object-detection, image-classification, pose-estimation, gan, instance-segmentation, research, linux, gpu

## Member repositories
- donnyyou/torchcv (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:31.030614+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:43:50.361461+00:00, confidence not recorded.
  - readme: https://github.com/donnyyou/torchcv (fetched 2026-08-28T04:06:31.030614+00:00, sha 8e5592d364eb)
- Data as of 2026-08-30T08:39:29.467469+00:00.