# DrSleep/tensorflow-deeplab-resnet

DeepLab-ResNet rebuilt in TensorFlow

Repository: https://github.com/DrSleep/tensorflow-deeplab-resnet
Canonical: https://ross.abutalabs.com/products/tensorflow-deeplab-resnet
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, deeplab-resnet, pascal-voc, semantic-segmentation
Archived: true
Last push: 2021-10-11T04:52:36+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3532, "days_push": 1787, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1258, forks 424 (observed 2026-08-28T04:04:09.489332+00:00)

## What it is
A TensorFlow re-implementation of the DeepLab-ResNet model for semantic image segmentation, trained and evaluated on the PASCAL VOC dataset. It includes training, multi-scale training, and evaluation scripts with pretrained checkpoints.

## Use cases
- semantic segmentation of images with tensorflow
- train deeplab resnet on pascal voc
- segment objects in images using deep learning
- fine-tune deeplab on my own dataset
- evaluate semantic segmentation model mean IoU
- pretrained segmentation model for image labeling

## When to choose
- you need a DeepLab-v2 ResNet implementation in TensorFlow for PASCAL VOC-style segmentation
- you want pretrained checkpoints and training scripts to fine-tune on a custom dataset
- you are reproducing classic semantic segmentation research results

## When to avoid
- you need modern TensorFlow 2.x or PyTorch - this targets legacy TF 1.x and Python 2.7
- you want actively maintained segmentation tooling with recent updates
- you need real-time or production-grade segmentation pipelines

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, image-processing
- platform: python
- tags: semantic-segmentation, tensorflow, resnet, pascal-voc, deeplab, linux, gpu

## Member repositories
- DrSleep/tensorflow-deeplab-resnet (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.489332+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 2026-08-30T05:05:33.208147+00:00, confidence not recorded.
  - readme: https://github.com/DrSleep/tensorflow-deeplab-resnet (fetched 2026-08-28T04:04:09.489332+00:00, sha bb9e70828f82)
- Data as of 2026-08-30T08:39:29.467469+00:00.