# lucasjinreal/yolov7_d2

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

Repository: https://github.com/lucasjinreal/yolov7_d2
Canonical: https://ross.abutalabs.com/products/yolov7_d2
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: yolo, yolox, detection, detextron2, tensorrt, yolov6, yolov7, face, transformers, detr, instance-segmentation, onnx, object-detection
Last push: 2023-11-18T05:23:29+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1897, "days_push": 1019, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3109, forks 467 (observed 2026-08-28T04:07:43.877643+00:00)

## What it is
A detectron2-based implementation of YOLOv7 that extends YOLO-style detection to instance segmentation, keypoint detection, and multi-head vision models, with TensorRT/ONNX deployment support. It also supports other SOTA detectors like DETR, DINO, YOLOX, and YOLOv6 for painless training.

## Use cases
- train a custom YOLO object detection model
- run instance segmentation with YOLO
- deploy YOLO models with TensorRT acceleration
- detect faces with YOLO
- build multi-head detection models like pose estimation
- convert YOLO models to ONNX for inference

## When to avoid
- you need the official YOLOv7 implementation or its latest research updates
- you need actively maintained software - the project has been quiet since late 2023
- you want a non-GPL license for commercial products

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python
- tags: object-detection, yolo, detectron2, instance-segmentation, tensorrt, onnx, transformers, detr, model-training, inference, gpu, linux

## Member repositories
- lucasjinreal/yolov7_d2 (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:43.877643+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 2026-08-30T07:26:51.445465+00:00, confidence not recorded.
  - readme: https://github.com/lucasjinreal/yolov7_d2 (fetched 2026-08-28T04:07:43.877643+00:00, sha d3bc4fbac994)
- Data as of 2026-08-30T08:39:29.467469+00:00.