facebook / object-detection updated 2 years ago

detr-resnet-50

Name: detr-resnet-50
Author: facebook

DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images). It was introduced in the paper End-to-End Object Detection with Transformers by Carion et al. and first released in this repository.

Params

40 M

Context

1,024

Downloads 30d

544 K

Likes

965

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.4 M544 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.2 GB	0.7 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: DetrForObjectDetection
Parameters: 40 M
Tensor type: F32
Context length: 1,024
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: coco
Added to our catalog: 2026-07-28

Compare with

table-transformer-structure-recognition 1.5 M table-transformer-detection 1.2 M PP-DocLayoutV3_safetensors 822 K yolos-small 746 K rtdetr_r101vd_coco_o365 416 K table-transformer-structure-recognition-v1.1-all 240 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB