keremberke / object-detection Open weights updated 2 years ago

yolov8m-table-extraction

Name: yolov8m-table-extraction
Author: keremberke

model.overrides['conf'] = 0.25 # NMS confidence threshold model.overrides['iou'] = 0.45 # NMS IoU threshold model.overrides['agnosticnms'] = False # NMS class-agnostic model.overrides['maxdet'] = 1000 # maximum number of detections per image

Params

8.0 M

Context

—

Downloads 30d

191 K

Likes

Licence: agpl-3.0 Not gated View on Hugging Face ↗

Download history

daily snapshots · 20 days

224 K191 K

Oct 5Oct 11Oct 18Oct 24

Specifications

Parameters: 8.0 M
Licence: agpl-3.0
First seen on the Hub: 2023-01-29
Training datasets: keremberke/table-extraction
table-extraction (reported): 0.95194
Added to our catalog: 2026-10-05

Compare with any object-detection model

Popular comparisons

table-transformer-structure-recognition 1.3 M rtdetr_r101vd_coco_o365 1.2 M PP-DocLayoutV3_safetensors 922 K yolos-small 697 K table-transformer-detection 328 K rtdetr_v2_r18vd 290 K