README.md

metadata

license: apache-2.0
datasets:
  - visdrone
model-index:
  - name: ENOT-AutoDL/yolov8s_visdrone
    results:
      - task:
          type: object-detection
          dataset:
            type: visdrone
            name: visdrone
        metrics:
          - type: precision
            value: 49,4
            name: mAP50(baseline)
          - type: precision
            value: 48,4
            name: mAP50(GMACs x2)
          - type: precision
            value: 46,0
            name: mAP50(GMACs x3)
library_name: ultralytics
pipeline_tag: object-detection
tags:
  - yolov8
  - ENOT-AutoDL
  - yolo
  - vision
  - ultralytics
  - object-detection

ENOT-AutoDL YOLOv8 optimization on VisDrone dataset

This repository contains models accelerated with ENOT-AutoDL framework. We trained yolov8s on VisDrone dataset and used it as our baseline. Also we provide simple python script to measure flops and metrics.

YOLOv8 Small

Model	GMACs	Image Size	mAP50	mAP50-95
YOLOv8 Ultralytics Baseline	14,28	640	40,2	24,2
YOLOv8n Enot Baseline	8,57	928	42,9	26,0
YOLOv8s Enot Baseline	30,03	928	49,4	30,6
YOLOv8s (x2)	15,01 (x2)	928	48,3 (-1,1)	29,8 (-0,8)
YOLOv8s (x3)	10,01 (x3)	928	46,0 (-3,4)	28,3 (-2,3)

Validation

To validate results, follow this steps:

1. Install all required packages:

pip install -r requrements.txt

2. Use validation script:

python validate.py enot_neural_architecture_selection_x2/weights/best.pt --imgsz 928

3. Use measure_macs script:

python measure_macs.py enot_neural_architecture_selection_x2/weights/best.pt --imgsz 928