YOLOv7-D6 (44 fps)

Reported on 5 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

3DonCOCO test-dev
box mAP· uses extra data· 2022-07-06
56.6
best: 66 (Co-DETR)
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors arXiv:2207.02696
2D ClassificationonCOCO test-dev
box mAP· uses extra data· 2022-07-06
56.6
best: 66 (Co-DETR)
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors arXiv:2207.02696
2D Object DetectiononCOCO test-dev
box mAP· uses extra data· 2022-07-06
56.6
best: 66 (Co-DETR)
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors arXiv:2207.02696
16konCOCO test-dev
box mAP· uses extra data· 2022-07-06
56.6
best: 66 (Co-DETR)
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors arXiv:2207.02696

Computer Vision1 result

Object DetectiononCOCO test-dev
box mAP· uses extra data· 2022-07-06
56.6
best: 66 (Co-DETR)
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors arXiv:2207.02696