These models are trained on deepghs/anime_face_detection and open-sourced real photos datasets.

So both anime and photos are supported.

Use this with dghs-realutils

pip install dghs-realutils
from realutils.detect import detect_faces

print(detect_faces('yolo/solo.jpg'))
# [((157, 94, 252, 208), 'face', 0.8836570382118225)]
print(detect_faces('yolo/2girls.jpg'))
# [((718, 154, 1110, 728), 'face', 0.8841166496276855), ((157, 275, 519, 715), 'face', 0.8668240904808044)]
print(detect_faces('yolo/3+cosplay.jpg'))
# [((349, 227, 413, 305), 'face', 0.8543888330459595), ((383, 61, 432, 117), 'face', 0.8080574870109558), ((194, 107, 245, 162), 'face', 0.8035706877708435)]
print(detect_faces('yolo/multiple.jpg'))
# [((1070, 728, 1259, 985), 'face', 0.8765808939933777), ((548, 286, 760, 558), 'face', 0.8693087697029114), ((896, 315, 1067, 520), 'face', 0.8671919107437134), ((1198, 220, 1342, 406), 'face', 0.8485829830169678), ((1376, 526, 1546, 719), 'face', 0.8469308018684387)]

For more information, see documentation of realutils.

Model Type FLOPS Params F1 Score Threshold precision(B) recall(B) mAP50(B) mAP50-95(B) F1 Plot Confusion Labels
face_detect_v0_s_yv12 yolo 21.5G 9.25M 0.74 0.272 0.86931 0.6404 0.73074 0.42652 plot confusion face
face_detect_v0_n_yv12 yolo 6.48G 2.57M 0.7 0.258 0.85246 0.59089 0.6793 0.39182 plot confusion face
face_detect_v0_l_yv11 yolo 87.3G 25.3M 0.77 0.291 0.88458 0.67474 0.76666 0.45722 plot confusion face
face_detect_v0_m_yv11 yolo 68.2G 20.1M 0.76 0.262 0.87947 0.67315 0.76073 0.45288 plot confusion face
face_detect_v0_s_yv11 yolo 21.5G 9.43M 0.73 0.271 0.87001 0.63572 0.72683 0.42706 plot confusion face
face_detect_v0_n_yv11 yolo 6.44G 2.59M 0.7 0.263 0.86044 0.58577 0.67641 0.38975 plot confusion face
face_detect_v0_l yolo 165G 43.6M 0.76 0.277 0.87894 0.67335 0.76313 0.4532 plot confusion face
face_detect_v0_m yolo 79.1G 25.9M 0.75 0.277 0.87687 0.66265 0.75114 0.44262 plot confusion face
face_detect_v0_s yolo 28.6G 11.1M 0.73 0.282 0.86932 0.63557 0.72494 0.42219 plot confusion face
face_detect_v0_n yolo 8.19G 3.01M 0.7 0.257 0.85337 0.58877 0.67471 0.38692 plot confusion face
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support object-detection models for dghs-imgutils library.

Dataset used to train deepghs/real_face_detection

Space using deepghs/real_face_detection 1