deepghs/real_person_detection

By deepghs · ↓ 0 · ♥ 3 · Updated 2025-02-20

What's in this repo

This page lists the files in deepghs/real_person_detection, including model.onnx and more.

8 ONNX models (.onnx files)
130 files, including 56 .png, 24 .json, 16 .jpg, 8 .0, 8 .onnx, 8 .pt
Repository size ~824 MB
Last updated 2025-02-20

ONNX files

File	Size	Download
person_detect_v0_l/model.onnx	167 MB	Download
person_detect_v0_l_yv11/model.onnx	96.7 MB	Download
person_detect_v0_m/model.onnx	98.7 MB	Download
person_detect_v0_m_yv11/model.onnx	76.6 MB	Download
person_detect_v0_n/model.onnx	11.6 MB	Download
person_detect_v0_n_yv11/model.onnx	10.0 MB	Download
person_detect_v0_s/model.onnx	42.5 MB	Download
person_detect_v0_s_yv11/model.onnx	36.1 MB	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

These models are trained on deepghs/anime_person_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_persons

print(detect_persons('yolo/solo.jpg'))
#[((0, 30, 398, 599), 'person', 0.926707923412323)]
print(detect_persons('yolo/2girls.jpg'))
# [((0, 74, 760, 1598), 'person', 0.7578195333480835), ((437, 33, 1200, 1600), 'person', 0.6875205039978027)]
print(detect_persons('yolo/3+cosplay.jpg'))
# [((106, 69, 347, 591), 'person', 0.8794167041778564), ((326, 14, 592, 534), 'person', 0.8018194437026978), ((167, 195, 676, 675), 'person', 0.5351650714874268)]
print(detect_persons('yolo/multiple.jpg'))
# [((1305, 441, 1891, 1534), 'person', 0.8789498805999756), ((206, 191, 932, 1533), 'person', 0.8423126935958862), ((1054, 170, 1417, 1055), 'person', 0.8138357996940613), ((697, 659, 1473, 1534), 'person', 0.7926754951477051), ((685, 247, 1128, 1526), 'person', 0.5261526703834534), ((690, 251, 1125, 1126), 'person', 0.4193646311759949)]

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
person_detect_v0_l_yv11	yolo	87.3G	25.3M	0.79	0.359	0.84037	0.74055	0.82796	0.57272	plot	confusion	`person`
person_detect_v0_m_yv11	yolo	68.2G	20.1M	0.78	0.351	0.83393	0.73614	0.82195	0.56267	plot	confusion	`person`
person_detect_v0_s_yv11	yolo	21.5G	9.43M	0.75	0.344	0.82356	0.6967	0.79224	0.52304	plot	confusion	`person`
person_detect_v0_n_yv11	yolo	6.44G	2.59M	0.71	0.325	0.80096	0.64148	0.74612	0.46875	plot	confusion	`person`
person_detect_v0_l	yolo	165G	43.6M	0.79	0.359	0.83674	0.74182	0.82536	0.57022	plot	confusion	`person`
person_detect_v0_m	yolo	79.1G	25.9M	0.78	0.363	0.83439	0.72529	0.81314	0.55388	plot	confusion	`person`
person_detect_v0_s	yolo	28.6G	11.1M	0.76	0.346	0.82522	0.69696	0.79105	0.52201	plot	confusion	`person`
person_detect_v0_n	yolo	8.19G	3.01M	0.72	0.32	0.80883	0.64552	0.74996	0.47272	plot	confusion	`person`

Model info

object-detection dghs-imgutils

dghs-imgutils tensorboard onnx art anime photo person object-detection dataset:deepghs/real_person_detection dataset:deepghs/anime_person_detection region:us

↓ 0 ♥ 3

Created: 2025-02-06

Updated: 2025-02-20

View on Hugging Face

Files (130)

.gitattributes

README.md

person_detect_v0_l/F1_curve.png

person_detect_v0_l/PR_curve.png

person_detect_v0_l/P_curve.png

person_detect_v0_l/R_curve.png

person_detect_v0_l/confusion_matrix.png

person_detect_v0_l/confusion_matrix_normalized.png

person_detect_v0_l/events.out.tfevents.1738876259.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.3804866.0

person_detect_v0_l/labels.jpg

person_detect_v0_l/labels.json

person_detect_v0_l/labels_correlogram.jpg

person_detect_v0_l/model.onnx 167 MB ONNX

person_detect_v0_l/model.pt

person_detect_v0_l/model_type.json

person_detect_v0_l/results.csv

person_detect_v0_l/results.png

person_detect_v0_l/threshold.json

person_detect_v0_l_yv11/F1_curve.png

person_detect_v0_l_yv11/PR_curve.png

person_detect_v0_l_yv11/P_curve.png

person_detect_v0_l_yv11/R_curve.png

person_detect_v0_l_yv11/confusion_matrix.png

person_detect_v0_l_yv11/confusion_matrix_normalized.png

person_detect_v0_l_yv11/events.out.tfevents.1738898085.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.4177002.0

person_detect_v0_l_yv11/labels.jpg

person_detect_v0_l_yv11/labels.json

person_detect_v0_l_yv11/labels_correlogram.jpg

person_detect_v0_l_yv11/model.onnx 96.7 MB ONNX

person_detect_v0_l_yv11/model.pt

person_detect_v0_l_yv11/model_type.json

person_detect_v0_l_yv11/results.csv

person_detect_v0_l_yv11/results.png

person_detect_v0_l_yv11/threshold.json

person_detect_v0_m/F1_curve.png

person_detect_v0_m/PR_curve.png

person_detect_v0_m/P_curve.png

person_detect_v0_m/R_curve.png

person_detect_v0_m/confusion_matrix.png

person_detect_v0_m/confusion_matrix_normalized.png

person_detect_v0_m/events.out.tfevents.1738870487.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.3707067.0

person_detect_v0_m/labels.jpg

person_detect_v0_m/labels.json

person_detect_v0_m/labels_correlogram.jpg

person_detect_v0_m/model.onnx 98.7 MB ONNX

person_detect_v0_m/model.pt

person_detect_v0_m/model_type.json

person_detect_v0_m/results.csv

person_detect_v0_m/results.png

person_detect_v0_m/threshold.json

person_detect_v0_m_yv11/F1_curve.png

person_detect_v0_m_yv11/PR_curve.png

person_detect_v0_m_yv11/P_curve.png

person_detect_v0_m_yv11/R_curve.png

person_detect_v0_m_yv11/confusion_matrix.png

person_detect_v0_m_yv11/confusion_matrix_normalized.png

person_detect_v0_m_yv11/events.out.tfevents.1738891931.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.4072975.0

person_detect_v0_m_yv11/labels.jpg

person_detect_v0_m_yv11/labels.json

person_detect_v0_m_yv11/labels_correlogram.jpg

person_detect_v0_m_yv11/model.onnx 76.6 MB ONNX

person_detect_v0_m_yv11/model.pt

person_detect_v0_m_yv11/model_type.json

person_detect_v0_m_yv11/results.csv

person_detect_v0_m_yv11/results.png

person_detect_v0_m_yv11/threshold.json

person_detect_v0_n/F1_curve.png

person_detect_v0_n/PR_curve.png

person_detect_v0_n/P_curve.png

person_detect_v0_n/R_curve.png

person_detect_v0_n/confusion_matrix.png

person_detect_v0_n/confusion_matrix_normalized.png

person_detect_v0_n/events.out.tfevents.1738863182.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.3578579.0

person_detect_v0_n/labels.jpg

person_detect_v0_n/labels.json

person_detect_v0_n/labels_correlogram.jpg

person_detect_v0_n/model.onnx 11.6 MB ONNX

person_detect_v0_n/model.pt

person_detect_v0_n/model_type.json

person_detect_v0_n/results.csv

person_detect_v0_n/results.png

person_detect_v0_n/threshold.json

person_detect_v0_n_yv11/F1_curve.png

person_detect_v0_n_yv11/PR_curve.png

person_detect_v0_n_yv11/P_curve.png

person_detect_v0_n_yv11/R_curve.png

person_detect_v0_n_yv11/confusion_matrix.png

person_detect_v0_n_yv11/confusion_matrix_normalized.png

person_detect_v0_n_yv11/events.out.tfevents.1738884045.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.3934536.0

person_detect_v0_n_yv11/labels.jpg

person_detect_v0_n_yv11/labels.json

person_detect_v0_n_yv11/labels_correlogram.jpg

person_detect_v0_n_yv11/model.onnx 10.0 MB ONNX

person_detect_v0_n_yv11/model.pt

person_detect_v0_n_yv11/model_type.json

person_detect_v0_n_yv11/results.csv

person_detect_v0_n_yv11/results.png

person_detect_v0_n_yv11/threshold.json

person_detect_v0_s/F1_curve.png

person_detect_v0_s/PR_curve.png

person_detect_v0_s/P_curve.png

person_detect_v0_s/R_curve.png

person_detect_v0_s/confusion_matrix.png

person_detect_v0_s/confusion_matrix_normalized.png

person_detect_v0_s/events.out.tfevents.1738866493.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.3637442.0

person_detect_v0_s/labels.jpg

person_detect_v0_s/labels.json

person_detect_v0_s/labels_correlogram.jpg

person_detect_v0_s/model.onnx 42.5 MB ONNX

person_detect_v0_s/model.pt

person_detect_v0_s/model_type.json

person_detect_v0_s/results.csv

person_detect_v0_s/results.png

person_detect_v0_s/threshold.json

person_detect_v0_s_yv11/F1_curve.png

person_detect_v0_s_yv11/PR_curve.png

person_detect_v0_s_yv11/P_curve.png

person_detect_v0_s_yv11/R_curve.png

person_detect_v0_s_yv11/confusion_matrix.png

person_detect_v0_s_yv11/confusion_matrix_normalized.png

person_detect_v0_s_yv11/events.out.tfevents.1738887778.74aa4261331bbcab0987b94433af8ac622a654e7594a46e49f97167a.4000812.0

person_detect_v0_s_yv11/labels.jpg

person_detect_v0_s_yv11/labels.json

person_detect_v0_s_yv11/labels_correlogram.jpg

person_detect_v0_s_yv11/model.onnx 36.1 MB ONNX

person_detect_v0_s_yv11/model.pt

person_detect_v0_s_yv11/model_type.json

person_detect_v0_s_yv11/results.csv

person_detect_v0_s_yv11/results.png

person_detect_v0_s_yv11/threshold.json

Related models

More object-detection models

Browse all object-detection models