Menu
close
Menu
close
DX Model Zoo

DX Model Zoo

Image Classification

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
AlexNet ImageNet 224x224x3 715.98 61.10 BSD 3-Clause Top1 56.538 56.17 636 1,283.19
DenseNet121 ImageNet 224x224x3 3.18 8.04 BSD 3-Clause Top1 74.434 74.07 43 130.18
DenseNet161 ImageNet 224x224x3 8.43 28.86 BSD 3-Clause Top1 77.108 76.77 17 55.51
EfficientNetB2 ImageNet 288x288x3 1.60 9.08 BSD 3-Clause Top1 80.606 79.05 770 808.23
EfficientNetV2S ImageNet 384x384x3 9.47 21.38 BSD 3-Clause Top1 84.238 82.08 449 224.53
HarDNet39DS ImageNet 224x224x3 438.76 3.48 MIT Top1 72.08 71.03 1,796 2,317.19
MobileNetV1 ImageNet 224x224x3 578.88 4.22 No License Top1 69.492 68.81 3,920 2,869.47
MobileNetV2 ImageNet 224x224x3 319.95 3.49 BSD 3-Clause Top1 72.142 71.74 3,439 3,215.20
MobileNetV3Large ImageNet 224x224x3 232.57 5.47 BSD 3-Clause Top1 75.256 72.02 3,131 3,597.91
RegNetX400MF ImageNet 224x224x3 420.64 5.48 BSD 3-Clause Top1 74.884 74.44 1,381 2,082.77
RegNetX800MF ImageNet 224x224x3 810.70 7.24 BSD 3-Clause Top1 77.522 76.69 1,028 2,082.77
RegNetY200MF ImageNet 224x224x3 204.91 3.15 MIT Top1 70.36 69.59 2,453 1,283.58
RegNetY400MF ImageNet 224x224x3 411.81 4.33 BSD 3-Clause Top1 75.782 75.07 1,663 3,908.09
RegNetY800MF ImageNet 224x224x3 847.84 6.42 BSD 3-Clause Top1 78.828 78.33 1,180 1,258.76
RepVGGA1 ImageNet 320x320x3 4.83 12.79 MIT Top1 74.09 64.04 1,608 635.24
ResNet101 ImageNet 224x224x3 7.84 44.50 BSD 3-Clause Top1 81.898 80.21 641 310.90
ResNet18 ImageNet 224x224x3 1.82 11.68 BSD 3-Clause Top1 69.754 69.60 2,405 1,296.99
ResNet34 ImageNet 224x224x3 3.67 21.79 BSD 3-Clause Top1 73.294 73.27 1,380 666.98
ResNet50 ImageNet 224x224x3 4.12 25.53 BSD 3-Clause Top1 80.854 80.62 1,071 573.63
ResNeXt26_32x4d ImageNet 224x224x3 2.49 15.37 MIT Top1 75.852 75.70 863 637.43
ResNeXt50_32x4d ImageNet 224x224x3 4.27 24.99 BSD 3-Clause
MIT		 Top1 81.19 81.00 501 366.16
SqueezeNet1_0 ImageNet 224x224x3 832.77 1.25 BSD 3-Clause Top1 58.088 55.06 2,181 1,634.88
SqueezeNet1_1 ImageNet 224x224x3 357.48 1.24 BSD 3-Clause Top1 58.18 56.72 3,738 4,155.93
VGG11 ImageNet 224x224x3 7.63 132.86 BSD 3-Clause Top1 69.034 68.20 288 247.53
VGG11BN ImageNet 224x224x3 7.63 132.86 BSD 3-Clause Top1 70.372 70.17 287 249.04
VGG13 ImageNet 224x224x3 11.34 133.05 BSD 3-Clause Top1 69.934 69.71 268 176.89
VGG13BN ImageNet 224x224x3 11.34 133.05 BSD 3-Clause Top1 71.556 71.43 268 195.43
VGG19BN ImageNet 224x224x3 19.67 143.67 BSD 3-Clause Top1 74.238 74.07 236 135.27
WideResNet101_2 ImageNet 224x224x3 22.80 126.82 BSD 3-Clause Top1 82.52 82.31 271 116.59
WideResNet50_2 ImageNet 224x224x3 11.43 68.85 BSD 3-Clause Top1 81.61 81.43 495 225.30
EfficientNetLite0 ImageNet 224x224x3 404.52 4.63 Apache-2.0 Top1 67.28 66.10 3,306 2,706.37
EfficientNetLite1 ImageNet 240x240x3 629.42 5.39 Apache-2.0 Top1 70.95 71.18 2,591 1,854.13
EfficientNetLite2 ImageNet 260x260x3 896.92 6.06 Apache-2.0 Top1 71.14 70.98 1,655 1,273.57
EfficientNetLite4 ImageNet 380x380x3 4.08 12.95 Apache-2.0 Top1 77.83 77.42 531 347.43
HarDNet68 ImageNet 224x224x3 4.26 17.56 MIT Top1 76.474 76.30 579 421.12
EfficientNetLite3 ImageNet 300x300x3 1.67 8.16 Apache-2.0 Top1 75.31 75.20 1,066 761.34
OSNet0_25 ImageNet 224x224x3 135.39 713.14 No License Top1 58.336 50.49 1,630 2,906.48
OSNet0_5 ImageNet 224x224x3 436.04 1.14 No License Top1 69.446 62.28 1,526 1,905.12
RepVGGA2 ImageNet 320x320x3 10.45 25.50 MIT Top1 76.266 57.25 819 304.73
InceptionV1 ImageNet 224x224x3 1.52 6.62 Apache-2.0 Top1 70.07 69.99 2,277 1,268.03
ResNeXt50_32x4d ImageNet 224x224x3 4.27 24.99 BSD 3-Clause
MIT		 Top1 78.906 78.62 501 363.26

Object Detection

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
SSDMV1 VOC2007Detection 300x300x3 1.55 9.46 Apache-2.0 mAP50 67.59 67.638 1,550 1,303.16
SSDMV2Lite VOC2007Detection 300x300x3 700.57 3.36 Apache-2.0 mAP50 68.704 68.652 1,468 1,543.14
NanoDet COCO 416x416x3 5.66 6.74 Apache-2.0 mAP50 38.779 38.044 464 374.98
NanoDet_RepVGGA COCO 640x640x3 21.44 10.79 Apache-2.0 mAP50 44.24 43.982 200 113.58
DamoYOLOT COCO 640x640x3 9.13 8.50 Apache-2.0 mAP50 58.644 57.744 130 170.79
DamoYOLOS COCO 640x640x3 18.96 16.27 Apache-2.0 mAP50 63.274 62.286 115 101.35
DamoYOLOM COCO 640x640x3 31.84 28.19 Apache-2.0 mAP50 65.621 64.849 118 69.58
DamoYOLOL COCO 640x640x3 50.07 42.06 Apache-2.0 mAP50 67.602 65.171 93 47.26
YOLOv3 COCO 640x640x3 81.13 61.92 AGPL-3.0 mAP50 66.051 65.748 101 37.23
YOLOv5N COCO 640x640x3 2.71 1.87 AGPL-3.0 mAP50 46.13 45.099 102 347.64
YOLOv5S COCO 640x640x3 9.10 7.23 AGPL-3.0 mAP50 57.081 56.777 102 183.05
YOLOv5M COCO 640x640x3 26.07 21.17 AGPL-3.0 mAP50 64.143 63.933 102 77.40
YOLOv5L COCO 640x640x3 57.10 46.53 AGPL-3.0 mAP50 67.167 67.054 101 43.47
YOLOXTiny COCO 416x416x3 3.55 5.05 Apache-2.0 mAP50 50.449 50.244 380 453.52
YOLOXS COCO 640x640x3 14.41 8.96 Apache-2.0 mAP50 59.309 59.143 158 140.65
YOLOXSLeaky COCO 640x640x3 13.49 8.96 Apache-2.0 mAP50 57.226 57.157 158 136.97
YOLOXSWideLeaky COCO 640x640x3 29.89 20.12 Apache-2.0 mAP50 62.313 62.146 154 74.06
YOLOXLLeaky COCO 640x640x3 78.01 54.17 Apache-2.0 mAP50 67.69 67.578 108 39.76
YOLOv6N COCO 640x640x3 5.64 4.32 Apache-2.0 mAP50 52.975 50.608 161 293.83
YOLOv7Tiny COCO 640x640x3 7.01 6.24 GPL-3.0 mAP50 55.415 55.032 102 198.34
YOLOv7 COCO 640x640x3 55.28 36.92 GPL-3.0 mAP50 69.643 69.645 101 46.19
YOLOv7E6 COCO 1280x1280x3 269.21 97.20 GPL-3.0 mAP50 72.969 73.297 21 9.33
YOLOv8N COCO 640x640x3 4.89 3.18 AGPL-3.0 mAP50 52.976 51.706 135 262.60
YOLOv8S COCO 640x640x3 8.43 28.86 AGPL-3.0 mAP50 61.896 60.569 134 126.49
YOLOv8M COCO 640x640x3 41.13 25.91 AGPL-3.0 mAP50 67.274 65.788 123 57.46
YOLOv8L COCO 640x640x3 85.13 43.69 AGPL-3.0 mAP50 69.78 68.617 82 34.32
YOLOv8X COCO 640x640x3 132.08 68.23 AGPL-3.0 mAP50 70.813 69.7 47 18.98
YOLOv9T COCO 640x640x3 4.56 2.03 GPL-3.0 mAP50 52.298 49.858 135 247.96
YOLOv9S COCO 640x640x3 14.50 7.13 GPL-3.0 mAP50 62.119 59.926 135 124.96
YOLOv9C COCO 640x640x3 53.92 25.31 GPL-3.0 mAP50 69.084 58.851 82 43.84
YOLOv10N COCO 640x640x3 4.02 2.34 Apache-2.0 mAP50 53.519 50.416 134 270.45
YOLOv10S COCO 640x640x3 12.04 7.29 Apache-2.0 mAP50 62.9 58.101 124 123.37
YOLOv10M COCO 640x640x3 31.74 15.40 Apache-2.0 mAP50 67.921 53.17 93 61.22
YOLOv10B COCO 640x640x3 48.87 19.11 Apache-2.0 mAP50 69.283 66.884 84 46.79
YOLOv10L COCO 640x640x3 63.65 24.41 Apache-2.0 mAP50 69.806 56.167 72 37.85
YOLOv10X COCO 640x640x3 85.05 29.52 Apache-2.0 mAP50 70.988 70.046 45 23.53
YOLOv11N COCO 640x640x3 3.88 2.66 AGPL-3.0 mAP50 54.55 53.152 134 282.31
YOLOv11S COCO 640x640x3 11.90 9.49 AGPL-3.0 mAP50 62.887 60.555 132 143.75
YOLOv11M COCO 640x640x3 36.40 20.13 AGPL-3.0 mAP50 67.563 67.329 100 60.65
YOLOv11L COCO 640x640x3 46.61 25.38 AGPL-3.0 mAP50 69.073 68.325 70 45.30
YOLOv11X COCO 640x640x3 102.16 56.96 AGPL-3.0 mAP50 70.526 70.079 39 20.99
YOLO26N COCO 640x640x3 3.35 2.45 AGPL-3.0 mAP50 55.361 54.109 148 296.93
YOLO26S COCO 640x640x3 11.63 9.54 AGPL-3.0 mAP50 63.989 63.554 110 134.90
YOLO26M COCO 640x640x3 36.57 20.45 AGPL-3.0 mAP50 68.896 68.342 81 56.95
YOLO26L COCO 640x640x3 46.42 24.85 AGPL-3.0 mAP50 70.652 66.395 61 43.00
YOLO26X COCO 640x640x3 101.72 55.77 AGPL-3.0 mAP50 72.796 72.619 34 20.47

Face Detection

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
YOLOv5s_Face WiderFace 640x640x3 8.53 7.06 MIT AP(Easy)
AP(Med)
AP(Hard)		 94.57
92.94
83.698		 94.643
92.934
83.7		 352 243.72
YOLOv5m_Face WiderFace 640x640x3 25.84 21.04 MIT AP(Easy)
AP(Med)
AP(Hard)		 95.507
94.027
85.649		 95.482
94.023
85.602		 204 91.74
YOLOv7s_Face WiderFace 640x640x3 9.35 4.27 MIT AP(Easy)
AP(Med)
AP(Hard)		 94.86
93.3
85.304		 94.85
93.263
85.222		 258 189.44
YOLOv7_Face WiderFace 640x640x3 54.63 36.56 MIT AP(Easy)
AP(Med)
AP(Hard)		 96.925
95.689
88.337		 96.927
95.687
88.257		 121 52.75
YOLOv7_W6_Face WiderFace 960x960x3 100.22 69.90 MIT AP(Easy)
AP(Med)
AP(Hard)		 96.41
95.091
88.61		 96.421
95.074
88.575		 68 28.22
YOLOv7_W6_TTA_Face WiderFace 1280x1280x3 178.16 69.90 MIT AP(Easy)
AP(Med)
AP(Hard)		 95.89
94.929
89.952		 96.062
95.122
90.401		 37 15.60
SCRFD10G WiderFace 640x640x3 13.41 4.23 Apache-2.0 AP(Easy)
AP(Med)
AP(Hard)		 95.469
94.021
82.674		 95.375
94.001
82.648		 267 142.89
SCRFD2_5G WiderFace 640x640x3 3.46 817.96 Apache-2.0 AP(Easy)
AP(Med)
AP(Hard)		 93.888
92.042
77.0		 93.737
92.036
76.935		 316 349.32
SCRFD500M WiderFace 640x640x3 764.58 626.34 Apache-2.0 AP(Easy)
AP(Med)
AP(Hard)		 91.08
88.467
69.375		 90.675
88.179
68.799		 390 828.95

Image De-noising

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
DnCNN_15 BSD68 512x512x1 145.79 555.14 MIT PSNR
SSIM		 31.709
0.89		 31.481
0.887		 35 15.63
DnCNN_25 BSD68 512x512x1 145.79 555.14 MIT PSNR
SSIM		 29.192
0.828		 28.833
0.82		 35 15.69
DnCNN_50 BSD68 512x512x1 145.79 555.14 MIT PSNR
SSIM		 26.188
0.718		 25.084
0.679		 35 15.48

Depth Estimation

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
FastDepth NYU 224x224x3 547.19 1.38 MIT RMSE 0.604 0.653 271 1,042.81

Pose Estimation

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
YOLOV8S_Pose COCOPose 640x640x3 16.05 11.66 AGPL-3.0 mAP50 83.327 83.089 161 123.89
YOLOV8M_Pose COCOPose 640x640x3 42.18 26.49 AGPL-3.0 mAP50 85.541 85.309 119 55.91

Semantic Segmentation

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
BiSeNetV1 CitySpace 1024x2048x3 118.98 13.27 MIT mIoU 75.367 74.983 19 15.05
BiSeNetV2 CitySpace 1024x2048x3 99.14 3.35 MIT mIoU 74.951 74.541 28 18.46
DeepLabV3PlusMobilenet VOCSegmentation 512x512x3 26.62 5.80 MIT mIoU 70.806 67.839 244 93.00

Instance Segmentation

Class Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
YoloV5N_Seg COCO 640x640x3 4.11 1.99 AGPL-3.0 mAP50 40.67 40.326 54 203.00
YoloV5S_Seg COCO 640x640x3 14.23 7.61 AGPL-3.0 mAP50 52.802 52.414 54 108.33
YoloV5M_Seg COCO 640x640x3 37.29 21.97 AGPL-3.0 mAP50 58.573 58.497 54 50.30
YoloV5L_Seg COCO 640x640x3 76.77 47.89 AGPL-3.0 mAP50 62.908 62.76 54 29.58
YoloV8N_Seg COCO 640x640x3 6.95 3.40 AGPL-3.0 mAP50 48.799 48.588 80 179.37
YoloV8S_Seg COCO 640x640x3 22.43 11.84 AGPL-3.0 mAP50 57.489 57.134 78 82.36
YoloV8M_Seg COCO 640x640x3 57.03 27.29 AGPL-3.0 mAP50 62.488 62.066 74 37.87

Generated on 2026-01-26 06:19:20

DX Model Zoo - Powered by DeepX DevOps

Welcome to the DEEPX Developer Page.

I will provide a brief introduction to DXNN (DEEPX SDK) and a guide on how to install it.

Introduction to DXNN

DXNN is the SDK for DEEPX NPUs and consists of the following components:

Quick Start Guide for DX-Allsuite

DX-Allsuite is a comprehensive package that ensures version compatibility across all DXNN components, allowing for a seamless, all-in-one installation.

You can download DX-Allsuite from our Developer Page or GitHub(https://github.com/DEEPX-AI/dx-all-suite).

DEEPX HQ
5F, 20, Pangyoyeok-ro 241beon-gil, Bundang-gu,
Seongnam-si, Gyeonggi-do, Republic of Korea
US Office
3003 North First Street #316, San Jose, CA 95135
Taiwan Office
Rm. 950, 9F., No. 208, Sec. 3, Nanjing E. Rd.,
Zhongshan Dist., Taipei City 104, Taiwan (R.O.C.)
Contact US
E-mail: tech_support@deepx.ai
Copyrightⓒ 2025 DEEPX Co., Ltd. All Rights Reserved.