DX Model Zoo

Image Classification

Task Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
Image Classification AlexNet-1 ImageNet 224x224x3 0.72 61.1 BSD 3-Clause Top1 56.54 56.34 680 1,425.54 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification DenseNet121-1 ImageNet 224x224x3 3.19 8.04 BSD 3-Clause Top1 74.43 73.53 263 336.52 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification DenseNet161-1 ImageNet 224x224x3 8.43 28.86 BSD 3-Clause Top1 77.11 76.69 74 119.37 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification EfficientNetB2-1 ImageNet 288x288x3 1.6 9.08 BSD 3-Clause Top1 80.61 79.24 752 774.66 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification EfficientNetV2S-1 ImageNet 384X384x3 9.47 21.38 BSD 3-Clause Top1 84.24 79.41 437 192.92 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification HarDNet39DS-1 ImageNet 224x224x3 4.26 17.56 MIT Top1 72.08 71.4 2,788 2,519.00 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification MobileNetV1-1 ImageNet 224x224x3 0.58 4.22 Apache-2.0 Top1 69.49 68.77 5,148 2,743.36 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification MobileNetV2-1 ImageNet 224x224x3 0.32 3.49 BSD 3-Clause Top1 72.14 71.82 3,667 3,201.44 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification MobileNetV3L-1 ImageNet 224x224x3 0.23 5.47 BSD 3-Clause Top1 75.25 71.35 2,702 3,199.59 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification RegNetX400MF-1 ImageNet 224x224x3 0.42 5.48 BSD 3-Clause Top1 74.88 74.44 1,492 2,259.62 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification RegNetX800MF-1 ImageNet 224x224x3 0.81 7.24 BSD 3-Clause Top1 77.52 77.19 1,099 1,369.13 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification RegNetY200MF-1 ImageNet 224x224x3 0.21 3.15 MIT Top1 70.36 70.12 2,592 4,298.96 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification RegNetY400MF-1 ImageNet 224x224x3 0.41 4.33 BSD 3-Clause Top1 75.78 75.41 1,853 2,286.38 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification RegNetY800MF-1 ImageNet 224x224x3 0.85 6.42 BSD 3-Clause Top1 78.83 78.53 1,218 1,334.79 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification RepVGGA1-1 ImageNet 320X320x3 4.83 12.79 MIT Top1 75.28 9.72 1,631 577.49 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification ResNet101-1 ImageNet 224x224x3 7.8 44.55 BSD 3-Clause Top1 81.9 81.63 682 269.41 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification ResNet18-1 ImageNet 224x224x3 1.82 11.69 BSD 3-Clause Top1 69.75 69.66 2,746 1,095.21 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification ResNet34-1 ImageNet 224x224x3 3.67 21.79 BSD 3-Clause Top1 73.3 73.22 1,369 513.35 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification ResNet50-1 ImageNet 224x224x3 4.27 25.0 BSD 3-Clause Top1 80.85 80.67 1,056 454.56 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification ResNeXt26_32x4d-1 ImageNet 224x224x3 2.49 15.37 MIT Top1 75.85 75.8 856 596.68 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification ResNeXt50_32x4d-1 ImageNet 224x224x3 4.27 25.0 BSD 3-Clause Top1 81.19 81.04 497 343.54 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification SqueezeNet1_0-1 ImageNet 224x224x3 0.83 1.25 BSD 3-Clause Top1 58.09 57.88 2,127 1,650.05 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification SqueezeNet1_1-1 ImageNet 224x224x3 0.36 1.24 BSD 3-Clause Top1 58.18 58.09 3,239 4,080.14 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification VGG11-1 ImageNet 224x224x3 7.63 132.86 BSD 3-Clause Top1 69.03 68.86 305 254.78 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification VGG11BN-1 ImageNet 224x224x3 7.63 132.86 BSD 3-Clause Top1 70.37 70.16 306 249.73 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification VGG13-1 ImageNet 224x224x3 11.34 133.05 BSD 3-Clause Top1 69.93 69.77 283 168.23 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification VGG13BN-1 ImageNet 224x224x3 11.34 133.05 BSD 3-Clause Top1 71.55 71.52 282 187.92 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification VGG19BN-1 ImageNet 224x224x3 19.69 143.67 BSD 3-Clause Top1 74.24 74.11 237 128.59 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification WideResNet101-2 ImageNet 224x224x3 22.81 126.82 BSD 3-Clause Top1 82.52 82.32 210 80.19 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image Classification WideResNet50-2 ImageNet 224x224x3 11.43 68.85 BSD 3-Clause Top1 81.61 81.45 382 186.07 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n

Object Detection

Task Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
Object Detection SSDMV1-1 VOC2007Detection 300X300x3 1.55 9.48 MIT mAP50 67.59 67.674 1,892 1,263.31 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection SSDMV2Lite-1 VOC2007Detection 300x300x3 0.7 3.38 MIT mAP50 68.704 68.647 1,631 1,561.85 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV3-1 COCO 640x640x3 81.13 62.02 AGPL-3.0 mAP50 46.654 46.437 55 20.75 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV5L-1 COCO 640x640x3 57.1 46.64 AGPL-3.0 mAP50 48.74 48.367 79 35.31 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV5M-1 COCO 640x640x3 26.07 21.27 AGPL-3.0 mAP50 45.082 44.717 155 71.34 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV5N-1 COCO 640x640x3 2.71 1.97 AGPL-3.0 mAP50 28.081 27.616 259 503.86 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV5S-1 COCO 640x640x3 9.1 7.33 AGPL-3.0 mAP50 37.451 37.134 260 206.70 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV7-2 COCO 640x640x3 55.28 36.92 GPL-3.0 mAP50 50.862 50.677 90 31.26 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV7E6-1 COCO 1280x1280x3 269.21 97.27 GPL-3.0 mAP50 55.58 55.398 15 6.32 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV7Tiny-1 COCO 640x640x3 7.01 6.24 GPL-3.0 mAP50 37.289 37.061 254 223.28 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOV8L-1 COCO 640x640x3 85.13 43.69 AGPL-3.0 mAP50 52.572 51.946 51 20.74 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOv9-C-2 COCO 640x640x3 53.92 25.31 AGPL-3.0 mAP50 52.856 52.28 64 34.08 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOv9-S-2 COCO 640x640x3 14.51 7.13 AGPL-3.0 mAP50 46.683 44.576 104 106.88 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOv9-T-2 COCO 640x640x3 4.56 2.03 AGPL-3.0 mAP50 38.268 36.249 110 213.23 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Object Detection YOLOXS-1 COCO 640x640x3 14.41 8.96 Apache-2.0 mAP50 40.29 40.049 268 126.84 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n

Segmentation

Task Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
Segmentation BiSeNetV1-1 CitySpace 1280x2048x3 118.98 13.27 MIT mIoU 75.367 75.049 19 15.17 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Segmentation BiSeNetV2-1 CitySpace 1280x2048x3 99.14 3.35 MIT mIoU 74.925 74.109 31 19.69 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Segmentation DeepLabV3PlusMobilenet-1 VOCSegmentation 512x512x3 26.62 5.8 MIT mIoU 68.473 68.109 227 72.54 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n

Face ID

Task Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
Face ID YOLOV5M_Face-1 WiderFace 640x640x3 25.84 22.0 GPL-3.0 AP(Easy)
AP(Med)
AP(Hard)		 95.507
94.027
85.649		 95.44
93.95
85.664		 144 65.74 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Face ID YOLOV5S_Face-1 WiderFace 640x640x3 8.53 8.07 GPL-3.0 AP(Easy)
AP(Med)
AP(Hard)		 94.57
92.94
83.698		 94.635
93.003
83.828		 351 219.79 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Face ID YOLOV7_Face-1 WiderFace 640x640x3 54.63 38.55 GPL-3.0 AP(Easy)
AP(Med)
AP(Hard)		 96.925
95.689
88.337		 96.965
95.724
88.29		 85 29.03 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Face ID YOLOV7_W6_Face-1 WiderFace 960x960x3 100.21 74.44 GPL-3.0 AP(Easy)
AP(Med)
AP(Hard)		 96.41
95.091
88.61		 96.442
95.128
88.677		 43 19.31 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Face ID YOLOV7_W6_TTA_Face-1 WiderFace 1280x1280x3 178.16 77.96 GPL-3.0 AP(Easy)
AP(Med)
AP(Hard)		 95.89
94.929
89.952		 95.994
95.043
90.254		 24 9.49 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Face ID YOLOV7s_Face-1 WiderFace 640x640x3 9.35 6.26 GPL-3.0 AP(Easy)
AP(Med)
AP(Hard)		 94.86
93.3
85.304		 94.885
93.252
85.234		 274 186.95 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n

Image De-noising

Task Name Dataset Input Resolution Operations Parameters License Metric Raw Accuracy NPU Accuracy FPS FPS/Watt Source Compiled onnx json
Image De-noising DnCNN-2 BSD68 512x512x1 145.8 0.56 Not Specified PSNR
SSIM		 31.709
0.8905		 31.709
0.8905		 52 13.37 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image De-noising DnCNN-3 BSD68 512x512x1 145.8 0.56 Not Specified PSNR
SSIM		 29.1919
0.8276		 29.1919
0.8276		 52 13.68 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Image De-noising DnCNN-4 BSD68 512x512x1 145.8 0.56 Not Specified PSNR
SSIM		 26.1882
0.7184		 26.1882
0.7184		 38 11.31 \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n