11.3.1. MobileNetv1
INPUT SIZE: 1x224x224x3
C(GOPs): 1.14
FPS: 3793.70
ITC(ms): 0.901
TCPP(ms): 0.061
RV(mb): 3.89
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7061(FLOAT)/0.7026(INT8)
11.3.2. MobileNetv2
INPUT SIZE: 1x224x224x3
C(GOPs): 0.63
FPS: 4197.62
ITC(ms): 0.767
TCPP(ms): 0.090
RV(mb): 2.94
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7265(FLOAT)/0.7153(INT8)
11.3.3. GoogleNet
INPUT SIZE: 1x224x224x3
C(GOPs): 3.00
FPS: 2312.97
ITC(ms): 1.210
TCPP(ms): 0.062
RV(mb): 6.39
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7001(FLOAT)/0.6989(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/GoogleNet
11.3.4. Resnet18
INPUT SIZE: 1x224x224x3
C(GOPs): 3.65
FPS: 1560.14
ITC(ms): 1.650
TCPP(ms): 0.061
RV(mb): 10.53
WV(mb): 0.09
Dataset: ImageNet
ACCURACY: Top1: 0.6837(FLOAT)/0.6829(INT8)
LINKS: https://github.com/HolmesShuan/ResNet-18-Caffemodel-on-ImageNet
11.3.5. EfficientNet_Lite0
INPUT SIZE: 1x224x224x3
C(GOPs): 0.77
FPS: 2792.34
ITC(ms): 1.115
TCPP(ms): 0.062
RV(mb): 5.08
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7490(FLOAT)/0.7469(INT8)
LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite
11.3.6. EfficientNet_Lite1
INPUT SIZE: 1x240x240x3
C(GOPs): 1.20
FPS: 2404.13
ITC(ms): 1.764
TCPP(ms): 0.062
RV(mb): 5.85
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7648(FLOAT)/0.7624(INT8)
LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite
11.3.7. EfficientNet_Lite2
INPUT SIZE: 1x260x260x3
C(GOPs): 1.72
FPS: 2135.66
ITC(ms): 1.329
TCPP(ms): 0.061
RV(mb): 6.64
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7738(FLOAT)/0.7715(INT8)
LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite
11.3.8. EfficientNet_Lite3
INPUT SIZE: 1x280x280x3
C(GOPs): 2.77
FPS: 1603.91
ITC(ms): 1.630
TCPP(ms): 0.061
RV(mb): 9.00
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7922(FLOAT)/0.7902(INT8)
LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite
11.3.9. EfficientNet_Lite4
INPUT SIZE: 1x300x300x3
C(GOPs): 5.11
FPS: 1067.30
ITC(ms): 2.258
TCPP(ms): 0.062
RV(mb): 13.91
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.8069(FLOAT)/0.8058(INT8)
LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite
11.3.10. Vargconvnet
INPUT SIZE: 1x224x224x3
C(GOPs): 9.06
FPS: 1573.19
ITC(ms): 1.627
TCPP(ms): 0.062
RV(mb): 9.07
WV(mb): 0.05
Dataset: ImageNet
ACCURACY: Top1: 0.7790(FLOAT)/0.7785(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/VargConvNet
11.3.11. Efficientnasnet_m
INPUT SIZE: 1x300x300x3
C(GOPs): 4.53
FPS: 1141.20
ITC(ms): 2.110
TCPP(ms): 0.062
RV(mb): 13.20
WV(mb): 0.05
Dataset: ImageNet
ACCURACY: Top1: 0.7973(FLOAT)/0.7916(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/EfficientnasNet
11.3.12. Efficientnasnet_s
INPUT SIZE: 1x280x280x3
C(GOPs): 1.44
FPS: 2706.59
ITC(ms): 1.106
TCPP(ms): 0.062
RV(mb): 5.17
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7578(FLOAT)/0.7518(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/EfficientnasNet
11.3.13. YOLOv2_Darknet19
INPUT SIZE: 1x608x608x3
C(GOPs): 62.94
FPS: 280.60
ITC(ms): 7.264
TCPP(ms): 1.680
RV(mb): 47.35
WV(mb): 2.43
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.2760(FLOAT)/0.2730(INT8)
11.3.14. YOLOv3_Darknet53
INPUT SIZE: 1x416x416x3
C(GOPs): 65.87
FPS: 213.63
ITC(ms): 9.521
TCPP(ms): 9.937
RV(mb): 56.84
WV(mb): 3.63
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.3330(FLOAT)/0.3350(INT8)
11.3.15. YOLOv5x_v2.0
INPUT SIZE: 1x672x672x3
C(GOPs): 243.86
FPS: 78.78
ITC(ms): 24.940
TCPP(ms): 30.784
RV(mb): 123.69
WV(mb): 49.35
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.4800(FLOAT)/0.4660(INT8)
LINKS: https://github.com/ultralytics/yolov5/releases/tag/v2.0
11.3.16. Ssd_mobilenetv1
INPUT SIZE: 1x300x300x3
C(GOPs): 2.30
FPS: 2588.11
ITC(ms): 1.102
TCPP(ms): 1.101
RV(mb): 5.82
WV(mb): 0.20
Dataset: VOC
ACCURACY: mAP: 0.7342(FLOAT)/0.7275(INT8)
11.3.17. Centernet_resnet101
INPUT SIZE: 1x512x512x3
C(GOPs): 90.54
FPS: 250.20
ITC(ms): 8.292
TCPP(ms): 4.667
RV(mb): 35.98
WV(mb): 6.67
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.3420(FLOAT)/0.3350(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Centernet
11.3.18. YOLOv3_VargDarknet
INPUT SIZE: 1x416x416x3
C(GOPs): 42.82
FPS: 302.11
ITC(ms): 6.866
TCPP(ms): 9.921
RV(mb): 42.39
WV(mb): 5.22
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.3350(FLOAT)/0.3270(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Yolov3_VargDarknet
11.3.19. Deeplabv3plus_efficientnetb0
INPUT SIZE: 1x1024x2048x3
C(GOPs): 30.78
FPS: 203.40
ITC(ms): 10.023
TCPP(ms): 0.790
RV(mb): 12.55
WV(mb): 7.72
Dataset: Cityscapes
ACCURACY: mIoU: 0.7630(FLOAT)/0.7568(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus
11.3.20. Fastscnn_efficientnetb0
INPUT SIZE: 1x1024x2048x3
C(GOPs): 12.49
FPS: 294.50
ITC(ms): 7.148
TCPP(ms): 0.785
RV(mb): 5.59
WV(mb): 2.79
Dataset: Cityscapes
ACCURACY: mIoU: 0.6997(FLOAT)/0.6928(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/FastSCNN
11.3.21. Deeplabv3plus_efficientnetm1
INPUT SIZE: 1x1024x2048x3
C(GOPs): 77.05
FPS: 117.35
ITC(ms): 17.009
TCPP(ms): 0.771
RV(mb): 38.42
WV(mb): 24.44
Dataset: Cityscapes
ACCURACY: mIoU: 0.7794(FLOAT)/0.7740(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus
11.3.22. Deeplabv3plus_efficientnetm2
INPUT SIZE: 1x1024x2048x3
C(GOPs): 124.16
FPS: 89.91
ITC(ms): 22.420
TCPP(ms): 0.768
RV(mb): 46.63
WV(mb): 34.28
Dataset: Cityscapes
ACCURACY: mIoU: 0.7882(FLOAT)/0.7856(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus
11.3.23. Resnet50
INPUT SIZE: 1x224x224x3
C(GOPs): 7.72
FPS: 683.52
ITC(ms): 3.144
TCPP(ms): 0.090
RV(mb): 24.03
WV(mb): 0.52
Dataset: ImageNet
ACCURACY: Top1: 0.7737(FLOAT)/0.7674(INT8)
11.3.24. VargNetV2
INPUT SIZE: 1x224x224x3
C(GOPs): 0.72
FPS: 3530.60
ITC(ms): 0.863
TCPP(ms): 0.090
RV(mb): 3.68
WV(mb): 0.03
Dataset: ImageNet
ACCURACY: Top1: 0.7394(FLOAT)/0.7321(INT8)
11.3.25. Swint
INPUT SIZE: 1x224x224x3
C(GOPs): 8.98
FPS: 138.90
ITC(ms): 14.718
TCPP(ms): 0.088
RV(mb): 40.95
WV(mb): 1.31
Dataset: ImageNet
ACCURACY: Top1: 0.8024(FLOAT)/0.7947(INT8)
11.3.26. MixVarGENet
INPUT SIZE: 1x224x224x3
C(GOPs): 2.07
FPS: 5809.93
ITC(ms): 0.646
TCPP(ms): 0.089
RV(mb): 2.26
WV(mb): 0.02
Dataset: ImageNet
ACCURACY: Top1: 0.7133(FLOAT)/0.7066(INT8)
11.3.27. Fcos_efficientnetb0
INPUT SIZE: 1x512x512x3
C(GOPs): 5.02
FPS: 1757.02
ITC(ms): 1.466
TCPP(ms): 0.247
RV(mb): 4.73
WV(mb): 0.30
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.3626(FLOAT)/0.3562(INT8)
11.3.28. Fcos_efficientnetb2
INPUT SIZE: 1x768x768x3
C(GOPs): 22.08
FPS: 450.32
ITC(ms): 4.837
TCPP(ms): 6.736
RV(mb): 16.32
WV(mb): 9.85
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.4470(FLOAT)/0.4470(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/PreQQAT
11.3.29. Fcos_efficientnetb3
INPUT SIZE: 1x896x896x3
C(GOPs): 41.45
FPS: 269.01
ITC(ms): 7.766
TCPP(ms): 9.117
RV(mb): 24.57
WV(mb): 17.56
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.4720(FLOAT)/0.4740(INT8)
LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/PreQQAT
11.3.30. Pointpillars_kitti_car
INPUT SIZE: 1x1x150000x4
C(GOPs): 66.82
FPS: 117.31
ITC(ms): 32.183
TCPP(ms): 2.566
RV(mb): 43.30
WV(mb): 24.47
Dataset: Kitti3d
ACCURACY: APDet= 0.7731(FLOAT)/0.7676(INT8)
11.3.31. RetinaNet_vargnetv2_fpn
INPUT SIZE: 1x1024x1024x3
C(GOPs): 301.27
FPS: 80.92
ITC(ms): 24.689
TCPP(ms): 6.540
RV(mb): 74.94
WV(mb): 37.52
Dataset: COCO
ACCURACY: [IoU=0.50:0.95]= 0.3151(FLOAT)/0.3129(INT8)
11.3.32. Yolov3_mobilenetv1
INPUT SIZE: 1x416x416x3
C(GOPs): 20.58
FPS: 491.66
ITC(ms): 4.334
TCPP(ms): 1.662
RV(mb): 25.87
WV(mb): 1.53
Dataset: VOC
ACCURACY: mAP: 0.7657(FLOAT)/0.7581(INT8)
11.3.33. Ganet_mixvargenet
INPUT SIZE: 1x320x800x3
C(GOPs): 10.74
FPS: 2424.77
ITC(ms): 1.155
TCPP(ms): 0.953
RV(mb): 1.36
WV(mb): 0.21
Dataset: CuLane
ACCURACY: F1Score: 0.7949(FLOAT)/0.7872(INT8)
11.3.34. DETR_resnet50
INPUT SIZE: 1x800x1333x3
C(GOPs): 202.99
FPS: 47.40
ITC(ms): 41.375
TCPP(ms): 1.666
RV(mb): 174.56
WV(mb): 100.56
Dataset: MS COCO
ACCURACY: [IoU=0.50:0.95]= 0.3570(FLOAT)/0.3134(INT8)
11.3.35. DETR_efficientnetb3
INPUT SIZE: 1x800x1333x3
C(GOPs): 67.31
FPS: 62.28
ITC(ms): 32.334
TCPP(ms): 1.669
RV(mb): 119.12
WV(mb): 63.56
Dataset: MS COCO
ACCURACY: [IoU=0.50:0.95]= 0.3721(FLOAT)/0.3597(INT8)
11.3.36. FCOS3D_efficientnetb0
INPUT SIZE: 1x512x896x3
C(GOPs): 19.94
FPS: 604.57
ITC(ms): 3.994
TCPP(ms): 8.708
RV(mb): 11.55
WV(mb): 5.10
Dataset: nuscenes
ACCURACY: NDS: 0.3062(FLOAT)/0.3019(INT8)
11.3.37. Centerpoint_pointpillar
INPUT SIZE: 300000x5
C(GOPs): 127.73
FPS: 100.64
ITC(ms): 24.618
TCPP(ms): 52.566
RV(mb): 39.37
WV(mb): 19.04
Dataset: nuscenes
ACCURACY: NDS: 0.5832(FLOAT)/0.5814(INT8)
11.3.38. Keypoint_efficientnetb0
INPUT SIZE: 1x128x128x3
C(GOPs): 0.45
FPS: 3221.86
ITC(ms): 0.914
TCPP(ms): 0.361
RV(mb): 4.41
WV(mb): 0.04
Dataset: carfusion
ACCURACY: PCK(alpha=0.1): 0.9433(FLOAT)/0.9431(INT8)
11.3.39. Unet_mobilenetv1
INPUT SIZE: 1x1024x2048x3
C(GOPs): 7.36
FPS: 1050.12
ITC(ms): 2.129
TCPP(ms): 0.589
RV(mb): 6.96
WV(mb): 2.88
Dataset: Cityscapes
ACCURACY: mIoU: 0.6802(FLOAT)/0.6753(INT8)
11.3.40. Pwcnet_pwcnetneck
INPUT SIZE: 1x384x512x6
C(GOPs): 81.71
FPS: 161.49
ITC(ms): 12.671
TCPP(ms): 0.304
RV(mb): 27.65
WV(mb): 15.32
Dataset: flyingchairs
ACCURACY: EndPointError: 1.4117(FLOAT)/1.4075(INT8)
11.3.41. Motr_efficientnetb3
INPUT SIZE: image: 1x800x1422x3 track_query: 1x2x128x156 ref_points: 1x2x128x4 mask_query: 1x1x256x1
C(GOPs): 64.43
FPS: 72.72
ITC(ms): 26.535
TCPP(ms): 22.895
RV(mb): 73.95
WV(mb): 28.09
Dataset: Mot17
ACCURACY: MOTA: 0.5802(FLOAT)/0.5776(INT8)
11.3.42. Bev_lss_efficientnetb0_multitask
INPUT SIZE: image: 6x256x704x3 points(0&1): 10x128x128x2
C(GOPs): 2.41
FPS: 278.20
ITC(ms): 7.925
TCPP(ms): 17.903
RV(mb): 2.56
WV(mb): 1.99
Dataset: nuscenes
ACCURACY: NDS: 0.3006(FLOAT)/0.3000(INT8) MeanIOU: 0.5180(FLOAT)/0.5148(INT8)
11.3.43. Bev_gkt_mixvargenet_multitask
INPUT SIZE: image: 6x512x960x3 points(0-8): 6x64x64x2
C(GOPs): 34.49
FPS: 85.83
ITC(ms): 23.624
TCPP(ms): 18.009
RV(mb): 10.98
WV(mb): 6.89
Dataset: nuscenes
ACCURACY: NDS: 0.2809(FLOAT)/0.2791(INT8) MeanIOU: 0.4851(FLOAT)/0.4836(INT8)
11.3.44. Bev_ipm_efficientnetb0_multitask
INPUT SIZE: image: 6x512x960x3 points: 6x128x128x2
C(GOPs): 8.83
FPS: 209.61
ITC(ms): 9.739
TCPP(ms): 17.980
RV(mb): 5.14
WV(mb): 3.63
Dataset: nuscenes
ACCURACY: NDS: 0.3053(FLOAT)/0.3041(INT8) MeanIOU: 0.5146(FLOAT)/0.5099(INT8)
11.3.45. Bev_ipm_4d_efficientnetb0_multitask
INPUT SIZE: image: 6x512x960x3 points: 6x128x128x2 prev_feat: 1x128x128x64 prev_point: 1x128x128x2
C(GOPs): 8.93
FPS: 188.10
ITC(ms): 10.565
TCPP(ms): 18.169
RV(mb): 5.70
WV(mb): 3.99
Dataset: nuscenes
ACCURACY: NDS: 0.3724(FLOAT)/0.3725(INT8) MeanIOU: 0.5290(FLOAT)/0.5388(INT8)
11.3.46. Detr3d_efficientnetb3_nuscenes
INPUT SIZE: coords(0-3): 6x4x256x2 image: 6x512x1408x3 masks: 1x4x256x24
C(GOPs): 37.55
FPS: 27.04
ITC(ms): 69.306
TCPP(ms): 2.410
RV(mb): 57.77
WV(mb): 40.23
Dataset: nuscenes
ACCURACY: NDS: 0.3304(FLOAT)/0.3283(INT8)
11.3.47. Petr_efficientnetb3_nuscenes
INPUT SIZE: image: 6x512x1408x3 pos_embed: 1x96x44x256
C(GOPs): 36.24
FPS: 8.41
ITC(ms): 226.049
TCPP(ms): 2.418
RV(mb): 301.52
WV(mb): 167.79
Dataset: nuscenes
ACCURACY: NDS: 0.3760(FLOAT)/0.3733(INT8)
11.3.48. Centerpoint_mixvargnet_multitask¶
INPUT SIZE: 300000x5
C(GOPs): 51.45
FPS: 106.09
ITC(ms): 23.532
TCPP(ms): 50.427
RV(mb): 33.84
WV(mb): 14.45
Dataset: nuscenes
ACCURACY: NDS: 0.5809(FLOAT)/0.5762(INT8) MeanIOU: 0.9129(FLOAT)/0.9122(INT8)
11.3.49. Stereonetplus_mixvargenet
INPUT SIZE: 2x544x960x3
C(GOPs): 24.29
FPS: 244.52
ITC(ms): 6.407
TCPP(ms): 15.433
RV(mb): 7.02
WV(mb): 6.74
Dataset: SceneFlow
ACCURACY: EPE: 1.1270(FLOAT)/1.1352(INT8)
11.3.50. Densetnt_vectornet
INPUT SIZE: goals_2d: 30x1x2048x2 goals_2d_mask: 30x1x2048x1 instance_mask: 30x1x96x1 lane_feat: 30x9x64x11 traj_feat: 30x19x32x9
C(GOPs): 0.42
FPS: 86.58
ITC(ms): 26.587
TCPP(ms): 10.518
RV(mb): 3.29
WV(mb): 2.92
Dataset: Argoverse 1
ACCURACY: minFDA: 1.2974(FLOAT)/1.3038(INT8)