#Descriptions

• Test Conditions:

  • Test Board: J6E.

  • Number of Test Cores: Single core.

  • Frequency to obtain model performance data: Average of performance parameters over a 5-minute period.

  • Python version: Python 3.10.

  • Models: Models under the samples/ucp_tutorial/dnn/ai_benchmark/j6 path in the OE package.

  • Runtime Environment: Linux.

• Table Header Acronyms:

  • C = Computation, in GOPs (i.e., billion operations per second), obtained by calling the hbm_perf interface.

  • FPS = Frame(s) Per Second, obtained by running the fps.sh script with multi thread of different models in the ai_benchmark sample package/script on the dev board. Post-processing included.

  • ITC = Inference Time Consumption, in ms (millisecond), obtained by running the latency.sh script with single thread of different models in the ai_benchmark sample package/script on the dev board. Post-processing not included.

  • TCPP = Postprocess Time Consumption, in ms (millisecond), obtained by running the latency.sh script with single thread of different models in the ai_benchmark sample package/script on the dev board.

  • RV = Read Volume in a single inference, in mb (Mbit), obtained by calling the hbm_perf interface.

  • WV = Write Volume in a single inference, in mb (Mbit), obtained by calling the hbm_perf interface.

#Model Key Performance Data

#Model Full Performance Data

#MobileNetv1

• INPUT SIZE: 1x3x224x224
• C(GOPs): 1.14
• FPS: 4249.80
• ITC(ms): 0.527
• TCPP(ms): 0.034
• RV(mb): 4.56
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7373(FLOAT)/0.7295(INT8)

#MobileNetv2

• INPUT SIZE: 1x3x224x224
• C(GOPs): 0.63
• FPS: 4272.40
• ITC(ms): 0.544
• TCPP(ms): 0.034
• RV(mb): 3.95
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7217(FLOAT)/0.7146(INT8)

#ResNet50

• INPUT SIZE: 1x3x224x224
• C(GOPs): 7.72
• FPS: 1155.20
• ITC(ms): 1.217
• TCPP(ms): 0.034
• RV(mb): 26.08
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7703(FLOAT)/0.7673(INT8)

#GoogleNet

• INPUT SIZE: 1x3x224x224
• C(GOPs): 3.00
• FPS: 2861.30
• ITC(ms): 0.693
• TCPP(ms): 0.033
• RV(mb): 7.16
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7018(FLOAT)/0.6998(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/GoogleNet

#EfficientNet_Lite0

• INPUT SIZE: 1x224x224x3
• C(GOPs): 0.77
• FPS: 3901.00
• ITC(ms): 0.625
• TCPP(ms): 0.034
• RV(mb): 5.67
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7479(FLOAT)/0.7453(INT8)
• LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite

#EfficientNet_Lite1

• INPUT SIZE: 1x240x240x3
• C(GOPs): 1.20
• FPS: 3175.90
• ITC(ms): 0.684
• TCPP(ms): 0.034
• RV(mb): 6.57
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7652(FLOAT)/0.7609(INT8)
• LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite

#EfficientNet_Lite2

• INPUT SIZE: 1x260x260x3
• C(GOPs): 1.72
• FPS: 2483.40
• ITC(ms): 0.774
• TCPP(ms): 0.034
• RV(mb): 7.41
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7734(FLOAT)/0.7697(INT8)
• LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite

#EfficientNet_Lite3

• INPUT SIZE: 1x280x280x3
• C(GOPs): 2.77
• FPS: 1874.50
• ITC(ms): 0.904
• TCPP(ms): 0.034
• RV(mb): 9.85
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7917(FLOAT)/0.7895(INT8)
• LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite

#EfficientNet_Lite4

• INPUT SIZE: 1x300x300x3
• C(GOPs): 5.11
• FPS: 1289.70
• ITC(ms): 1.148
• TCPP(ms): 0.034
• RV(mb): 14.93
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.8063(FLOAT)/0.8046(INT8)
• LINKS: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite

#Vargconvnet

• INPUT SIZE: 1x3x224x224
• C(GOPs): 9.06
• FPS: 1465.10
• ITC(ms): 1.026
• TCPP(ms): 0.033
• RV(mb): 10.67
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7793(FLOAT)/0.7770(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/VargConvNet

#Efficientnasnet_m

• INPUT SIZE: 1x3x300x300
• C(GOPs): 4.53
• FPS: 1478.80
• ITC(ms): 1.022
• TCPP(ms): 0.033
• RV(mb): 13.99
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7935(FLOAT)/0.7923(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/EfficientnasNet

#Efficientnasnet_s

• INPUT SIZE: 1x3x280x280
• C(GOPs): 1.44
• FPS: 3336.50
• ITC(ms): 0.642
• TCPP(ms): 0.033
• RV(mb): 5.68
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7441(FLOAT)/0.7524(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/EfficientnasNet

#ResNet18

• INPUT SIZE: 1x3x224x224
• C(GOPs): 3.63
• FPS: 2555.50
• ITC(ms): 0.729
• TCPP(ms): 0.034
• RV(mb): 11.87
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7169(FLOAT)/0.7162(INT8)

#YOLOv2_Darknet19

• INPUT SIZE: 1x3x608x608
• C(GOPs): 62.94
• FPS: 227.71
• ITC(ms): 4.777
• TCPP(ms): 0.311
• RV(mb): 51.86
• WV(mb): 0.77
• Dataset: COCO
• ACCURACY: [IoU=0.50:0.95]= 0.2760(FLOAT)/0.2700(INT8)
• LINKS: https://pjreddie.com/darknet/yolo

#YOLOv3_Darknet53

• INPUT SIZE: 1x3x416x416
• C(GOPs): 65.86
• FPS: 210.49
• ITC(ms): 5.187
• TCPP(ms): 1.773
• RV(mb): 68.45
• WV(mb): 9.38
• Dataset: COCO
• ACCURACY: [IoU=0.50:0.95]= 0.3370(FLOAT)/0.3360(INT8)
• LINKS: https://github.com/ChenYingpeng/caffe-yolov3/

#YOLOv5x_v2.0

• INPUT SIZE: 1x3x672x672
• C(GOPs): 243.85
• FPS: 62.39
• ITC(ms): 16.579
• TCPP(ms): 5.904
• RV(mb): 140.22
• WV(mb): 50.31
• Dataset: COCO
• ACCURACY: [IoU=0.50:0.95]= 0.4810(FLOAT)/0.4670(INT8)
• LINKS: https://github.com/ultralytics/yolov5/releases/tag/v2.0

#SSD_MobileNetv1

• INPUT SIZE: 1x3x300x300
• C(GOPs): 2.30
• FPS: 3188.00
• ITC(ms): 0.725
• TCPP(ms): 0.198
• RV(mb): 6.24
• WV(mb): 0.21
• Dataset: VOC
• ACCURACY: mAP: 0.7345(FLOAT)/0.7269(INT8)
• LINKS: https://github.com/chuanqi305/MobileNet-SSD

#Centernet_resnet101

• INPUT SIZE: 1x3x512x512
• C(GOPs): 90.53
• FPS: 186.43
• ITC(ms): 5.791
• TCPP(ms): 0.993
• RV(mb): 59.17
• WV(mb): 11.80
• Dataset: COCO
• ACCURACY: [IoU=0.50:0.95]= 0.3420(FLOAT)/0.3270(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Centernet

#YOLOv3_VargDarknet

• INPUT SIZE: 1x3x416x416
• C(GOPs): 42.82
• FPS: 306.47
• ITC(ms): 3.704
• TCPP(ms): 1.662
• RV(mb): 46.53
• WV(mb): 4.91
• Dataset: COCO
• ACCURACY: [IoU=0.50:0.95]= 0.3280(FLOAT)/0.3270(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/Yolov3_VargDarknet

#Deeplabv3plus_efficientnetb0

• INPUT SIZE: 1x3x1024x2048
• C(GOPs): 30.77
• FPS: 152.01
• ITC(ms): 7.010
• TCPP(ms): 0.311
• RV(mb): 22.10
• WV(mb): 11.80
• Dataset: Cityscapes
• ACCURACY: mIoU: 0.7630(FLOAT)/0.7571(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus

#Fastscnn_efficientnetb0

• INPUT SIZE: 1x3x1024x2048
• C(GOPs): 12.48
• FPS: 249.27
• ITC(ms): 4.433
• TCPP(ms): 0.311
• RV(mb): 12.04
• WV(mb): 9.57
• Dataset: Cityscapes
• ACCURACY: mIoU: 0.6997(FLOAT)/0.6914(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/FastSCNN

#Deeplabv3plus_efficientnetm1

• INPUT SIZE: 1x3x1024x2048
• C(GOPs): 77.04
• FPS: 92.28
• ITC(ms): 11.264
• TCPP(ms): 0.314
• RV(mb): 86.77
• WV(mb): 55.57
• Dataset: Cityscapes
• ACCURACY: mIoU: 0.7794(FLOAT)/0.7754(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus

#Deeplabv3plus_efficientnetm2

• INPUT SIZE: 1x3x1024x2048
• C(GOPs): 124.15
• FPS: 64.82
• ITC(ms): 15.866
• TCPP(ms): 0.312
• RV(mb): 155.15
• WV(mb): 89.13
• Dataset: Cityscapes
• ACCURACY: mIoU: 0.7882(FLOAT)/0.7854(INT8)
• LINKS: https://github.com/HorizonRobotics-Platform/ModelZoo/tree/master/DeeplabV3Plus

#Bev_gkt_mixvargenet_multitask

• INPUT SIZE: image: 6x3x512x960 points(0-8): 6x64x64x2
• C(GOPs): 207.16
• FPS: 68.38
• ITC(ms): 15.893
• TCPP(ms): 4.207
• RV(mb): 120.20
• WV(mb): 96.40
• Dataset: Nuscenes
• ACCURACY: NDS: 0.2810(FLOAT)/0.2786(INT8) MeanIOU: 0.4852(FLOAT)/0.4836(INT8) mAP: 0.1990(FLOAT)/0.2004(INT8)

#Bev_ipm_4d_efficientnetb0_multitask

• INPUT SIZE: image: 6x3x512x960 points: 6x128x128x2 prev_feat: 1x164x28x128 prev_point: 1x128x128x2
• C(GOPs): 53.58
• FPS: 112.27
• ITC(ms): 10.488
• TCPP(ms): 4.276
• RV(mb): 63.66
• WV(mb): 49.97
• Dataset: Nuscenes
• ACCURACY: NDS: 0.3721(FLOAT)/0.3728(INT8) MeanIOU: 0.5287(FLOAT)/0.5388(INT8) mAP: 0.2200(FLOAT)/0.2216(INT8)

#Bev_ipm_efficientnetb0_multitask

• INPUT SIZE: image: 6x3x512x960 points: 6x128x128x2
• C(GOPs): 52.97
• FPS: 115.24
• ITC(ms): 9.822
• TCPP(ms): 4.256
• RV(mb): 60.37
• WV(mb): 47.87
• Dataset: Nuscenes
• ACCURACY: NDS: 0.3056(FLOAT)/0.3041(INT8) MeanIOU: 0.5145(FLOAT)/0.5104(INT8) mAP: 0.2170(FLOAT)/0.2163(INT8)

#Bev_lss_efficientnetb0_multitask

• INPUT SIZE: image: 6x3x256x704 points(0&1): 10x128x128x2
• C(GOPs): 24.06
• FPS: 187.01
• ITC(ms): 6.501
• TCPP(ms): 4.213
• RV(mb): 25.43
• WV(mb): 19.02
• Dataset: Nuscenes
• ACCURACY: NDS: 0.3006(FLOAT)/0.3005(INT8) MeanIOU: 0.5180(FLOAT)/0.5147(INT8) mAP: 0.2061(FLOAT)/0.2043(INT8)

#Detr3d_efficientnetb3

• INPUT SIZE: coords(0-3): 6x4x256x2 image: 6x3x512x1408 masks: 1x4x256x24
• C(GOPs): 227.71
• FPS: 32.10
• ITC(ms): 31.841
• TCPP(ms): 1.104
• RV(mb): 333.48
• WV(mb): 175.59
• Dataset: Nuscenes
• ACCURACY: NDS: 0.3304(FLOAT)/0.3280(INT8) mAP: 0.2752(FLOAT)/0.2706(INT8)

#Petr_efficientnetb3

• INPUT SIZE: image: 6x3x512x1408 pos_embed: 1x96x44x256
• C(GOPs): 219.17
• FPS: 19.28
• ITC(ms): 52.663
• TCPP(ms): 1.122
• RV(mb): 261.01
• WV(mb): 144.25
• Dataset: Nuscenes
• ACCURACY: NDS: 0.3765(FLOAT)/0.3734(INT8) mAP: 0.3038(FLOAT)/0.2930(INT8)

#Bevformer_tiny_resnet50_detection

• INPUT SIZE: img: 6x3x480x800 prev_bev: 1x2500x256 prev_bev_ref: 1x50x50x2 queries_rebatch_grid: 6x20x32x2 restore_bev_grid: 1x100x50x2 reference_points_rebatch: 6x640x4x2 bev_pillar_counts: 1x2500x1
• C(GOPs): 387.29
• FPS: 31.18
• ITC(ms): 42.061
• TCPP(ms): 1.410
• RV(mb): 265.59
• WV(mb): 175.42
• Dataset: Nuscenes
• ACCURACY: NDS: 0.3713(FLOAT)/0.3679(INT8) mAP: 0.2673(FLOAT)/0.2614(INT8)

#Flashocc_henet_lss_occ3d_nuscenes

• INPUT SIZE: img: 6x3x512x960 points: 10x128x128x2 points_depth: 10x128x128x2
• C(GOPs): 126.75
• FPS: 96.42
• ITC(ms): 11.476
• TCPP(ms): 40.473
• RV(mb): 87.47
• WV(mb): 55.84
• Dataset: Nuscenes
• ACCURACY: mIoU: 0.3674(FLOAT)/0.3639(INT8)

#Horizon_swin_transformer

• INPUT SIZE: 1x3x224x224
• C(GOPs): 8.98
• FPS: 310.55
• ITC(ms): 3.589
• TCPP(ms): 0.035
• RV(mb): 45.99
• WV(mb): 6.52
• Dataset: ImageNet
• ACCURACY: Top1: 0.8024(FLOAT)/0.7958(INT8)

#Mixvargenet

• INPUT SIZE: 1x3x224x224
• C(GOPs): 2.07
• FPS: 4466.90
• ITC(ms): 0.530
• TCPP(ms): 0.034
• RV(mb): 2.51
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7075(FLOAT)/0.7049(INT8)

#Vargnetv2

• INPUT SIZE: 1x3x224x224
• C(GOPs): 0.72
• FPS: 4127.50
• ITC(ms): 0.577
• TCPP(ms): 0.034
• RV(mb): 4.68
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7342(FLOAT)/0.7326(INT8)

#Vit_small

• INPUT SIZE: 1x3x224x224
• C(GOPs): 9.20
• FPS: 545.78
• ITC(ms): 2.190
• TCPP(ms): 0.034
• RV(mb): 26.29
• WV(mb): 0.0041
• Dataset: ImageNet
• ACCURACY: Top1: 0.7950(FLOAT)/0.7933(INT8)

#Centerpoint_pointpillar

• INPUT SIZE: points: 300000x5 voxel_feature: 1x5x20x40000 coors: 40000x4
• C(GOPs): 127.73
• FPS: 124.75
• ITC(ms): 16.656
• TCPP(ms): 13.024
• RV(mb): 51.37
• WV(mb): 25.83
• Dataset: Nuscenes
• ACCURACY: NDS: 0.5832(FLOAT)/0.5816(INT8) mAP: 0.4804(FLOAT)/0.4784(INT8)

#Detr_efficientnetb3

• INPUT SIZE: 1x3x800x1333
• C(GOPs): 67.39
• FPS: 52.74
• ITC(ms): 19.379
• TCPP(ms): 0.340
• RV(mb): 261.92
• WV(mb): 134.89
• Dataset: MS COCO
• ACCURACY: [IoU=0.50:0.95]= 0.3721(FLOAT)/0.3595(INT8)

#Detr_resnet50

• INPUT SIZE: 1x3x800x1333
• C(GOPs): 203.07
• FPS: 40.46
• ITC(ms): 25.304
• TCPP(ms): 0.353
• RV(mb): 357.82
• WV(mb): 222.85
• Dataset: MS COCO
• ACCURACY: [IoU=0.50:0.95]= 0.3569(FLOAT)/0.3161(INT8)

#FCOS3D_efficientnetb0

• INPUT SIZE: 1x3x512x896
• C(GOPs): 19.94
• FPS: 447.92
• ITC(ms): 3.346
• TCPP(ms): 2.732
• RV(mb): 11.23
• WV(mb): 4.17
• Dataset: nuscenes
• ACCURACY: NDS: 0.3062(FLOAT)/0.3030(INT8) mAP: 0.2133(FLOAT)/0.2069(INT8)

#Fcos_efficientnetb0

• INPUT SIZE: 1x3x512x512
• C(GOPs): 5.02
• FPS: 1080.30
• ITC(ms): 1.615
• TCPP(ms): 0.137
• RV(mb): 6.09
• WV(mb): 2.68
• Dataset: MS COCO
• ACCURACY: [IoU=0.50:0.95]= 0.3626(FLOAT)/0.3553(INT8)

#Ganet_mixvargenet

• INPUT SIZE: 1x3x320x800
• C(GOPs): 10.74
• FPS: 1573.20
• ITC(ms): 1.018
• TCPP(ms): 0.213
• RV(mb): 2.16
• WV(mb): 0.52
• Dataset: CuLane
• ACCURACY: F1Score: 0.7949(FLOAT)/0.7882(INT8)

#Keypoint_efficientnetb0

• INPUT SIZE: 1x3x128x128
• C(GOPs): 0.45
• FPS: 4317.90
• ITC(ms): 0.543
• TCPP(ms): 0.073
• RV(mb): 4.62
• WV(mb): 0.01
• Dataset: Carfusion
• ACCURACY: PCK(alpha=0.1): 0.9433(FLOAT)/0.9432(INT8)

#Pointpillars_kitti_car

• INPUT SIZE: 150000x4
• C(GOPs): 66.82
• FPS: 150.45
• ITC(ms): 32.923
• TCPP(ms): 0.539
• RV(mb): 69.93
• WV(mb): 30.00
• Dataset: Kitti3d
• ACCURACY: APDet= 0.7732(FLOAT)/0.7678(INT8)

#Deformable_detr_resnet50

• INPUT SIZE: 1x3x800x1333
• C(GOPs): 408.94
• FPS: 5.27
• ITC(ms): 190.370
• TCPP(ms): 15.590
• RV(mb): 3495.68
• WV(mb): 2486.20
• Dataset: MS COCO
• ACCURACY: [IoU=0.50:0.95]= 0.4414(FLOAT)/0.4197(INT8)

#Stereonetplus_mixvargenet

• INPUT SIZE: 2x3x544x960
• C(GOPs): 48.57
• FPS: 229.34
• ITC(ms): 4.868
• TCPP(ms): 1.973
• RV(mb): 27.85
• WV(mb): 25.98
• Dataset: SceneFlow
• ACCURACY: EPE: 1.1270(FLOAT)/1.1341(INT8)

#Centerpoint_mixvargnet_multitask

• INPUT SIZE: points: 300000x5 voxel_feature: 1x5x20x40000 coors: 40000x4
• C(GOPs): 51.45
• FPS: 186.61
• ITC(ms): 14.074
• TCPP(ms): 11.740
• RV(mb): 32.08
• WV(mb): 16.79
• Dataset: Nuscenes
• ACCURACY: NDS: 0.5809(FLOAT)/0.5753(INT8) MeanIOU: 0.9128(FLOAT)/0.9121(INT8) mAP: 0.4726(FLOAT)/0.4626(INT8)

#Unet_mobilenetv1

• INPUT SIZE: 1x3x1024x2048
• C(GOPs): 7.36
• FPS: 810.01
• ITC(ms): 1.739
• TCPP(ms): 0.149
• RV(mb): 13.27
• WV(mb): 7.60
• Dataset: Cityscapes
• ACCURACY: mIoU: 0.6802(FLOAT)/0.6758(INT8)

#Motr_efficientnetb3

• INPUT SIZE: image: 1x800x1422x3 track_query: 1x2x128x156 ref_points: 1x2x128x4 mask_query: 1x1x256x1
• C(GOPs): 64.43
• FPS: 74.64
• ITC(ms): 13.600
• TCPP(ms): 5.098
• RV(mb): 114.93
• WV(mb): 47.16
• Dataset: Mot17
• ACCURACY: MOTA: 0.5805(FLOAT)/0.5749(INT8)

#Densetnt_vectornet

• INPUT SIZE: goals_2d: 30x1x2048x2 goals_2d_mask: 30x1x2048x1 instance_mask: 30x1x96x1 lane_feat: 30x9x64x11 traj_feat: 30x19x32x9
• C(GOPs): 12.50
• FPS: 104.53
• ITC(ms): 10.394
• TCPP(ms): 2.315
• RV(mb): 53.07
• WV(mb): 33.59
• Dataset: Argoverse 1
• ACCURACY: minFDA: 1.2975(FLOAT)/1.3054(INT8)

#Maptroe_henet_tinym_bevformer

• INPUT SIZE: img: 6x3x480x800 osm_mask: 1x1x50x100 queries_rebatch_grid: 6x20x100x2 restore_bev_grid: 1x100x100x2 reference_points_rebatch: 6x2000x4x2 bev_pillar_counts: 1x5000x1
• C(GOPs): 134.57
• FPS: 75.35
• ITC(ms): 13.961
• TCPP(ms): 0.260
• RV(mb): 121.59
• WV(mb): 36.83
• Dataset: Nuscenes
• ACCURACY: mAP: 0.6633(FLOAT)/0.6572(INT8)

#Qcnet_oe

• INPUT SIZE: valid_mask: 1x30x10 valid_mask_a2a: 1x10x30x30 agent_type: 1x30x1 x_a_cur: 1x1x30x1,1x1x30x1,1x1x30x1,1x1x30x1 r_pl2a_cur: 1x1x30x80,1x1x30x80,1x1x30x80 r_t_cur: 1x1x30x6,1x1x30x6,1x1x30x6,1x1x30x6 r_a2a_cur: 1x1x30x30,1x1x30x30,1x1x30x30 x_a_mid_emb: 1x30x2x128 x_a: 1x30x6x128 pl_type,is_intersection: 1x80 r_pl2pl: 1x1x80x80,1x1x80x80,1x1x80x80 r_pt2pl: 1x1x80x50,1x1x80x50,1x1x80x50 mask_pl2pl: 1x80x80 magnitude,pt_type,side,mask: 1x80x50 mask_a2m: 1x30x30 mask_dst: 1x30x1 type_pl2pl: 1x80x80
• C(GOPs): 7.85
• FPS: 236.24
• ITC(ms): 6.309
• TCPP(ms): 0.867
• RV(mb): 37.89
• WV(mb): 18.04
• Dataset: Argoverse 2
• ACCURACY: hitrate: 0.8025(FLOAT)/0.7953(INT8)