• English
  • 3.7.0

    • J6B Benchmark of Model Performance

    • Test Board: J6B

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

    • Runtime Environment: QNX

    MODEL ACCURACY

    MODEL NAMEINPUT SIZEACCURACYDataset
    ResNet50

    1x3x224x224

    Top1:

    0.7704(FLOAT)/0.7661(INT8)

    		ImageNet
    GoogleNet

    1x3x224x224

    Top1:

    0.7018(FLOAT)/0.6995(INT8)

    		ImageNet
    EfficientNet_Lite1

    1x240x240x3

    Top1:

    0.7652(FLOAT)/0.7602(INT8)

    		ImageNet
    EfficientNet_Lite2

    1x260x260x3

    Top1:

    0.7734(FLOAT)/0.7696(INT8)

    		ImageNet
    EfficientNet_Lite3

    1x280x280x3

    Top1:

    0.7917(FLOAT)/0.7885(INT8)

    		ImageNet
    EfficientNet_Lite4

    1x300x300x3

    Top1:

    0.8063(FLOAT)/0.8041(INT8)

    		ImageNet
    Vargconvnet

    1x3x224x224

    Top1:

    0.7793(FLOAT)/0.7765(INT8)

    		ImageNet
    Efficientnasnet_m

    1x3x300x300

    Top1:

    0.7935(FLOAT)/0.7923(INT8)

    		ImageNet
    Efficientnasnet_s

    1x3x280x280

    Top1:

    0.7441(FLOAT)/0.7516(INT8)

    		ImageNet
    ResNet18

    1x3x224x224

    Top1:

    0.7170(FLOAT)/0.7159(INT8)

    		ImageNet
    YOLOv2_Darknet19

    1x3x608x608

    [IoU=0.50:0.95]=

    0.2760(FLOAT)/0.2707(INT8)

    		COCO
    YOLOv3_Darknet53

    1x3x416x416

    [IoU=0.50:0.95]=

    0.3370(FLOAT)/0.3370(INT8)

    		COCO
    YOLOv5x_v2.0

    1x3x672x672

    [IoU=0.50:0.95]=

    0.4810(FLOAT)/0.4670(INT8)

    		COCO
    Centernet_resnet101

    1x3x512x512

    [IoU=0.50:0.95]=

    0.3420(FLOAT)/0.3270(INT8)

    		COCO
    YOLOv3_VargDarknet

    1x3x416x416

    [IoU=0.50:0.95]=

    0.3280(FLOAT)/0.3260(INT8)

    		COCO
    Deeplabv3plus_efficientnetb0

    1x3x1024x2048

    mIoU:

    0.7630(FLOAT)/0.7569(INT8)

    		Cityscapes
    Fastscnn_efficientnetb0

    1x3x1024x2048

    mIoU:

    0.6997(FLOAT)/0.6909(INT8)

    		Cityscapes
    Deeplabv3plus_efficientnetm1

    1x3x1024x2048

    mIoU:

    0.7794(FLOAT)/0.7756(INT8)

    		Cityscapes
    Deeplabv3plus_efficientnetm2

    1x3x1024x2048

    mIoU:

    0.7882(FLOAT)/0.7854(INT8)

    		Cityscapes
    Bev_gkt_mixvargenet_multitask

    image:

    6x3x512x960

    points(0-8):

    6x64x64x2

    NDS:

    0.2810(FLOAT)/0.2789(INT8)

    MeanIOU:

    0.4852(FLOAT)/0.4839(INT8)

    mAP:

    0.1990(FLOAT)/0.1993(INT8)

    		Nuscenes
    Bev_ipm_4d_efficientnetb0_multitask

    image:

    6x3x512x960

    points:

    6x128x128x2

    prev_feat:

    1x164x28x128

    prev_point:

    1x128x128x2

    NDS:

    0.3722(FLOAT)/0.3723(INT8)

    MeanIOU:

    0.5287(FLOAT)/0.5389(INT8)

    mAP:

    0.2201(FLOAT)/0.2217(INT8)

    		Nuscenes
    Bev_ipm_efficientnetb0_multitask

    image:

    6x3x512x960

    points:

    6x128x128x2

    NDS:

    0.3055(FLOAT)/0.3042(INT8)

    MeanIOU:

    0.5145(FLOAT)/0.5103(INT8)

    mAP:

    0.2170(FLOAT)/0.2166(INT8)

    		Nuscenes
    Bev_lss_efficientnetb0_multitask

    image:

    6x3x256x704

    points(0&1):

    10x128x128x2

    NDS:

    0.3006(FLOAT)/0.3010(INT8)

    MeanIOU:

    0.5180(FLOAT)/0.5172(INT8)

    mAP:

    0.2061(FLOAT)/0.2047(INT8)

    		Nuscenes
    Detr3d_efficientnetb3

    coords(0-3):

    6x4x256x2

    image:

    6x3x512x1408

    masks:

    1x4x256x24

    NDS:

    0.3304(FLOAT)/0.3306(INT8)

    mAP:

    0.2753(FLOAT)/0.2742(INT8)

    		Nuscenes
    Petr_efficientnetb3

    image:

    6x3x512x1408

    pos_embed:

    1x96x44x256

    NDS:

    0.3765(FLOAT)/0.3748(INT8)

    mAP:

    0.3038(FLOAT)/0.2942(INT8)

    		Nuscenes
    Bevformer_tiny_resnet50_detection

    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

    NDS:

    0.3713(FLOAT)/0.3700(INT8)

    mAP:

    0.2673(FLOAT)/0.2644(INT8)

    		Nuscenes
    Flashocc_henet_lss_occ3d_nuscenes

    img:

    6x3x512x960

    points:

    10x128x128x2

    points_depth:

    10x128x128x2

    mIoU:

    0.3675(FLOAT)/0.3685(INT8)

    		Nuscenes
    Horizon_swin_transformer

    1x3x224x224

    Top1:

    0.8024(FLOAT)/0.7982(INT8)

    		ImageNet
    Vargnetv2

    1x3x224x224

    Top1:

    0.7342(FLOAT)/0.7332(INT8)

    		ImageNet
    Vit_small

    1x3x224x224

    Top1:

    0.7950(FLOAT)/0.7924(INT8)

    		ImageNet
    Centerpoint_pointpillar

    points:

    300000x5

    voxel_feature:

    1x5x20x40000

    coors:

    40000x4

    NDS:

    0.5832(FLOAT)/0.5820(INT8)

    mAP:

    0.4804(FLOAT)/0.4782(INT8)

    		Nuscenes
    Detr_efficientnetb3

    1x3x800x1333

    [IoU=0.50:0.95]=

    0.3720(FLOAT)/0.3584(INT8)

    		MS COCO
    Detr_resnet50

    1x3x800x1333

    [IoU=0.50:0.95]=

    0.3569(FLOAT)/0.3163(INT8)

    		MS COCO
    FCOS3D_efficientnetb0

    1x3x512x896

    NDS:

    0.3061(FLOAT)/0.3022(INT8)

    mAP:

    0.2133(FLOAT)/0.2098(INT8)

    		nuscenes
    Fcos_efficientnetb0

    1x3x512x512

    [IoU=0.50:0.95]=

    0.3626(FLOAT)/0.3563(INT8)

    		MS COCO
    Ganet_mixvargenet

    1x3x320x800

    F1Score:

    0.7949(FLOAT)/0.7884(INT8)

    		CuLane
    Stereonetplus_mixvargenet

    2x3x544x960

    EPE:

    1.1270(FLOAT)/1.1336(INT8)

    		SceneFlow
    Centerpoint_mixvargnet_multitask

    points:

    300000x5

    voxel_feature:

    1x5x20x40000

    coors:

    40000x4

    NDS:

    0.5809(FLOAT)/0.5766(INT8)

    MeanIOU:

    0.9128(FLOAT)/0.9126(INT8)

    mAP:

    0.4727(FLOAT)/0.4649(INT8)

    		Nuscenes
    Unet_mobilenetv1

    1x3x1024x2048

    mIoU:

    0.6801(FLOAT)/0.6764(INT8)

    		Cityscapes
    Densetnt_vectornet

    goals_2d:

    30x1x2048x2

    goals_2d_mask:

    30x1x2048x1

    instance_mask:

    30x1x96x1

    lane_feat:

    30x9x64x11

    traj_feat:

    30x19x32x9

    minFDA:

    1.2975(FLOAT)/1.2989(INT8)

    		Argoverse 1
    Maptroe_henet_tinym_bevformer

    img:

    6x3x480x800

    osm_mask:

    1x1x50x100

    queries_rebatch_grid:

    6x20x100x2

    restore_bev_grid:

    1x100x100x2

    reference_points_rebatch:

    6x2000x4x2

    bev_pillar_counts:

    1x5000x1

    mAP:

    0.6633(FLOAT)/0.6565(INT8)

    		Nuscenes

    MODEL PERFORMANCE

    MODEL NAMEINPUT SIZELatency(ms)FPSFPS Configuration
    ResNet50

    1x3x224x224

    		2.607469.22thread_num:4
    GoogleNet

    1x3x224x224

    		1.2841204.96thread_num:4
    EfficientNet_Lite1

    1x240x240x3

    		1.1601617.90thread_num:4
    EfficientNet_Lite2

    1x260x260x3

    		1.4951053.15thread_num:4
    EfficientNet_Lite3

    1x280x280x3

    		1.845771.38thread_num:4
    EfficientNet_Lite4

    1x300x300x3

    		2.508510.09thread_num:4
    Vargconvnet

    1x3x224x224

    		2.107604.95thread_num:4
    Efficientnasnet_m

    1x3x300x300

    		2.171581.15thread_num:4
    Efficientnasnet_s

    1x3x280x280

    		1.1371455.22thread_num:4
    ResNet18

    1x3x224x224

    		1.482987.00thread_num:4
    YOLOv2_Darknet19

    1x3x608x608

    		14.08273.55thread_num:4
    YOLOv3_Darknet53

    1x3x416x416

    		13.65876.07thread_num:4
    YOLOv5x_v2.0

    1x3x672x672

    		48.13621.04thread_num:4
    Centernet_resnet101

    1x3x512x512

    		15.11668.50thread_num:4
    YOLOv3_VargDarknet

    1x3x416x416

    		9.477111.42thread_num:4
    Deeplabv3plus_efficientnetb0

    1x3x1024x2048

    		15.06268.63thread_num:4
    Fastscnn_efficientnetb0

    1x3x1024x2048

    		8.290128.03thread_num:4
    Deeplabv3plus_efficientnetm1

    1x3x1024x2048

    		26.99737.77thread_num:4
    Deeplabv3plus_efficientnetm2

    1x3x1024x2048

    		40.96424.75thread_num:4
    Bev_gkt_mixvargenet_multitask

    image:

    6x3x512x960

    points(0-8):

    6x64x64x2

    		38.69026.69thread_num:4
    Bev_ipm_4d_efficientnetb0_multitask

    image:

    6x3x512x960

    points:

    6x128x128x2

    prev_feat:

    1x164x28x128

    prev_point:

    1x128x128x2

    		21.93348.06thread_num:4
    Bev_ipm_efficientnetb0_multitask

    image:

    6x3x512x960

    points:

    6x128x128x2

    		21.51848.95thread_num:4
    Bev_lss_efficientnetb0_multitask

    image:

    6x3x256x704

    points(0&1):

    10x128x128x2

    		11.89792.54thread_num:4
    Detr3d_efficientnetb3

    coords(0-3):

    6x4x256x2

    image:

    6x3x512x1408

    masks:

    1x4x256x24

    		76.34613.23thread_num:4
    Petr_efficientnetb3

    image:

    6x3x512x1408

    pos_embed:

    1x96x44x256

    		104.9879.60thread_num:4
    Bevformer_tiny_resnet50_detection

    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

    		82.76312.21thread_num:4
    Flashocc_henet_lss_occ3d_nuscenes

    img:

    6x3x512x960

    points:

    10x128x128x2

    points_depth:

    10x128x128x2

    		29.20435.04thread_num:6
    Horizon_swin_transformer

    1x3x224x224

    		5.404202.95thread_num:4
    Vargnetv2

    1x3x224x224

    		0.7603243.04thread_num:4
    Vit_small

    1x3x224x224

    		3.804300.47thread_num:4
    Centerpoint_pointpillar

    points:

    300000x5

    voxel_feature:

    1x5x20x40000

    coors:

    40000x4

    		47.78146.22thread_num:4
    Detr_efficientnetb3

    1x3x800x1333

    		37.89626.80thread_num:4
    Detr_resnet50

    1x3x800x1333

    		56.94917.75thread_num:4
    FCOS3D_efficientnetb0

    1x3x512x896

    		6.451184.53thread_num:4
    Fcos_efficientnetb0

    1x3x512x512

    		3.079527.25thread_num:4
    Ganet_mixvargenet

    1x3x320x800

    		2.205584.60thread_num:4
    Stereonetplus_mixvargenet

    2x3x544x960

    		9.206115.12thread_num:4
    Centerpoint_mixvargnet_multitask

    points:

    300000x5

    voxel_feature:

    1x5x20x40000

    coors:

    40000x4

    		36.97989.53thread_num:6
    Unet_mobilenetv1

    1x3x1024x2048

    		3.793331.25thread_num:4
    Densetnt_vectornet

    goals_2d:

    30x1x2048x2

    goals_2d_mask:

    30x1x2048x1

    instance_mask:

    30x1x96x1

    lane_feat:

    30x9x64x11

    traj_feat:

    30x19x32x9

    		12.91882.19thread_num:4
    Maptroe_henet_tinym_bevformer

    img:

    6x3x480x800

    osm_mask:

    1x1x50x100

    queries_rebatch_grid:

    6x20x100x2

    restore_bev_grid:

    1x100x100x2

    reference_points_rebatch:

    6x2000x4x2

    bev_pillar_counts:

    1x5000x1

    		34.16829.92thread_num:4