• 中文
  • 3.8.1

    • J6B 模型性能Benchmark

    • 测试开发板：J6B

    • 模型来源：OE包内 samples/ucp_tutorial/dnn/ai_benchmark/j6 路径下的模型

    • 运行环境：QNX

    模型精度

    MODEL NAMEINPUT SIZEACCURACYDataset
    ResNet50

    1x3x224x224

    Top1:

    0.7703(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:

    0.6976(FLOAT)/0.6948(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
    Flashocc_henet_lss_occ3d_nuscenes

    img:

    6x3x512x960

    points:

    10x128x128x2

    points_depth:

    10x128x128x2

    mIoU:

    0.3675(FLOAT)/0.3685(INT8)

    		Nuscenes
    FCOS3D_efficientnetb0

    1x3x512x896

    NDS:

    0.3061(FLOAT)/0.3022(INT8)

    mAP:

    0.2133(FLOAT)/0.2098(INT8)

    		nuscenes
    Unet_mobilenetv1

    1x3x1024x2048

    mIoU:

    0.6802(FLOAT)/0.6764(INT8)

    		Cityscapes
    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:

    0.6632(FLOAT)/0.6566(INT8)

    		Nuscenes

    模型性能

    MODEL NAMEINPUT SIZELatency(ms)FPSFPS Configuration
    ResNet50

    1x3x224x224

    		2.585469.11thread_num:4
    GoogleNet

    1x3x224x224

    		1.2761204.82thread_num:4
    EfficientNet_Lite1

    1x240x240x3

    		1.1621617.32thread_num:4
    EfficientNet_Lite2

    1x260x260x3

    		1.4851053.13thread_num:4
    EfficientNet_Lite3

    1x280x280x3

    		1.832771.38thread_num:4
    EfficientNet_Lite4

    1x300x300x3

    		2.496510.08thread_num:4
    Vargconvnet

    1x3x224x224

    		2.104604.94thread_num:4
    Efficientnasnet_m

    1x3x300x300

    		2.165581.15thread_num:4
    Efficientnasnet_s

    1x3x280x280

    		1.1351455.17thread_num:4
    ResNet18

    1x3x224x224

    		1.497961.40thread_num:4
    YOLOv2_Darknet19

    1x3x608x608

    		14.02573.55thread_num:4
    YOLOv3_Darknet53

    1x3x416x416

    		13.58776.07thread_num:4
    YOLOv5x_v2.0

    1x3x672x672

    		48.00721.04thread_num:4
    Centernet_resnet101

    1x3x512x512

    		15.05068.50thread_num:4
    YOLOv3_VargDarknet

    1x3x416x416

    		9.440111.42thread_num:4
    Deeplabv3plus_efficientnetb0

    1x3x1024x2048

    		14.99468.63thread_num:4
    Fastscnn_efficientnetb0

    1x3x1024x2048

    		8.293128.03thread_num:4
    Deeplabv3plus_efficientnetm1

    1x3x1024x2048

    		26.87837.77thread_num:4
    Deeplabv3plus_efficientnetm2

    1x3x1024x2048

    		40.84324.75thread_num:4
    Flashocc_henet_lss_occ3d_nuscenes

    img:

    6x3x512x960

    points:

    10x128x128x2

    points_depth:

    10x128x128x2

    		29.69034.30thread_num:6
    FCOS3D_efficientnetb0

    1x3x512x896

    		6.397184.55thread_num:4
    Unet_mobilenetv1

    1x3x1024x2048

    		3.790331.25thread_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

    		35.70928.50thread_num:4