Bump version 4.9 (#222)

* update benchmark results on i7-12700K

* update benchmark results on edge2

* add benchmark results on Horizon Sunrise X3 PI

* add benchmark results on Jetson Nano B01 (CPU)

* add benchmark results on Raspberry Pi 4B

* add benchmark results on Jetson Nano B01 (GPU)

* add MAIX-III and StarFive benchmark results

* update benchmark results on Khadas VIM3

* update hardware setup info

* bump opencv version requirement to 4.9.0

* update benchmark results on RV1126

* regenerate table

* change * to x in input size text

* regenerate table

* rollback for '\\*'

* regenerate table

* add description for atlas 200i dk a2

* tune table

---------

Co-authored-by: Wanli <wanli.zhong.1999@gmail.com>

README.md

@@ -25,16 +25,24 @@ Guidelines:
 
 Hardware Setup:
 
+x86-64:
 - [Intel Core i7-12700K](https://www.intel.com/content/www/us/en/products/sku/134594/intel-core-i712700k-processor-25m-cache-up-to-5-00-ghz/specifications.html): 8 Performance-cores (3.60 GHz, turbo up to 4.90 GHz), 4 Efficient-cores (2.70 GHz, turbo up to 3.80 GHz), 20 threads.
-- [Raspberry Pi 4B](https://www.raspberrypi.com/products/raspberry-pi-4-model-b/specifications/): Broadcom BCM2711 SoC with a Quad core Cortex-A72 (ARM v8) 64-bit @ 1.5 GHz.
-- [Toybrick RV1126](https://t.rock-chips.com/en/portal.php?mod=view&aid=26): Rockchip RV1126 SoC with a quard-core ARM Cortex-A7 CPU and a 2.0 TOPs NPU.
+
+ARM:
+- [Khadas VIM3](https://www.khadas.com/vim3): Amlogic A311D SoC with a 2.2GHz Quad core ARM Cortex-A73 + 1.8GHz dual core Cortex-A53 ARM CPU, and a 5 TOPS NPU. Benchmarks are done using **per-tensor quantized** models. Follow [this guide](https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU) to build OpenCV with TIM-VX backend enabled.
+- [Khadas VIM4](https://www.khadas.com/vim4): Amlogic A311D2 SoC with 2.2GHz Quad core ARM Cortex-A73 and 2.0GHz Quad core Cortex-A53 CPU, and 3.2 TOPS Build-in NPU.
 - [Khadas Edge 2](https://www.khadas.com/edge2): Rockchip RK3588S SoC with a CPU of 2.25 GHz Quad Core ARM Cortex-A76 + 1.8 GHz Quad Core Cortex-A55, and a 6 TOPS NPU.
+- [Atlas 200 DK](https://e.huawei.com/en/products/computing/ascend/atlas-200): Ascend 310 NPU with 22 TOPS @ INT8. Follow [this guide](https://github.com/opencv/opencv/wiki/Huawei-CANN-Backend) to build OpenCV with CANN backend enabled.
+- [Atlas 200I DK A2](https://www.hiascend.com/hardware/developer-kit-a2): SoC with 1.0GHz Quad-core CPU and Ascend 310B NPU with 8 TOPS @ INT8.
+- [NVIDIA Jetson Nano B01](https://developer.nvidia.com/embedded/jetson-nano-developer-kit): a Quad-core ARM A57 @ 1.43 GHz CPU, and a 128-core NVIDIA Maxwell GPU.
+- [NVIDIA Jetson Nano Orin](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/): a 6-core Arm® Cortex®-A78AE v8.2 64-bit CPU, and a 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores (max freq 625MHz).
+- [Raspberry Pi 4B](https://www.raspberrypi.com/products/raspberry-pi-4-model-b/specifications/): Broadcom BCM2711 SoC with a Quad core Cortex-A72 (ARM v8) 64-bit @ 1.5 GHz.
 - [Horizon Sunrise X3](https://developer.horizon.ai/sunrise): an SoC from Horizon Robotics with a quad-core ARM Cortex-A53 1.2 GHz CPU and a 5 TOPS BPU (a.k.a NPU).
 - [MAIX-III AXera-Pi](https://wiki.sipeed.com/hardware/en/maixIII/ax-pi/axpi.html#Hardware): Axera AX620A SoC with a quad-core ARM Cortex-A7 CPU and a 3.6 TOPS @ int8 NPU.
+- [Toybrick RV1126](https://t.rock-chips.com/en/portal.php?mod=view&aid=26): Rockchip RV1126 SoC with a quard-core ARM Cortex-A7 CPU and a 2.0 TOPs NPU.
+
+RISC-V:
 - [StarFive VisionFive 2](https://doc-en.rvspace.org/VisionFive2/Product_Brief/VisionFive_2/specification_pb.html): `StarFive JH7110` SoC with a RISC-V quad-core CPU, which can turbo up to 1.5GHz, and an GPU of model `IMG BXE-4-32 MC1` from Imagination, which has a work freq up to 600MHz.
-- [NVIDIA Jetson Nano B01](https://developer.nvidia.com/embedded/jetson-nano-developer-kit): a Quad-core ARM A57 @ 1.43 GHz CPU, and a 128-core NVIDIA Maxwell GPU.
-- [Khadas VIM3](https://www.khadas.com/vim3): Amlogic A311D SoC with a 2.2GHz Quad core ARM Cortex-A73 + 1.8GHz dual core Cortex-A53 ARM CPU, and a 5 TOPS NPU. Benchmarks are done using **per-tensor quantized** models. Follow [this guide](https://github.com/opencv/opencv/wiki/TIM-VX-Backend-For-Running-OpenCV-On-NPU) to build OpenCV with TIM-VX backend enabled.
-- [Atlas 200 DK](https://e.huawei.com/en/products/computing/ascend/atlas-200): Ascend 310 NPU with 22 TOPS @ INT8. Follow [this guide](https://github.com/opencv/opencv/wiki/Huawei-CANN-Backend) to build OpenCV with CANN backend enabled.
 - [Allwinner Nezha D1](https://d1.docs.aw-ol.com/en): Allwinner D1 SoC with a 1.0 GHz single-core RISC-V [Xuantie C906 CPU](https://www.t-head.cn/product/C906?spm=a2ouz.12986968.0.0.7bfc1384auGNPZ) with RVV 0.7.1 support. YuNet is tested for now. Visit [here](https://github.com/fengyuentau/opencv_zoo_cpp) for more details.
 
 ***Important Notes***:

benchmark/README.md

@@ -72,51 +72,51 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-0.73       0.81       0.58       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-0.85       0.78       0.58       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-4.52       4.70       4.25       [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-6.67       7.25       4.25       [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-2.53       2.33       2.18       [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-3.77       3.71       2.18       [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-3.91       3.84       3.65       [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-4.66       4.99       3.65       [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-8.21       8.97       6.22       [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-8.73       10.08      6.22       [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-4.33       4.70       3.65       [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-4.20       4.05       3.19       [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-4.87       3.92       3.19       [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-5.30       6.19       3.19       [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-24.26      23.81      23.25      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-29.45      30.19      23.25      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-9.06       8.40       7.64       [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-10.25      12.59      7.64       [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-44.85      45.84      43.06      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-46.10      47.53      43.06      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-144.89     149.58     125.71     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-143.83     146.39     119.75     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-12.52      14.47      11.63      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-12.99      13.11      12.14      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-12.64      12.44      10.82      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-12.64      11.83      11.03      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-22.13      21.99      21.48      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-26.37      33.51      21.48      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-10.07      9.68       8.16       [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+0.69       0.70       0.68       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+0.79       0.80       0.68       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+5.09       5.13       4.96       [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+6.50       6.79       4.96       [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+1.79       1.76       1.75       [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+2.92       3.11       1.75       [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+2.40       2.43       2.37       [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+3.11       3.15       2.37       [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+5.59       5.56       5.28       [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+6.07       6.22       5.28       [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+3.13       3.14       3.05       [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+3.04       3.02       2.92       [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+3.46       3.03       2.92       [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+3.84       3.77       2.92       [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+19.47      19.47      19.08      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+21.52      21.86      19.08      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+5.68       5.66       5.51       [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+7.41       7.36       5.51       [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+41.02      40.99      40.86      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+42.23      42.30      40.86      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+78.77      79.76      77.16      [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+75.69      75.58      72.57      [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+4.01       3.84       3.79       [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+5.35       5.41       5.22       [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+6.73       6.85       5.22       [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+7.65       7.65       7.55       [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+15.56      15.57      15.10      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+16.67      16.57      15.10      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+6.33       6.63       6.14       [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
 1.19       1.30       1.07       [100, 100]   WeChatQRCode with ['detect_2021nov.prototxt', 'detect_2021nov.caffemodel', 'sr_2021nov.prototxt', 'sr_2021nov.caffemodel']
-23.86      24.16      23.26      [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-23.94      23.76      23.26      [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-26.89      24.78      23.26      [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-28.82      29.58      23.26      [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-17.97      16.18      12.43      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-19.54      20.66      12.43      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-17.73      24.25      9.65       [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-17.65      18.90      9.65       [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-16.97      15.14      9.65       [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-17.21      16.47      9.65       [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-17.68      14.54      9.65       [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-17.31      16.09      9.65       [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
-```
-
-### Rasberry Pi 4B
+18.76      19.59      18.48      [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+18.59      19.33      18.12      [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+22.05      18.60      18.12      [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+24.47      25.06      18.12      [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+10.61      10.66      10.50      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+11.03      11.23      10.50      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+9.85       11.62      7.74       [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+10.02      9.71       7.74       [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+9.53       7.83       7.74       [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+9.68       9.21       7.74       [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+9.85       10.63      7.74       [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+9.63       9.28       7.74       [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+```
+
+### Raspberry Pi 4B
 
 Specs: [details](https://www.raspberrypi.com/products/raspberry-pi-4-model-b/specifications/)
 - CPU: Broadcom BCM2711, Quad core Cortex-A72 (ARM v8) 64-bit SoC @ 1.5 GHz.
@@ -129,48 +129,48 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-5.96       5.93       5.90       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-6.09       6.11       5.90       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-73.30      73.22      72.32      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-88.20      89.95      72.32      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-32.33      32.20      31.99      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-39.82      40.78      31.99      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-108.37     108.31     106.93     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-75.91      78.95      49.78      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-76.29      77.10      75.21      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-77.33      77.73      75.21      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-66.22      66.09      65.90      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-59.91      60.72      54.63      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-62.83      54.85      54.63      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-62.47      62.13      54.63      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-625.82     667.05     425.55     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-508.92     667.04     373.14     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-147.19     146.62     146.31     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-143.70     155.87     139.90     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-214.87     214.19     213.21     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-212.90     212.93     209.55     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-1690.06    2303.34    1480.63    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-1489.54    1435.48    1308.12    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-90.49      89.23      86.83      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-356.63     357.29     354.42     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-217.52     229.39     101.61     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-198.63     198.25     196.68     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-417.23     434.54     388.38     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-381.72     394.15     308.62     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-194.47     195.18     191.67     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+6.23       6.27       6.18       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+6.68       6.73       6.18       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+68.82      69.06      68.45      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+87.42      89.84      68.45      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+27.81      27.77      27.67      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+35.71      36.67      27.67      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+42.58      42.41      42.25      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+46.49      46.95      42.25      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+71.35      71.62      70.78      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+73.81      74.23      70.78      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+64.20      64.30      63.98      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+57.91      58.41      52.53      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+61.35      52.83      52.53      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+61.49      61.28      52.53      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+420.93     420.73     419.04     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+410.96     395.74     364.68     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+153.87     152.71     140.85     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+157.86     145.90     140.85     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+214.59     211.95     210.98     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+215.09     238.39     208.18     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+1614.13    1639.80    1476.58    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+1597.92    1599.12    1476.58    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+48.55      46.87      41.75      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+97.05      95.40      80.93      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+112.39     116.22     80.93      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+105.60     113.27     88.55      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+478.89     498.05     444.14     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+442.56     477.87     369.59     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+116.15     120.13     106.81     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
 5.90       5.90       5.81       [100, 100]   WeChatQRCode with ['detect_2021nov.prototxt', 'detect_2021nov.caffemodel', 'sr_2021nov.prototxt', 'sr_2021nov.caffemodel']
-462.50     463.67     456.98     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-462.97     464.33     456.98     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-470.79     464.35     456.98     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-481.71     479.50     456.98     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-237.73     237.57     236.82     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-265.16     270.22     236.82     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-239.69     298.68     198.88     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-234.90     249.29     198.88     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-227.47     200.42     198.88     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-226.39     213.26     198.88     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-226.10     227.18     198.88     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-220.63     217.04     193.47     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+325.02     325.88     303.55     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+323.54     332.45     303.55     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+372.32     328.56     303.55     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+407.90     411.97     303.55     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+235.70     236.07     234.87     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+240.95     241.14     234.87     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+226.09     247.02     200.44     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+229.25     224.63     200.44     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+224.10     201.29     200.44     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+223.58     219.82     200.44     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+225.60     243.89     200.44     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+220.97     223.16     193.91     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 ### Jetson Nano B01
@@ -187,48 +187,48 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-5.64       5.55       5.50       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-5.91       6.00       5.50       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-61.32      61.38      61.08      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-76.85      78.69      61.08      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-27.39      27.54      27.26      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-34.69      35.62      27.26      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-50.39      50.31      50.22      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-48.97      49.42      47.46      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-68.07      67.81      67.72      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-73.97      74.83      67.72      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-63.85      63.63      63.51      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-55.14      55.93      47.84      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-60.80      48.09      47.84      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-60.99      61.22      47.84      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-352.73     352.51     351.53     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-374.22     376.71     351.53     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-134.60     135.00     133.68     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-137.10     137.32     133.68     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-215.10     215.30     214.30     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-216.18     216.19     214.30     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-1207.83    1208.71    1203.64    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-1236.98    1250.21    1203.64    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-123.30     125.37     116.69     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-124.89     125.25     124.53     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-107.99     109.82     94.05      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-108.41     108.33     107.91     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-354.88     354.70     354.34     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-343.35     344.56     333.41     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-89.93      91.58      88.28      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-5.69       5.72       5.66       [100, 100]   WeChatQRCode with ['detect_2021nov.prototxt', 'detect_2021nov.caffemodel', 'sr_2021nov.prototxt', 'sr_2021nov.caffemodel']
-238.89     238.22     236.97     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-238.41     240.39     236.97     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-276.96     240.19     236.97     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-304.04     311.21     236.97     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-258.11     258.13     257.64     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-275.27     277.20     257.64     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-254.90     295.88     221.12     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-252.73     258.90     221.12     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-245.08     222.01     221.12     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-245.75     236.58     221.12     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-248.42     251.65     221.12     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-244.31     236.64     221.12     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+5.62       5.54       5.52       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+6.14       6.24       5.52       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+64.80      64.95      64.60      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+78.31      79.85      64.60      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+26.54      26.61      26.37      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+33.96      34.85      26.37      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+38.45      41.45      38.20      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+42.62      43.20      38.20      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+64.95      64.85      64.73      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+72.39      73.16      64.73      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+65.72      65.98      65.59      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+56.66      57.56      49.10      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+62.09      49.27      49.10      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+62.17      62.02      49.10      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+346.78     348.06     345.53     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+371.11     373.54     345.53     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+134.36     134.33     133.45     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+140.62     140.94     133.45     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+215.67     216.76     214.69     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+216.58     216.78     214.69     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+1209.12    1213.05    1201.68    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+1240.02    1249.95    1201.68    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+48.39      47.38      45.00      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+75.30      75.25      74.96      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+83.83      84.99      74.96      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+87.65      87.59      87.37      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+356.78     357.77     355.69     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+346.84     351.10     335.96     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+75.20      79.36      73.71      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+5.56       5.56       5.48       [100, 100]   WeChatQRCode with ['detect_2021nov.prototxt', 'detect_2021nov.caffemodel', 'sr_2021nov.prototxt', 'sr_2021nov.caffemodel']
+209.80     210.04     208.84     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+209.60     212.74     208.49     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+254.56     211.17     208.49     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+286.57     296.56     208.49     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+252.60     252.48     252.21     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+259.28     261.38     252.21     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+245.18     266.94     220.49     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+247.72     244.25     220.49     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+241.63     221.43     219.06     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+243.46     238.98     219.06     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+246.87     256.05     219.06     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+243.37     238.90     219.06     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 GPU (CUDA-FP32):
@@ -239,29 +239,27 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_CUDA
 target=cv.dnn.DNN_TARGET_CUDA
 mean       median     min        input size   model
-11.16      10.31      10.23      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-24.82      24.90      24.33      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-14.39      14.44      13.83      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-24.52      24.01      23.84      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-69.63      69.88      64.73      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-29.06      29.10      28.80      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-28.54      28.57      27.88      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-99.05      99.65      93.60      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-54.24      55.24      52.87      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-63.63      63.43      63.32      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-371.45     378.00     366.39     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-43.06      42.32      39.92      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-33.85      33.90      33.61      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-38.16      37.33      37.10      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-91.65      91.98      89.90      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-91.40      92.74      89.76      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-112.35     111.90     109.99     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-112.68     114.63     109.93     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-183.96     112.72     109.93     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-234.57     249.45     109.93     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-44.24      45.21      41.87      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-45.15      44.15      41.87      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-36.82      46.54      21.75      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+10.99      10.71      9.64       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+25.25      25.81      24.54      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+13.97      14.01      13.72      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+24.47      24.36      23.69      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+67.25      67.99      64.90      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+28.96      28.92      28.85      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+28.61      28.45      27.92      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+98.80      100.11     94.57      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+54.88      56.51      52.78      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+63.86      63.59      63.35      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+371.32     374.79     367.78     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+47.26      45.56      44.69      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+37.61      37.61      33.64      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+37.39      37.71      37.03      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+90.84      91.34      85.77      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+76.44      78.00      74.90      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+112.68     112.21     110.42     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+112.48     111.86     110.04     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+43.99      43.33      41.68      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+44.97      44.42      41.68      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+36.77      46.38      21.77      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
 ```
 
 GPU (CUDA-FP16):
@@ -272,29 +270,27 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_CUDA
 target=cv.dnn.DNN_TARGET_CUDA_FP16
 mean       median     min        input size   model
-25.41      25.43      25.31      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-113.14     112.02     111.74     [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-89.04      88.90      88.59      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-96.62      96.39      96.26      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-69.78      70.65      66.74      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-118.47     118.45     118.10     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-125.69     126.63     118.10     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-64.08      62.97      62.33      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-366.46     366.88     363.46     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-163.06     163.34     161.77     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-301.10     311.52     297.74     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-43.36      40.65      39.85      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-149.37     149.95     148.01     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-153.89     153.96     153.43     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-44.29      44.03      43.62      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-91.28      92.89      89.79      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-427.53     428.67     425.63     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-427.79     429.28     425.63     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-414.07     429.46     387.26     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-406.10     407.83     383.41     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-33.07      32.88      32.00      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-33.88      33.64      32.00      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-29.32      33.70      20.69      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+25.05      25.05      24.95      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+117.82     126.96     113.17     [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+88.54      88.33      88.04      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+97.43      97.38      96.98      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+69.40      68.28      66.36      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+120.92     131.57     119.37     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+128.43     128.08     119.37     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+64.90      63.88      62.81      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+370.21     371.97     366.38     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+164.28     164.75     162.94     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+299.22     300.54     295.64     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+49.61      47.58      47.14      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+149.50     151.12     147.24     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+156.59     154.01     153.92     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+43.66      43.64      43.31      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+75.87      77.33      74.38      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+428.97     428.99     426.11     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+428.66     427.46     425.66     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+32.41      31.90      31.68      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+33.42      35.75      31.68      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+29.34      36.44      21.27      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
 ```
 
 ### Khadas VIM3
@@ -304,82 +300,82 @@ Specs: [details](https://www.khadas.com/vim3)
 - NPU: 5 TOPS Performance NPU INT8 inference up to 1536 MAC Supports all major deep learning frameworks including TensorFlow and Caffe 
 
 CPU:
-
+<!-- config wechat is excluded due to it needs building with opencv_contrib -->
 ```
-$ python3 benchmark.py --all
+$ python3 benchmark.py --all --cfg_exclude wechat
 Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-4.60       4.57       4.47       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-5.10       5.15       4.47       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-53.88      52.80      51.99      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-67.86      67.67      51.99      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-40.93      41.29      27.33      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-42.81      56.31      27.33      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-58.84      56.15      53.14      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-56.36      60.14      45.29      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-76.53      67.95      65.13      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-72.25      69.88      65.13      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-66.50      64.06      58.56      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-59.10      75.36      45.69      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-62.44      48.81      45.69      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-60.46      54.93      45.69      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-372.65     404.31     326.91     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-359.72     336.21     326.91     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-145.21     125.62     124.87     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-130.10     139.45     116.10     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-218.21     216.01     199.88     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-212.69     262.75     170.88     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-1110.87    1112.27    1085.31    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-1128.73    1157.12    1085.31    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-67.31      67.41      66.23      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-147.01     144.01     139.27     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-119.70     118.95     94.09      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-107.63     107.09     105.61     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-333.03     346.65     322.37     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-322.95     315.22     303.07     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-127.16     173.93     99.77      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-238.38     241.90     233.21     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-238.05     236.53     232.05     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-262.58     238.47     232.05     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-280.63     279.26     232.05     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-194.80     195.37     192.65     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-209.49     208.33     192.65     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-192.90     227.02     161.94     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-192.52     197.03     161.94     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-185.92     168.22     161.94     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-185.01     183.14     161.94     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-186.09     194.14     161.94     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-181.79     181.65     154.21     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+4.62       4.62       4.53       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+5.24       5.29       4.53       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+55.04      54.55      53.54      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+67.34      67.96      53.54      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+29.50      45.62      26.14      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+35.59      36.22      26.14      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+35.80      35.08      34.76      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+40.32      45.32      34.76      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+71.92      66.92      62.98      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+70.68      72.31      62.98      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+59.27      53.91      52.09      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+52.17      67.58      41.23      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+55.44      47.28      41.23      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+55.83      56.80      41.23      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+335.75     329.39     325.42     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+340.42     335.78     325.42     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+128.58     127.15     124.03     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+125.85     126.47     110.14     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+179.93     170.66     166.76     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+178.61     213.72     164.61     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+1108.12    1100.93    1072.45    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+1100.58    1121.31    982.74     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+32.20      32.84      30.99      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+78.26      78.96      75.60      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+87.18      88.22      75.60      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+83.22      84.20      80.07      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+327.07     339.80     321.98     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+316.56     302.60     269.10     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+75.38      73.67      70.15      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+211.02     213.14     199.28     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+210.19     217.15     199.28     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+242.34     225.59     199.28     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+265.33     271.87     199.28     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+194.77     195.13     192.69     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+197.16     200.94     192.69     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+185.45     199.47     161.37     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+187.64     180.57     161.37     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+182.53     166.96     161.37     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+182.90     178.97     161.37     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+184.26     194.43     161.37     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+180.65     180.59     155.36     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 NPU (TIMVX):
-<!-- config face_detection and licence_plate are excluded due to https://github.com/opencv/opencv_zoo/pull/190#discussion_r1257832066 -->
+
 ```
-$ python3 benchmark.py --all --int8 --cfg_overwrite_backend_target 3 --cfg_exclude face_detection:license_plate
+$ python3 benchmark.py --all --int8 --cfg_overwrite_backend_target 3
 Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_TIMVX
 target=cv.dnn.DNN_TARGET_NPU
 mean       median     min        input size   model
-5.08       4.72       4.70       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-45.83      47.06      43.04      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-29.20      27.55      26.25      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-18.47      18.16      17.96      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-28.25      28.35      27.98      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-149.05     155.10     144.42     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-147.40     147.49     135.90     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-75.91      79.27      71.98      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-30.98      30.56      29.36      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-117.71     119.69     107.37     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-379.46     366.19     360.02     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-33.90      36.32      31.71      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-40.34      41.50      38.47      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-162.54     162.78     155.24     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-161.50     160.70     147.69     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-239.68     239.31     236.03     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-199.42     203.20     166.15     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-197.49     169.51     166.15     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+5.24       7.45       4.77       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+45.96      46.10      43.21      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+30.25      30.30      28.68      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+19.75      20.18      18.19      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+28.75      28.85      28.47      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+148.80     148.85     143.45     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+143.17     141.11     136.58     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+73.19      78.57      62.89      [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+32.11      30.50      29.97      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+116.32     120.72     99.40      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+408.18     418.89     374.12     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+37.34      38.57      32.03      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+41.82      39.84      37.63      [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+160.70     160.90     153.15     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+160.47     160.48     151.88     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+239.38     237.47     231.95     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+197.61     201.16     162.69     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+196.69     164.78     162.69     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 ### Atlas 200 DK
@@ -479,47 +475,47 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-56.45      56.29      56.18      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-48.83      49.41      41.52      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-1554.78    1545.63    1523.62    [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-1215.44    1251.08    921.26     [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-612.58     613.61     587.83     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-502.02     513.29     399.51     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-525.72     532.34     502.00     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-415.87     442.23     318.14     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-1631.40    1635.83    1608.43    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-1115.29    1159.60    675.51     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-1546.54    1547.64    1516.69    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-1163.10    1227.05    816.99     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-980.56     852.38     689.31     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-837.72     778.61     507.03     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-11819.74   11778.79   11758.31   [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-7742.66    8151.17    4442.93    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-3266.08    3250.08    3216.03    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-2260.88    2368.00    1437.58    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-2335.65    2342.12    2304.69    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-1903.82    1962.71    1533.79    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-37604.10   37569.30   37502.48   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-24229.20   25577.94   13483.54   [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-415.72     403.04     399.44     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-1133.44    1131.54    1124.83    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-883.96     919.07     655.33     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-1430.98    1424.55    1415.68    [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-11131.81   11141.37   11080.20   [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-7065.00    7461.37    3748.85    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-790.98     823.19     755.99     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-4422.65    4432.92    4376.19    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-4407.88    4405.92    4353.22    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-3782.89    4404.01    2682.63    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-3472.93    3557.78    2682.63    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-2183.70    2172.36    2156.29    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-2225.19    2222.58    2156.29    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-2214.03    2302.61    2156.29    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-2203.45    2231.47    2150.19    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-2201.14    2188.00    2150.19    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-2029.28    2178.36    1268.17    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-1923.12    2219.63    1268.17    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-1818.21    2196.98    1184.98    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+56.78      56.74      56.46      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+51.16      51.41      45.18      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+1737.74    1733.23    1723.65    [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+1298.48    1336.02    920.44     [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+609.51     611.79     584.89     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+500.21     517.38     399.97     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+465.12     471.89     445.36     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+389.95     385.01     318.29     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+10.16.66.1781623.94    1607.90    1595.09    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+1109.61    1186.03    671.15     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+1567.09    1578.61    1542.75    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+1188.83    1219.46    850.92     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+996.30     884.80     689.11     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+849.51     805.93     507.78     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+11855.64   11836.80   11750.10   [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+7752.60    8149.00    4429.83    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+3260.22    3251.14    3204.85    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+2287.10    2400.53    1482.04    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+2335.89    2335.93    2313.63    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+1899.16    1945.72    1529.46    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+37600.81   37558.85   37414.98   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+24185.35   25519.27   13395.47   [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+411.41     448.29     397.86     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+905.77     890.22     866.06     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+780.94     817.69     653.26     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+1315.48    1321.44    1299.68    [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+11143.23   11155.05   11105.11   [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+7056.60    7457.76    3753.42    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+736.02     732.90     701.14     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+4267.03    4288.42    4229.69    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+4265.58    4276.54    4222.22    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+3678.65    4265.95    2636.57    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+3383.73    3490.66    2636.57    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+2180.44    2197.45    2152.67    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+2217.08    2241.77    2152.67    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+2217.15    2251.65    2152.67    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+2206.73    2219.60    2152.63    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+2208.84    2219.14    2152.63    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+2035.98    2185.05    1268.94    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+1927.93    2178.84    1268.94    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+1822.23    2213.30    1183.93    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 ### Khadas Edge2 (with RK3588)
@@ -537,47 +533,47 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-2.29       2.30       2.25       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-2.62       2.64       2.25       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-28.19      28.12      28.01      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-36.68      37.80      28.01      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-12.56      12.55      12.50      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-17.28      17.83      12.50      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-22.74      22.87      22.43      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-24.56      24.61      22.43      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-29.91      30.23      28.16      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-35.54      35.46      28.16      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-27.28      27.20      27.20      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-22.91      23.33      19.28      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-27.36      19.46      19.28      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-28.28      29.17      19.28      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-150.06     150.89     147.05     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-180.91     184.75     147.05     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-54.14      52.95      49.31      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-60.01      61.20      49.31      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-117.60     128.98     83.33      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-117.28     150.31     83.33      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-553.58     558.76     535.47     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-594.18     592.64     535.47     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-49.47      49.21      48.84      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-56.35      55.73      55.25      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-57.07      57.19      55.25      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-47.94      48.41      47.05      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-146.02     145.89     139.08     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-157.60     158.88     139.08     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-41.26      42.74      40.08      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-110.51     111.04     107.73     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-110.67     111.54     107.73     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-131.52     111.76     107.73     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-146.42     149.47     107.73     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-68.70      68.63      68.54      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-78.17      80.48      68.54      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-71.42      91.44      61.14      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-70.07      76.28      61.14      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-67.69      61.72      61.14      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-68.29      65.04      61.14      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-69.58      68.63      61.14      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-68.99      65.02      61.14      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+2.30       2.29       2.26       [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+2.70       2.73       2.26       [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+28.94      29.00      28.60      [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+37.46      38.85      28.60      [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+12.44      12.40      12.36      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+17.14      17.64      12.36      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+20.22      20.36      20.08      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+23.11      23.50      20.08      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+29.63      29.78      28.61      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+35.57      35.61      28.61      [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+27.45      27.46      27.25      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+22.95      23.37      19.13      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+27.50      19.40      19.13      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+28.46      29.33      19.13      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+151.10     151.79     146.96     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+181.69     184.19     146.96     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+53.83      52.64      50.24      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+60.95      60.06      50.24      [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+98.03      104.53     83.47      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+106.91     110.68     83.47      [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+554.30     550.32     538.99     [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+591.95     599.62     538.99     [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+14.02      13.89      13.56      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+45.03      44.65      43.28      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+50.87      52.24      43.28      [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+42.90      42.68      42.40      [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+148.01     146.42     139.56     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+159.16     155.98     139.56     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+37.06      37.43      36.39      [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+103.42     104.24     101.26     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+103.41     104.41     100.08     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+126.21     103.90     100.08     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+142.53     147.66     100.08     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+69.49      69.52      69.17      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+70.63      70.69      69.17      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+67.15      72.03      61.13      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+67.74      66.72      61.13      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+66.26      61.46      61.13      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+67.36      65.65      61.13      [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+68.52      69.93      61.13      [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+68.36      65.65      61.13      [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 ### Horizon Sunrise X3 PI
@@ -594,48 +590,48 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-10.15      10.07      10.04      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-11.27      11.40      10.04      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-116.44     116.29     116.15     [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-158.75     164.22     116.15     [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-55.42      55.80      55.27      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-76.04      78.44      55.27      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-91.39      95.06      90.66      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-95.54      95.39      90.66      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-135.16     134.82     134.75     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-148.05     149.55     134.75     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-115.69     115.73     115.38     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-99.37      100.71     85.65      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-111.02     85.94      85.65      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-112.94     112.72     85.65      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-641.92     643.42     640.64     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-700.42     708.18     640.64     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-251.52     250.97     250.36     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-261.00     280.82     250.36     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-395.23     398.77     385.68     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-406.28     416.58     385.68     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-2608.90    2612.42    2597.93    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-2609.88    2609.39    2597.93    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-189.23     188.72     182.28     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-228.95     228.74     228.35     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-227.97     228.61     226.76     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-192.29     192.26     191.74     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-660.62     662.28     659.49     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-646.25     647.89     631.03     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-182.57     185.52     179.71     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+10.56      10.69      10.46      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+12.45      12.60      10.46      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+124.80     127.36     124.45     [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+168.67     174.03     124.45     [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+55.12      55.38      54.91      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+76.31      79.00      54.91      [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+77.44      77.53      77.07      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+89.22      90.40      77.07      [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+132.95     133.21     132.35     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+147.40     149.99     132.35     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+119.71     120.69     119.32     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+102.57     104.40     88.49      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+114.56     88.81      88.49      [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+117.12     116.07     88.49      [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+653.39     653.85     651.99     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+706.43     712.61     651.99     [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+252.05     252.16     250.98     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+273.03     274.27     250.98     [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+399.35     405.40     390.82     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+413.37     410.75     390.82     [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+2516.91    2516.82    2506.54    [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+2544.65    2551.55    2506.54    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+84.15      85.18      77.31      [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+168.54     169.05     168.15     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+196.46     199.81     168.15     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+172.55     172.83     171.85     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+678.74     678.04     677.44     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+653.71     655.74     631.68     [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+162.87     165.82     160.04     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
 9.93       9.97       9.82       [100, 100]   WeChatQRCode with ['detect_2021nov.prototxt', 'detect_2021nov.caffemodel', 'sr_2021nov.prototxt', 'sr_2021nov.caffemodel']
-495.04     493.75     489.41     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-493.63     491.89     489.41     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-598.94     496.42     489.41     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-667.75     683.91     489.41     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-439.96     441.91     436.49     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-465.56     466.86     436.49     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-431.93     495.94     373.61     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-432.47     435.40     373.61     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-418.75     375.76     373.61     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-421.81     410.25     373.61     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-429.30     437.71     373.61     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-422.15     406.50     373.61     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+475.98     475.34     472.72     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+475.90     477.57     472.44     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+585.72     475.98     472.44     [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+663.34     687.10     472.44     [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+446.82     445.92     444.32     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+453.60     456.07     444.32     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+427.47     463.88     381.10     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+432.15     421.18     381.10     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+420.61     386.28     380.35     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+425.24     426.69     380.35     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+431.14     447.85     380.35     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+424.77     417.01     380.35     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 ### MAIX-III AX-PI
@@ -653,47 +649,47 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-83.67      83.60      83.50      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-76.45      77.17      70.53      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-2102.93    2102.75    2102.23    [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-1846.25    1872.36    1639.46    [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-825.27     825.74     824.83     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-752.57     759.68     693.90     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-742.35     742.87     741.42     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-630.16     641.82     539.73     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-2190.53    2188.01    2187.75    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-1662.81    1712.08    1235.22    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-2099.43    2099.39    2098.89    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-1589.86    1641.45    1181.62    [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-1451.24    1182.16    1181.62    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-1277.21    1224.66    888.62     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-15832.31   15832.41   15830.59   [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-11649.30   12067.68   8300.79    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-4376.55    4398.44    4371.68    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-3376.78    3480.89    2574.72    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-3422.70    3414.45    3413.72    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-3002.36    3047.94    2655.38    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-50678.08   50651.82   50651.19   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-36249.71   37771.22   24606.37   [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-707.79     706.32     699.40     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-1502.15    1501.98    1500.99    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-1300.15    1320.44    1137.60    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-1993.05    1993.98    1991.86    [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-14925.56   14926.90   14912.28   [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-10507.96   10944.15   6974.74    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-1113.51    1124.83    1106.81    [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-6094.40    6093.77    6091.85    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-6073.33    6076.77    6055.13    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-5547.32    6057.15    4653.05    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-5284.79    5356.47    4653.05    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-3230.93    3228.61    3228.29    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-3312.02    3323.17    3228.29    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-3262.32    3413.03    3182.11    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-3250.66    3298.06    3182.11    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-3231.37    3185.37    3179.37    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-3064.17    3213.91    2345.80    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-2975.21    3227.38    2345.80    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-2862.33    3212.57    2205.48    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+83.95      83.76      83.62      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+79.35      79.92      75.47      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+2326.96    2326.49    2326.08    [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+1950.83    1988.86    1648.47    [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+823.42     823.35     822.50     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+750.31     757.91     691.41     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+664.73     664.61     663.84     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+596.29     603.96     540.72     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+2175.34    2173.62    2172.91    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+1655.11    1705.43    1236.22    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+2123.08    2122.92    2122.18    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+1619.08    1672.32    1215.05    [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+1470.74    1216.86    1215.05    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+1287.09    1242.01    873.92     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+15841.89   15841.20   15828.32   [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+11652.03   12079.50   8299.15    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+4371.75    4396.81    4370.29    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+3428.89    3521.87    2670.46    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+3421.19    3412.22    3411.20    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+2990.22    3034.11    2645.09    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+50633.38   50617.44   50614.78   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+36260.23   37731.28   24683.40   [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+548.36     551.97     537.90     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+1285.54    1285.40    1284.43    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+1204.04    1211.89    1137.65    [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+1849.87    1848.78    1847.80    [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+14895.99   14894.27   14884.17   [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+10496.44   10931.97   6976.60    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+1045.98    1052.05    1040.56    [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+5899.23    5900.08    5896.73    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+5889.39    5890.58    5878.81    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+5436.61    5884.03    4665.77    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+5185.53    5273.76    4539.47    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+3230.95    3226.14    3225.53    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+3281.31    3295.46    3225.53    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+3247.56    3337.52    3196.25    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+3243.20    3276.35    3196.25    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+3230.49    3196.80    3195.02    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+3065.33    3217.99    2348.42    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+2976.24    3244.75    2348.42    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+2864.72    3219.46    2208.44    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 ### StarFive VisionFive 2
@@ -710,47 +706,47 @@ Benchmarking ...
 backend=cv.dnn.DNN_BACKEND_OPENCV
 target=cv.dnn.DNN_TARGET_CPU
 mean       median     min        input size   model
-41.10      41.09      41.04      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
-35.87      36.37      31.62      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
-1050.45    1050.38    1050.01    [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
-832.25     854.08     657.41     [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
-425.36     425.42     425.19     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
-351.86     372.26     292.72     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
-348.67     347.98     347.67     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
-290.95     297.03     243.79     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
-1135.09    1135.25    1134.72    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
-788.33     822.69     509.67     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
-1065.61    1065.99    1065.30    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
-805.26     830.66     595.78     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
-687.98     609.35     514.14     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
-592.59     555.25     381.33     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
-8091.50    8090.44    8088.72    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
-5394.46    5666.14    3235.23    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
-2270.14    2270.29    2267.51    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
-1584.83    1656.13    1033.23    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
-1732.53    1732.14    1731.47    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
-1434.56    1463.32    1194.57    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
-26172.62   26160.04   26151.67   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
-17004.06   17909.88   9659.54    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
-304.58     309.56     280.05     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
-734.97     735.58     733.95     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
-609.61     621.69     508.04     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
-961.41     962.26     960.39     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
-7594.21    7590.75    7589.16    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
-4884.04    5154.38    2715.94    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
-548.41     550.86     546.09     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
-3031.81    3031.79    3030.41    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
-3031.41    3031.17    3029.99    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
-2638.47    3031.01    1969.10    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
-2446.99    2500.65    1967.72    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
-1397.09    1396.95    1396.74    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
-1428.65    1432.59    1396.74    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
-1429.56    1467.34    1396.74    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
-1419.29    1450.55    1395.55    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
-1421.72    1434.46    1395.55    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
-1307.27    1415.63    807.66     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
-1237.00    1395.68    807.66     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
-1169.59    1415.29    774.09     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
+41.13      41.07      41.06      [160, 120]   YuNet with ['face_detection_yunet_2023mar.onnx']
+37.43      37.83      34.35      [160, 120]   YuNet with ['face_detection_yunet_2023mar_int8.onnx']
+1169.96    1169.72    1168.74    [150, 150]   SFace with ['face_recognition_sface_2021dec.onnx']
+887.13     987.00     659.71     [150, 150]   SFace with ['face_recognition_sface_2021dec_int8.onnx']
+423.91     423.98     423.62     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx']
+350.89     358.26     292.27     [112, 112]   FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx']
+319.69     319.26     318.76     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx']
+278.74     282.75     245.22     [224, 224]   MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx']
+1127.61    1127.36    1127.17    [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx']
+785.44     819.07     510.77     [192, 192]   PPHumanSeg with ['human_segmentation_pphumanseg_2023mar_int8.onnx']
+1079.69    1079.66    1079.31    [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr.onnx']
+820.15     845.54     611.26     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr.onnx']
+698.13     612.64     516.41     [224, 224]   MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx']
+600.12     564.13     382.59     [224, 224]   MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx']
+8116.21    8127.96    8113.70    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan.onnx']
+5408.02    5677.71    3240.16    [224, 224]   PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx']
+2267.96    2268.26    2266.59    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx']
+1605.80    1671.91    1073.50    [320, 240]   LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar_int8.onnx']
+1731.61    1733.17    1730.54    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov.onnx']
+1435.43    1477.52    1196.01    [416, 416]   NanoDet with ['object_detection_nanodet_2022nov_int8.onnx']
+26185.41   26190.85   26168.68   [640, 640]   YoloX with ['object_detection_yolox_2022nov.onnx']
+17019.14   17923.20   9673.68    [640, 640]   YoloX with ['object_detection_yolox_2022nov_int8.onnx']
+288.95     290.28     260.40     [1280, 720]  VitTrack with ['object_tracking_vittrack_2023sep.onnx']
+628.64     628.47     628.27     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx']
+562.90     569.91     509.93     [192, 192]   MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx']
+910.38     910.94     909.64     [224, 224]   MPPersonDet with ['person_detection_mediapipe_2023mar.onnx']
+7613.64    7626.26    7606.07    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov.onnx']
+4895.28    5166.85    2716.65    [128, 256]   YoutuReID with ['person_reid_youtu_2021nov_int8.onnx']
+524.52     526.33     522.71     [256, 256]   MPPose with ['pose_estimation_mediapipe_2023mar.onnx']
+2988.22    2996.51    2980.17    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may.onnx']
+2981.84    2979.74    2975.80    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may.onnx']
+2610.78    2979.14    1979.37    [640, 480]   PPOCRDet with ['text_detection_cn_ppocrv3_2023may_int8.onnx']
+2425.29    2478.92    1979.37    [640, 480]   PPOCRDet with ['text_detection_en_ppocrv3_2023may_int8.onnx']
+1404.01    1415.46    1401.36    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2021sep.onnx']
+1425.42    1426.51    1401.36    [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov.onnx']
+1432.21    1450.47    1401.36    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2021sep.onnx']
+1425.24    1448.27    1401.36    [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2023feb_fp16.onnx']
+1428.84    1446.76    1401.36    [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2023feb_fp16.onnx']
+1313.68    1427.46    808.70     [1280, 720]  CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx']
+1242.07    1408.93    808.70     [1280, 720]  CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx']
+1174.32    1426.07    774.78     [1280, 720]  CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx']
 ```
 
 ### Khadas VIM4

benchmark/benchmark.py

@@ -9,7 +9,7 @@ from models import MODELS
 from utils import METRICS, DATALOADERS
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python for benchmark: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

benchmark/table_config.yaml

@@ -75,14 +75,14 @@ Models:
 
   - name: "CRNN-EN"
     task: "Text Recognition"
-    input_size: "100*32"
+    input_size: "100x32"
     folder: "text_recognition_crnn"
     acceptable_time: 2000
     keyword: "text_recognition_CRNN_EN"
 
   - name: "CRNN-CN"
     task: "Text Recognition"
-    input_size: "100*32"
+    input_size: "100x32"
     folder: "text_recognition_crnn"
     acceptable_time: 2000
     keyword: "text_recognition_CRNN_CN"
@@ -170,28 +170,24 @@ Devices:
     display_info: "Intel\n12700K\nCPU"
     platform: "CPU"
 
-  - name: "Rasberry Pi 4B"
-    display_info: "Rasberry Pi 4B\nBCM2711\nCPU"
-    platform: "CPU"
-
-  - name: "StarFive VisionFive 2"
-    display_info: "StarFive VisionFive 2\nStarFive JH7110\nCPU"
+  - name: "Khadas VIM3"
+    display_info: "Khadas VIM3\nA311D\nCPU"
     platform: "CPU"
 
-  - name: "Toybrick RV1126"
-    display_info: "Toybrick\nRV1126\nCPU"
+  - name: "Khadas VIM4"
+    display_info: "Khadas VIM4\nA311D2\nCPU"
     platform: "CPU"
 
   - name: "Khadas Edge2 (with RK3588)"
     display_info: "Khadas Edge2\nRK3588S\nCPU"
     platform: "CPU"
 
-  - name: "Horizon Sunrise X3 PI"
-    display_info: "Horizon Sunrise Pi\nX3\nCPU"
+  - name: "Atlas 200 DK"
+    display_info: "Atlas 200 DK\nAscend 310\nCPU"
     platform: "CPU"
 
-  - name: "MAIX-III AX-PI"
-    display_info: "MAIX-III AX-Pi\nAX620A\nCPU"
+  - name: "Atlas 200I DK A2"
+    display_info: "Atlas 200I DK A2\nAscend 310B\nCPU"
     platform: "CPU"
 
   - name: "Jetson Nano B01"
@@ -202,20 +198,24 @@ Devices:
     display_info: "Jetson Nano\nOrin\nCPU"
     platform: "CPU"
 
-  - name: "Khadas VIM3"
-    display_info: "Khadas VIM3\nA311D\nCPU"
+  - name: "Raspberry Pi 4B"
+    display_info: "Raspberry Pi 4B\nBCM2711\nCPU"
     platform: "CPU"
 
-  - name: "Khadas VIM4"
-    display_info: "Khadas VIM4\nA311D2\nCPU"
+  - name: "Horizon Sunrise X3 PI"
+    display_info: "Horizon Sunrise Pi\nX3\nCPU"
     platform: "CPU"
 
-  - name: "Atlas 200 DK"
-    display_info: "Atlas 200 DK\nAscend 310\nCPU"
+  - name: "MAIX-III AX-PI"
+    display_info: "MAIX-III AX-Pi\nAX620A\nCPU"
     platform: "CPU"
 
-  - name: "Atlas 200I DK A2"
-    display_info: "Atlas 200I DK A2\nAscend 310B\nCPU"
+  - name: "Toybrick RV1126"
+    display_info: "Toybrick\nRV1126\nCPU"
+    platform: "CPU"
+
+  - name: "StarFive VisionFive 2"
+    display_info: "StarFive VisionFive 2\nStarFive JH7110\nCPU"
     platform: "CPU"
 
   - name: "Jetson Nano B01"
@@ -243,4 +243,4 @@ Suffixes:
   - model: "MobileNet-V2"
     device: "Khadas VIM3"
     platform: "NPU (TIMVX)"
-    str: "\\*"
+    str: "\\*"

models/face_detection_yunet/CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.24.0)
 project(opencv_zoo_face_detection_yunet)
 
-set(OPENCV_VERSION "4.8.0")
+set(OPENCV_VERSION "4.9.0")
 set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
 
 # Find OpenCV

models/face_detection_yunet/demo.py

@@ -12,7 +12,7 @@ import cv2 as cv
 from yunet import YuNet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/face_recognition_sface/demo.py

@@ -16,7 +16,7 @@ sys.path.append('../face_detection_yunet')
 from yunet import YuNet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/facial_expression_recognition/demo.py

@@ -12,7 +12,7 @@ sys.path.append('../face_detection_yunet')
 from yunet import YuNet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/handpose_estimation_mediapipe/demo.py

@@ -10,7 +10,7 @@ sys.path.append('../palm_detection_mediapipe')
 from mp_palmdet import MPPalmDet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/human_segmentation_pphumanseg/demo.py

@@ -12,7 +12,7 @@ import cv2 as cv
 from pphumanseg import PPHumanSeg
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/image_classification_mobilenet/CMakeLists.txt

@@ -3,7 +3,7 @@ set(project_name "opencv_zoo_image_classification_mobilenet")
 
 PROJECT (${project_name})
 
-set(OPENCV_VERSION "4.8.0")
+set(OPENCV_VERSION "4.9.0")
 set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
 find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
 # Find OpenCV, you may need to set OpenCV_DIR variable

models/image_classification_mobilenet/demo.py

@@ -6,7 +6,7 @@ import cv2 as cv
 from mobilenet import MobileNet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/image_classification_ppresnet/demo.py

@@ -12,7 +12,7 @@ import cv2 as cv
 from ppresnet import PPResNet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/license_plate_detection_yunet/demo.py

@@ -6,7 +6,7 @@ import cv2 as cv
 from lpd_yunet import LPD_YuNet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/object_detection_nanodet/demo.py

@@ -5,7 +5,7 @@ import argparse
 from nanodet import NanoDet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/object_detection_yolox/CMakeLists.txt

@@ -3,7 +3,7 @@ set(project_name "opencv_zoo_object_detection_yolox")
 
 PROJECT (${project_name})
 
-set(OPENCV_VERSION "4.7.0")
+set(OPENCV_VERSION "4.9.0")
 set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
 find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
 # Find OpenCV, you may need to set OpenCV_DIR variable

models/object_detection_yolox/demo.py

@@ -5,7 +5,7 @@ import argparse
 from yolox import YoloX
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/object_tracking_vittrack/demo.py

@@ -6,11 +6,10 @@ import argparse
 import numpy as np
 import cv2 as cv
 
-
 from vittrack import VitTrack
 
 # Check OpenCV version
-assert cv.__version__ > "4.8.0", \
+assert cv.__version__ > "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/optical_flow_estimation_raft/demo.py

@@ -5,6 +5,10 @@ import numpy as np
 
 from raft import Raft
 
+# Check OpenCV version
+assert cv.__version__ > "4.9.0", \
+       "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
+
 parser = argparse.ArgumentParser(description='RAFT (https://github.com/princeton-vl/RAFT)')
 parser.add_argument('--input1', '-i1', type=str,
                     help='Usage: Set input1 path to first image, omit if using camera or video.')

models/palm_detection_mediapipe/demo.py

@@ -6,7 +6,7 @@ import cv2 as cv
 from mp_palmdet import MPPalmDet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/person_detection_mediapipe/CMakeLists.txt

@@ -3,7 +3,7 @@ set(project_name "opencv_zoo_person_detection_mediapipe")
 
 PROJECT (${project_name})
 
-set(OPENCV_VERSION "4.7.0")
+set(OPENCV_VERSION "4.9.0")
 set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
 find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
 # Find OpenCV, you may need to set OpenCV_DIR variable

models/person_detection_mediapipe/demo.py

@@ -6,7 +6,7 @@ import cv2 as cv
 from mp_persondet import MPPersonDet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/person_reid_youtureid/demo.py

@@ -13,7 +13,7 @@ import cv2 as cv
 from youtureid import YoutuReID
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/pose_estimation_mediapipe/CMakeLists.txt

@@ -3,7 +3,7 @@ set(project_name "opencv_zoo_pose_estimation_mediapipe")
 
 PROJECT (${project_name})
 
-set(OPENCV_VERSION "4.8.0")
+set(OPENCV_VERSION "4.9.0")
 set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
 find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
 # Find OpenCV, you may need to set OpenCV_DIR variable

models/pose_estimation_mediapipe/demo.py

@@ -10,7 +10,7 @@ sys.path.append('../person_detection_mediapipe')
 from mp_persondet import MPPersonDet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/qrcode_wechatqrcode/demo.py

@@ -12,7 +12,7 @@ import cv2 as cv
 from wechatqrcode import WeChatQRCode
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/text_detection_ppocr/CMakeLists.txt

@@ -3,7 +3,7 @@ set(project_name "opencv_zoo_text_detection_ppocr")
 
 PROJECT (${project_name})
 
-set(OPENCV_VERSION "4.8.0")
+set(OPENCV_VERSION "4.9.0")
 set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
 find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
 # Find OpenCV, you may need to set OpenCV_DIR variable

models/text_detection_ppocr/demo.py

@@ -12,7 +12,7 @@ import cv2 as cv
 from ppocr_det import PPOCRDet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

models/text_recognition_crnn/CMakeLists.txt

@@ -3,7 +3,7 @@ set(project_name "opencv_zoo_text_recognition_crnn")
 
 PROJECT (${project_name})
 
-set(OPENCV_VERSION "4.7.0")
+set(OPENCV_VERSION "4.9.0")
 set(OPENCV_INSTALLATION_PATH "" CACHE PATH "Where to look for OpenCV installation")
 find_package(OpenCV ${OPENCV_VERSION} REQUIRED HINTS ${OPENCV_INSTALLATION_PATH})
 # Find OpenCV, you may need to set OpenCV_DIR variable

models/text_recognition_crnn/demo.py

@@ -16,7 +16,7 @@ sys.path.append('../text_detection_ppocr')
 from ppocr_det import PPOCRDet
 
 # Check OpenCV version
-assert cv.__version__ >= "4.8.0", \
+assert cv.__version__ >= "4.9.0", \
        "Please install latest opencv-python to try this demo: python3 -m pip install --upgrade opencv-python"
 
 # Valid combinations of backends and targets

tools/quantize/requirements.txt

@@ -1,4 +1,4 @@
-opencv-python>=4.8.0
+opencv-python>=4.9.0
 onnx
 onnxruntime
 onnxruntime-extensions