diff --git a/README.md b/README.md index 4fecf3eb36b06fca4c21407cd18e0dc6bdf34de3..0ac54a1378d869d3f534da3398af133ad4ec113d 100644 --- a/README.md +++ b/README.md @@ -31,6 +31,7 @@ Hardware Setup: - [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. - [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. +- [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. diff --git a/benchmark/README.md b/benchmark/README.md index 1e14d1493f3f5bc94f444e36a1c454534dc1fbc3..e254b2f74b2e9027352e79437a53eded4b44d88b 100644 --- a/benchmark/README.md +++ b/benchmark/README.md @@ -659,3 +659,55 @@ mean median min input size model 3001.31 3237.93 2353.81 [1280, 720] CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx'] 2887.05 3224.12 2206.89 [1280, 720] CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx'] ``` + +### StarFive VisionFive 2 + +Specs: [details_cn](https://doc.rvspace.org/VisionFive2/PB/VisionFive_2/specification_pb.html), [details_en](https://doc-en.rvspace.org/VisionFive2/Product_Brief/VisionFive_2/specification_pb.html) +- CPU: StarFive JH7110 with RISC-V quad-core CPU with 2 MB L2 cache and a monitor core, supporting RV64GC ISA, working up to 1.5 GHz +- GPU: IMG BXE-4-32 MC1 with work frequency up to 600 MHz + +CPU: + +``` +$ python3 benchmark.py --all --cfg_exclude wechat:dasiam --model_exclude license_plate_detection_lpd_yunet_2023mar_int8.onnx:human_segmentation_pphumanseg_2023mar_int8.onnx +Benchmarking ... +backend=cv.dnn.DNN_BACKEND_OPENCV +target=cv.dnn.DNN_TARGET_CPU +mean median min input size model +50.28 50.42 50.08 [160, 120] YuNet with ['face_detection_yunet_2022mar.onnx'] +44.45 44.84 39.29 [160, 120] YuNet with ['face_detection_yunet_2022mar_int8.onnx'] +1059.87 1059.79 1058.95 [150, 150] SFace with ['face_recognition_sface_2021dec.onnx'] +838.07 859.42 658.86 [150, 150] SFace with ['face_recognition_sface_2021dec_int8.onnx'] +424.55 424.74 424.06 [112, 112] FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july.onnx'] +350.30 357.95 290.66 [112, 112] FacialExpressionRecog with ['facial_expression_recognition_mobilefacenet_2022july_int8.onnx'] +314.50 313.75 313.67 [224, 224] MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx'] +275.80 280.48 243.97 [224, 224] MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx'] +1131.91 1132.16 1131.08 [192, 192] PPHumanSeg with ['human_segmentation_pphumanseg_2023mar.onnx'] +1072.77 1073.31 1072.07 [224, 224] MobileNet with ['image_classification_mobilenetv1_2022apr.onnx'] +811.64 837.32 602.08 [224, 224] MobileNet with ['image_classification_mobilenetv2_2022apr.onnx'] +692.68 602.74 516.39 [224, 224] MobileNet with ['image_classification_mobilenetv1_2022apr_int8.onnx'] +596.12 559.52 382.75 [224, 224] MobileNet with ['image_classification_mobilenetv2_2022apr_int8.onnx'] +8131.86 8132.90 8128.55 [224, 224] PPResNet with ['image_classification_ppresnet50_2022jan.onnx'] +5412.98 5684.12 3236.35 [224, 224] PPResNet with ['image_classification_ppresnet50_2022jan_int8.onnx'] +2265.62 2264.83 2263.38 [320, 240] LPD_YuNet with ['license_plate_detection_lpd_yunet_2023mar.onnx'] +1727.39 1727.31 1726.31 [416, 416] NanoDet with ['object_detection_nanodet_2022nov.onnx'] +1429.48 1458.69 1189.19 [416, 416] NanoDet with ['object_detection_nanodet_2022nov_int8.onnx'] +26156.87 26169.88 26134.95 [640, 640] YoloX with ['object_detection_yolox_2022nov.onnx'] +17151.71 17933.90 9675.03 [640, 640] YoloX with ['object_detection_yolox_2022nov_int8.onnx'] +316.26 315.72 315.55 [224, 224] MPHandPose with ['handpose_estimation_mediapipe_2023feb.onnx'] +276.38 280.84 243.11 [224, 224] MPHandPose with ['handpose_estimation_mediapipe_2023feb_int8.onnx'] +586.18 586.28 585.62 [192, 192] MPPalmDet with ['palm_detection_mediapipe_2023feb.onnx'] +542.79 546.26 506.12 [192, 192] MPPalmDet with ['palm_detection_mediapipe_2023feb_int8.onnx'] +910.67 910.62 909.72 [224, 224] MPPersonDet with ['person_detection_mediapipe_2023mar.onnx'] +7628.31 7624.65 7623.26 [128, 256] YoutuReID with ['person_reid_youtu_2021nov.onnx'] +4899.76 5171.88 2714.07 [128, 256] YoutuReID with ['person_reid_youtu_2021nov_int8.onnx'] +486.59 490.33 484.31 [256, 256] MPPose with ['pose_estimation_mediapipe_2023mar.onnx'] +34888.37 34834.51 34103.30 [640, 480] DB with ['text_detection_DB_IC15_resnet18_2021sep.onnx'] +35123.00 35996.09 34103.30 [640, 480] DB with ['text_detection_DB_TD500_resnet18_2021sep.onnx'] +1425.08 1543.33 1413.01 [1280, 720] CRNN with ['text_recognition_CRNN_CH_2021sep.onnx'] +1455.55 1580.51 1413.01 [1280, 720] CRNN with ['text_recognition_CRNN_CN_2021nov.onnx'] +1457.01 1484.13 1413.01 [1280, 720] CRNN with ['text_recognition_CRNN_EN_2021sep.onnx'] +1281.84 1468.77 810.51 [1280, 720] CRNN with ['text_recognition_CRNN_CH_2022oct_int8.onnx'] +1191.52 1517.48 810.51 [1280, 720] CRNN with ['text_recognition_CRNN_CN_2021nov_int8.onnx'] +1111.95 1131.27 775.96 [1280, 720] CRNN with ['text_recognition_CRNN_EN_2022oct_int8.onnx'] +``` diff --git a/benchmark/color_table.svg b/benchmark/color_table.svg index d83cb1e1b3d43a309369b11bc502fa966bb1589d..9bcefef45f0b00095bab4333746e58aecd5da482 100644 --- a/benchmark/color_table.svg +++ b/benchmark/color_table.svg @@ -1,7 +1,7 @@ - + @@ -16,22 +16,22 @@ - + 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" id="image37a3aff213" transform="scale(1 -1) translate(0 -13.68)" x="645.816774" y="0.635294" width="558" height="13.68"/> - Faster + Faster - Slower + Slower @@ -124,216 +124,237 @@ z - + + + StarFive VisionFive 2 + + + StarFive JH7110 + + + CPU + + + + + + + + - Toybrick + Toybrick - RV1126 + RV1126 - CPU + CPU - + - - + - Khadas Edge2 + Khadas Edge2 - RK3588S + RK3588S - CPU + CPU - + - - + - Horizon Sunrise Pi + Horizon Sunrise Pi - X3 + X3 - CPU + CPU - + - - + - MAIX-III AX-Pi + MAIX-III AX-Pi - AX620A + AX620A - CPU + CPU - + - - + - Jetson Nano + Jetson Nano - B01 + B01 - CPU + CPU - + - - + - Khadas VIM3 + Khadas VIM3 - A311D + A311D - CPU + CPU - + - - + - Atlas 200 DK + Atlas 200 DK - Ascend 310 + Ascend 310 - CPU + CPU - + - - + - Jetson Nano + Jetson Nano - B01 + B01 - GPU + GPU - + - - + - Khadas VIM3 + Khadas VIM3 - A311D + A311D - NPU + NPU - + - - + - Atlas 200 DK + Atlas 200 DK - Ascend 310 + Ascend 310 - NPU + NPU - + - + YuNet - + - + Face Detection - + - + 160x120 - + - + 0.58 - + - + 5.45 - + - - - 68.89 - - - - 2.47 + 50.28 - +" style="fill: #a50026; stroke: #000000; stroke-linejoin: miter"/> - 11.04 + 68.89 - +" style="fill: #63bc62; stroke: #000000; stroke-linejoin: miter"/> - 98.16 + 2.47 - +" style="fill: #eff8aa; stroke: #000000; stroke-linejoin: miter"/> - 5.37 + 11.04 - +" style="fill: #a50026; stroke: #000000; stroke-linejoin: miter"/> - 4.93 + 98.16 - +" style="fill: #abdb6d; stroke: #000000; stroke-linejoin: miter"/> - 8.02 + 5.37 - +" style="fill: #a2d76a; stroke: #000000; stroke-linejoin: miter"/> - 11.22 + 4.93 - +" style="fill: #d3ec87; stroke: #000000; stroke-linejoin: miter"/> - 5.67 + 8.02 - +" style="fill: #f1f9ac; stroke: #000000; stroke-linejoin: miter"/> - 2.24 + 11.22 + + + + 5.67 + + + + + + 2.24 + + - + SFace - + - + Face Recognition - + - + 112x112 - + - + 6.18 - + - + 78.04 - + - - - 1550.71 - - - - - - 33.79 - - - - 140.83 + 1059.87 - - 2093.12 + 1550.71 - +" style="fill: #d7ee8a; stroke: #000000; stroke-linejoin: miter"/> - 65.14 + 33.79 - +" style="fill: #e95538; stroke: #000000; stroke-linejoin: miter"/> - 60.02 + 140.83 - +" style="fill: #a50026; stroke: #000000; stroke-linejoin: miter"/> - 104.51 + 2093.12 - +" style="fill: #feeb9d; stroke: #000000; stroke-linejoin: miter"/> - 24.60 + 65.14 - +" style="fill: #fff2aa; stroke: #000000; stroke-linejoin: miter"/> - 76.97 + 60.02 - +" style="fill: #fba35c; stroke: #000000; stroke-linejoin: miter"/> - 2.66 + 104.51 + + + + 24.60 + + + + + + 76.97 + + + + + + 2.66 + + - + FER - + - + Face Expression Recognition - + - + 112x112 - + - + 3.32 - + - + 32.21 - + - - 604.36 + + 424.55 - - + + + + 604.36 + + + - - 15.99 + + 15.99 - - + - - 64.96 + + 64.96 - - + - - 811.32 + + 811.32 - - + - - 28.19 + + 28.19 - - + - - 29.36 + + 29.36 - - + - - 47.71 + + 47.71 - - + - - 20.64 + + 20.64 - - + - - 40.38 + + 40.38 - - + - - 2.19 + + 2.19 - + - + LPD_YuNet - + - + License Plate Detection - + - + 320x240 - + - + 8.53 - + - + 192.61 - + - - 3222.92 + + 2265.62 - - + + + + 3222.92 + + + - - 57.57 + + 57.57 - - + - - 283.75 + + 283.75 - - + - - 4300.13 + + 4300.13 - - + - - 133.15 + + 133.15 - - + - - 122.17 + + 122.17 - - + - - 226.08 + + 226.08 - - + - - 53.50 + + 53.50 - - + - - --- + + --- - - + - - 7.63 + + 7.63 - + - + YOLOX - + - + Object Detection - + - + 640x640 - + - + 137.53 - + - + 1932.97 - + - - 38359.93 + + 26156.87 - - + + + + 38359.93 + + + - - 577.93 + + 577.93 - - + - - 2749.22 + + 2749.22 - - + - - 49994.75 + + 49994.75 - - + - - 1228.13 + + 1228.13 - - + - - 1189.83 + + 1189.83 - - + - - 1995.97 + + 1995.97 - - + - - 1238.91 + + 1238.91 - - + - - 1103.24 + + 1103.24 - - + - - 28.59 + + 28.59 - + - + NanoDet - + - + Object Detection - + - + 416x416 - + - + 65.15 - + - + 248.03 - + + + + 1727.39 + + + - - 2303.55 + + 2303.55 - - + - - 118.38 + + 118.38 - - + - - 408.16 + + 408.16 - - + - - 3360.20 + + 3360.20 - - + - - 215.57 + + 215.57 - - + - - 208.25 + + 208.25 - - + - - 343.08 + + 343.08 - - + - - 214.99 + + 214.99 - - + - - 200.50 + + 200.50 - - + - - 20.62 + + 20.62 - + - + DB-IC15 (EN) - + - + Text Detection - + - + 640x480 - + - + 75.82 - + - + 2025.09 - + - - 49065.03 + + 34888.37 - - + + + + 49065.03 + + + - - 394.77 + + 394.77 - - + - - 1908.87 + + 1908.87 - - + - - 65681.91 + + 65681.91 - - + - - 1089.89 + + 1089.89 - - + - - 973.75 + + 973.75 - - + - - 1452.55 + + 1452.55 - - + - - 303.12 + + 303.12 - - + - - --- + + --- - - + - - 17.15 + + 17.15 - + - + DB-TD500 (EN&CN) - + - + Text Detection - + - + 640x480 - + - + 74.80 - + - + 2041.85 - + - - 49052.24 + + 35123.00 - - + + + + 49052.24 + + + - - 392.52 + + 392.52 - - + - - 1922.34 + + 1922.34 - - + - - 65630.56 + + 65630.56 - - + - - 1089.94 + + 1089.94 - - + - - 961.44 + + 961.44 - - + - - 1433.26 + + 1433.26 - - + - - 302.58 + + 302.58 - - + - - --- + + --- - - + - - 17.95 + + 17.95 - + - + CRNN-EN - + - + Text Recognition - + - + 100*32 - + - + 20.43 - + - + 271.57 - + + + + 1457.01 + + + - - 2230.12 + + 2230.12 - - + - - 77.51 + + 77.51 - - + - - 464.58 + + 464.58 - - + - - 3277.07 + + 3277.07 - - + - - 269.52 + + 269.52 - - + - - 199.81 + + 199.81 - - + - - 303.65 + + 303.65 - - + - - 45.60 + + 45.60 - - + - - 172.06 + + 172.06 - - + - - --- + + --- - + - + CRNN-CN - + - + Text Recognition - + - + 100*32 - + - + 23.08 - + - + 293.83 - + + + + 1455.55 + + + - - 2244.03 + + 2244.03 - - + - - 82.93 + + 82.93 - - + - - 495.94 + + 495.94 - - + - - 3330.69 + + 3330.69 - - + - - 290.82 + + 290.82 - - + - - 217.07 + + 217.07 - - + - - 329.84 + + 329.84 - - + - - 59.39 + + 59.39 - - + - - 183.51 + + 183.51 - - + - - --- + + --- - + - + PP-ResNet - + - + Image Classification - + - + 224x224 - + - + 35.40 - + - + 547.70 - + - - 11793.09 + + 8131.86 - - + + + + 11793.09 + + + - - 178.87 + + 178.87 - - + - - 759.81 + + 759.81 - - + - - 15753.56 + + 15753.56 - - + - - 376.88 + + 376.88 - - + - - 385.29 + + 385.29 - - + - - 564.69 + + 564.69 - - + - - 148.58 + + 148.58 - - + - - 340.20 + + 340.20 - - + - - 6.99 + + 6.99 - + - + MobileNet-V1 - + - + Image Classification - + - + 224x224 - + - + 6.25 - + - + 74.51 - + - - 1546.16 + + 1072.77 - - + + + + 1546.16 + + + - - 32.78 + + 32.78 - - + - - 140.60 + + 140.60 - - + - - 2091.13 + + 2091.13 - - + - - 68.94 + + 68.94 - - + - - 64.73 + + 64.73 - - + - - 103.96 + + 103.96 - - + - - 69.24 + + 69.24 - - + - - 60.75\* + + 60.75\* - - + - - 5.15 + + 5.15 - + - + MobileNet-V2 - + - + Image Classification - + - + 224x224 - + - + 6.00 - + - + 67.29 - + - - 1166.56 + + 811.64 - - + + + + 1166.56 + + + - - 28.38 + + 28.38 - - + - - 122.53 + + 122.53 - - + - - 1583.25 + + 1583.25 - - + - - 62.12 + + 62.12 - - + - - 58.18 + + 58.18 - - + - - 90.46 + + 90.46 - - + - - 62.12 + + 62.12 - - + - - 57.40\* + + 57.40\* - - + - - 5.41 + + 5.41 - + - + PP-HumanSeg - + - + Human Segmentation - + - + 192x192 - + - + 8.20 - + - + 73.29 - + - - 1610.78 + + 1131.91 - - + + + + 1610.78 + + + - - 34.58 + + 34.58 - - + - - 144.23 + + 144.23 - - + - - 2157.86 + + 2157.86 - - + - - 65.91 + + 65.91 - - + - - 70.82 + + 70.82 - - + - - 107.98 + + 107.98 - - + - - 90.86 + + 90.86 - - + - - --- + + --- - - + - - 6.94 + + 6.94 - + - + WeChatQRCode - + - + QR Code Detection and Parsing - + - + 100x100 - + - + 1.35 - + - + 8.18 - + - - --- + + --- - - + - - --- + + --- - - + - - --- + + --- - - + - - --- + + --- - - + + + + --- + + + - - 5.62 + + 5.62 - - + - - 5.29 + + 5.29 - - + - - --- + + --- - - + - - --- + + --- - - + - - --- + + --- - - + - - --- + + --- - + - + DaSiamRPN - + - + Object Tracking - + - + 1280x720 - + - + 29.46 - + - + 762.56 - + + + + --- + + + - - 14738.64 + + 14738.64 - - + - - 152.78 + + 152.78 - - + - - 929.63 + + 929.63 - - + - - 19800.14 + + 19800.14 - - + - - 466.19 + + 466.19 - - + - - 428.66 + + 428.66 - - + - - 701.08 + + 701.08 - - + - - 76.54 + + 76.54 - - + - - --- + + --- - - + - - --- + + --- - + - + YoutuReID - + - + Person Re-Identification - + - + 128x256 - + - + 30.87 - + - + 676.15 - + - - 11117.07 + + 7628.31 + + + + + + 11117.07 - - + - - 195.67 + + 195.67 - - + - - 898.23 + + 898.23 - - + - - 14886.02 + + 14886.02 - - + - - 411.49 + + 411.49 - - + - - 439.53 + + 439.53 - - + - - 631.70 + + 631.70 - - + - - 126.65 + + 126.65 - - + - - 307.90 + + 307.90 - - + - - 5.58 + + 5.58 - + - + MP-PalmDet - + - + Palm Detection - + - + 192x192 - + - + 6.14 - + - + 91.48 - + - - 872.09 + + 586.18 - - + + + + 872.09 + + + - - 38.03 + + 38.03 - - + - - 142.23 + + 142.23 - - + - - 1191.81 + + 1191.81 - - + - - 69.60 + + 69.60 - - + - - 66.91 + + 66.91 - - + - - 105.23 + + 105.23 - - + - - 67.34 + + 67.34 - - + - - 95.92 + + 95.92 - - + - - 5.17 + + 5.17 - + - + MP-HandPose - + - + Hand Pose Estimation - + - + 224x224 - + - + 4.68 - + - + 43.85 - + + + + 314.50 + + + - - 460.56 + + 460.56 - - + - - 20.27 + + 20.27 - - + - - 80.67 + + 80.67 - - + - - 636.22 + + 636.22 - - + - - 41.02 + + 41.02 - - + - - 38.60 + + 38.60 - - + - - 57.95 + + 57.95 - - + - - 41.15 + + 41.15 - - + - - 44.36 + + 44.36 - - + - - 6.27 + + 6.27 - + - + MP-PersonDet - + - + Person Detection - + - + 224x224 - + - + 13.88 - + - + 98.52 - + + + + 910.67 + + + - - 1326.56 + + 1326.56 - - + - - 46.07 + + 46.07 - - + - - 191.41 + + 191.41 - - + - - 1835.97 + + 1835.97 - - + - - 98.38 + + 98.38 - - + - - 84.42 + + 84.42 - - + - - 134.10 + + 134.10 - - + - - 56.69 + + 56.69 - - + - - --- + + --- - - + - - 16.45 + + 16.45 - + - + MP-Pose - + - + Pose Estimation - + - + 256x256 - + - + 7.72 - + - + 90.26 - + + + + 486.59 + + + - - 704.44 + + 704.44 - - + - - 35.47 + + 35.47 - - + - - 158.50 + + 158.50 - - + - - 987.30 + + 987.30 - - + - - 74.36 + + 74.36 - - + - - 68.51 + + 68.51 - - + - - 108.55 + + 108.55 - - + - - 73.84 + + 73.84 - - + - - --- + + --- - - + - - --- + + --- - + Units: All data in milliseconds (ms). - + \*: Models are quantized in per-channel mode, which run slower than per-tensor quantized models on NPU. - - + + diff --git a/benchmark/table_config.yaml b/benchmark/table_config.yaml index 27af76d925d4bcd6567e98aec77ac3d5f7ea9c10..10ae9cb97faf92c71806502a7674fd76b01254c6 100644 --- a/benchmark/table_config.yaml +++ b/benchmark/table_config.yaml @@ -174,6 +174,10 @@ Devices: display_info: "Rasberry Pi 4B\nBCM2711\nCPU" platform: "CPU" + - name: "StarFive VisionFive 2" + display_info: "StarFive VisionFive 2\nStarFive JH7110\nCPU" + platform: "CPU" + - name: "Toybrick RV1126" display_info: "Toybrick\nRV1126\nCPU" platform: "CPU"