--- comments: true --- # PaddleX Model List（CPU/GPU） PaddleX incorporates multiple pipelines, each containing several modules, and each module includes various models. You can choose which models to use based on the benchmark data below. If you prioritize model accuracy, select models with higher accuracy. If you prioritize inference speed, choose models with faster inference. If you prioritize model storage size, select models with smaller storage sizes. ## [Image Classification Module](../module_usage/tutorials/cv_modules/image_classification.en.md)
Model Name Top-1 Acc (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
CLIP_vit_base_patch16_224 85.36 13.1957 285.493 306.5 M CLIP_vit_base_patch16_224.yaml Inference Model/Trained Model
CLIP_vit_large_patch14_224 88.1 51.1284 1131.28 1.04 G CLIP_vit_large_patch14_224.yaml Inference Model/Trained Model
ConvNeXt_base_224 83.84 12.8473 1513.87 313.9 M ConvNeXt_base_224.yaml Inference Model/Trained Model
ConvNeXt_base_384 84.90 31.7607 3967.05 313.9 M ConvNeXt_base_384.yaml Inference Model/Trained Model
ConvNeXt_large_224 84.26 26.8103 2463.56 700.7 M ConvNeXt_large_224.yaml Inference Model/Trained Model
ConvNeXt_large_384 85.27 66.4058 6598.92 700.7 M ConvNeXt_large_384.yaml Inference Model/Trained Model
ConvNeXt_small 83.13 9.74075 1127.6 178.0 M ConvNeXt_small.yaml Inference Model/Trained Model
ConvNeXt_tiny 82.03 5.48923 672.559 101.4 M ConvNeXt_tiny.yaml Inference Model/Trained Model
FasterNet-L 83.5 23.4415 - 357.1 M FasterNet-L.yaml Inference Model/Trained Model
FasterNet-M 83.0 21.8936 - 204.6 M FasterNet-M.yaml Inference Model/Trained Model
FasterNet-S 81.3 13.0409 - 119.3 M FasterNet-S.yaml Inference Model/Trained Model
FasterNet-T0 71.9 12.2432 - 15.1 M FasterNet-T0.yaml Inference Model/Trained Model
FasterNet-T1 75.9 11.3562 - 29.2 M FasterNet-T1.yaml Inference Model/Trained Model
FasterNet-T2 79.1 10.703 - 57.4 M FasterNet-T2.yaml Inference Model/Trained Model
MobileNetV1_x0_5 63.5 1.86754 7.48297 4.8 M MobileNetV1_x0_5.yaml Inference Model/Trained Model
MobileNetV1_x0_25 51.4 1.83478 4.83674 1.8 M MobileNetV1_x0_25.yaml Inference Model/Trained Model
MobileNetV1_x0_75 68.8 2.57903 10.6343 9.3 M MobileNetV1_x0_75.yaml Inference Model/Trained Model
MobileNetV1_x1_0 71.0 2.78781 13.98 15.2 M MobileNetV1_x1_0.yaml Inference Model/Trained Model
MobileNetV2_x0_5 65.0 4.94234 11.1629 7.1 M MobileNetV2_x0_5.yaml Inference Model/Trained Model
MobileNetV2_x0_25 53.2 4.50856 9.40991 5.5 M MobileNetV2_x0_25.yaml Inference Model/Trained Model
MobileNetV2_x1_0 72.2 6.12159 16.0442 12.6 M MobileNetV2_x1_0.yaml Inference Model/Trained Model
MobileNetV2_x1_5 74.1 6.28385 22.5129 25.0 M MobileNetV2_x1_5.yaml Inference Model/Trained Model
MobileNetV2_x2_0 75.2 6.12888 30.8612 41.2 M MobileNetV2_x2_0.yaml Inference Model/Trained Model
MobileNetV3_large_x0_5 69.2 6.31302 14.5588 9.6 M MobileNetV3_large_x0_5.yaml Inference Model/Trained Model
MobileNetV3_large_x0_35 64.3 5.76207 13.9041 7.5 M MobileNetV3_large_x0_35.yaml Inference Model/Trained Model
MobileNetV3_large_x0_75 73.1 8.41737 16.9506 14.0 M MobileNetV3_large_x0_75.yaml Inference Model/Trained Model
MobileNetV3_large_x1_0 75.3 8.64112 19.1614 19.5 M MobileNetV3_large_x1_0.yaml Inference Model/Trained Model
MobileNetV3_large_x1_25 76.4 8.73358 22.1296 26.5 M MobileNetV3_large_x1_25.yaml Inference Model/Trained Model
MobileNetV3_small_x0_5 59.2 5.16721 11.2688 6.8 M MobileNetV3_small_x0_5.yaml Inference Model/Trained Model
MobileNetV3_small_x0_35 53.0 5.22053 11.0055 6.0 M MobileNetV3_small_x0_35.yaml Inference Model/Trained Model
MobileNetV3_small_x0_75 66.0 5.39831 12.8313 8.5 M MobileNetV3_small_x0_75.yaml Inference Model/Trained Model
MobileNetV3_small_x1_0 68.2 6.00993 12.9598 10.5 M MobileNetV3_small_x1_0.yaml Inference Model/Trained Model
MobileNetV3_small_x1_25 70.7 6.9589 14.3995 13.0 M MobileNetV3_small_x1_25.yaml Inference Model/Trained Model
MobileNetV4_conv_large 83.4 12.5485 51.6453 125.2 M MobileNetV4_conv_large.yaml Inference Model/Trained Model
MobileNetV4_conv_medium 79.9 9.65509 26.6157 37.6 M MobileNetV4_conv_medium.yaml Inference Model/Trained Model
MobileNetV4_conv_small 74.6 5.24172 11.0893 14.7 M MobileNetV4_conv_small.yaml Inference Model/Trained Model
MobileNetV4_hybrid_large 83.8 20.0726 213.769 145.1 M MobileNetV4_hybrid_large.yaml Inference Model/Trained Model
MobileNetV4_hybrid_medium 80.5 19.7543 62.2624 42.9 M MobileNetV4_hybrid_medium.yaml Inference Model/Trained Model
PP-HGNet_base 85.0 14.2969 327.114 249.4 M PP-HGNet_base.yaml Inference Model/Trained Model
PP-HGNet_small 81.51 5.50661 119.041 86.5 M PP-HGNet_small.yaml Inference Model/Trained Model
PP-HGNet_tiny 79.83 5.22006 69.396 52.4 M PP-HGNet_tiny.yaml Inference Model/Trained Model
PP-HGNetV2-B0 77.77 6.53694 23.352 21.4 M PP-HGNetV2-B0.yaml Inference Model/Trained Model
PP-HGNetV2-B1 79.18 6.56034 27.3099 22.6 M PP-HGNetV2-B1.yaml Inference Model/Trained Model
PP-HGNetV2-B2 81.74 9.60494 43.1219 39.9 M PP-HGNetV2-B2.yaml Inference Model/Trained Model
PP-HGNetV2-B3 82.98 11.0042 55.1367 57.9 M PP-HGNetV2-B3.yaml Inference Model/Trained Model
PP-HGNetV2-B4 83.57 9.66407 54.2462 70.4 M PP-HGNetV2-B4.yaml Inference Model/Trained Model
PP-HGNetV2-B5 84.75 15.7091 115.926 140.8 M PP-HGNetV2-B5.yaml Inference Model/Trained Model
PP-HGNetV2-B6 86.30 21.226 255.279 268.4 M PP-HGNetV2-B6.yaml Inference Model/Trained Model
PP-LCNet_x0_5 63.14 3.67722 6.66857 6.7 M PP-LCNet_x0_5.yaml Inference Model/Trained Model
PP-LCNet_x0_25 51.86 2.65341 5.81357 5.5 M PP-LCNet_x0_25.yaml Inference Model/Trained Model
PP-LCNet_x0_35 58.09 2.7212 6.28944 5.9 M PP-LCNet_x0_35.yaml Inference Model/Trained Model
PP-LCNet_x0_75 68.18 3.91032 8.06953 8.4 M PP-LCNet_x0_75.yaml Inference Model/Trained Model
PP-LCNet_x1_0 71.32 3.84845 9.23735 10.5 M PP-LCNet_x1_0.yaml Inference Model/Trained Model
PP-LCNet_x1_5 73.71 3.97666 12.3457 16.0 M PP-LCNet_x1_5.yaml Inference Model/Trained Model
PP-LCNet_x2_0 75.18 4.07556 16.2752 23.2 M PP-LCNet_x2_0.yaml Inference Model/Trained Model
PP-LCNet_x2_5 76.60 4.06028 21.5063 32.1 M PP-LCNet_x2_5.yaml Inference Model/Trained Model
PP-LCNetV2_base 77.05 5.23428 19.6005 23.7 M PP-LCNetV2_base.yaml Inference Model/Trained Model
PP-LCNetV2_large 78.51 6.78335 30.4378 37.3 M PP-LCNetV2_large.yaml Inference Model/Trained Model
PP-LCNetV2_small 73.97 3.89762 13.0273 14.6 M PP-LCNetV2_small.yaml Inference Model/Trained Model
ResNet18_vd 72.3 3.53048 31.3014 41.5 M ResNet18_vd.yaml Inference Model/Trained Model
ResNet18 71.0 2.4868 27.4601 41.5 M ResNet18.yaml Inference Model/Trained Model
ResNet34_vd 76.0 5.60675 56.0653 77.3 M ResNet34_vd.yaml Inference Model/Trained Model
ResNet34 74.6 4.16902 51.925 77.3 M ResNet34.yaml Inference Model/Trained Model
ResNet50_vd 79.1 10.1885 68.446 90.8 M ResNet50_vd.yaml Inference Model/Trained Model
ResNet50 76.5 9.62383 64.8135 90.8 M ResNet50.yaml Inference Model/Trained Model
ResNet101_vd 80.2 20.0563 124.85 158.4 M ResNet101_vd.yaml Inference Model/Trained Model
ResNet101 77.6 19.2297 121.006 158.7 M ResNet101.yaml Inference Model/Trained Model
ResNet152_vd 80.6 29.6439 181.678 214.3 M ResNet152_vd.yaml Inference Model/Trained Model
ResNet152 78.3 30.0461 177.707 214.2 M ResNet152.yaml Inference Model/Trained Model
ResNet200_vd 80.9 39.1628 235.185 266.0 M ResNet200_vd.yaml Inference Model/Trained Model
StarNet-S1 73.6 9.895 23.0465 11.2 M StarNet-S1.yaml Inference Model/Trained Model
StarNet-S2 74.8 7.91279 21.9571 14.3 M StarNet-S2.yaml Inference Model/Trained Model
StarNet-S3 77.0 10.7531 30.7656 22.2 M StarNet-S3.yaml Inference Model/Trained Model
StarNet-S4 79.0 15.2868 43.2497 28.9 M StarNet-S4.yaml Inference Model/Trained Model
SwinTransformer_base_patch4_window7_224 83.37 16.9848 383.83 310.5 M SwinTransformer_base_patch4_window7_224.yaml Inference Model/Trained Model
SwinTransformer_base_patch4_window12_384 84.17 37.2855 1178.63 311.4 M SwinTransformer_base_patch4_window12_384.yaml Inference Model/Trained Model
SwinTransformer_large_patch4_window7_224 86.19 27.5498 689.729 694.8 M SwinTransformer_large_patch4_window7_224.yaml Inference Model/Trained Model
SwinTransformer_large_patch4_window12_384 87.06 74.1768 2105.22 696.1 M SwinTransformer_large_patch4_window12_384.yaml Inference Model/Trained Model
SwinTransformer_small_patch4_window7_224 83.21 16.3982 285.56 175.6 M SwinTransformer_small_patch4_window7_224.yaml Inference Model/Trained Model
SwinTransformer_tiny_patch4_window7_224 81.10 8.54846 156.306 100.1 M SwinTransformer_tiny_patch4_window7_224.yaml Inference Model/Trained Model
Note: The above accuracy metrics are Top-1 Acc on the [ImageNet-1k](https://www.image-net.org/index.php) validation set. ## [Image Multi-Label Classification Module](../module_usage/tutorials/cv_modules/image_multilabel_classification.en.md)
Model Name mAP (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
CLIP_vit_base_patch16_448_ML 89.15 - - 325.6 M CLIP_vit_base_patch16_448_ML.yaml Inference Model/Trained Model
PP-HGNetV2-B0_ML 80.98 - - 39.6 M PP-HGNetV2-B0_ML.yaml Inference Model/Trained Model
PP-HGNetV2-B4_ML 87.96 - - 88.5 M PP-HGNetV2-B4_ML.yaml Inference Model/Trained Model
PP-HGNetV2-B6_ML 91.25 - - 286.5 M PP-HGNetV2-B6_ML.yaml Inference Model/Trained Model
PP-LCNet_x1_0_ML 77.96 - - 29.4 M PP-LCNet_x1_0_ML.yaml Inference Model/Trained Model
ResNet50_ML 83.50 - - 108.9 M ResNet50_ML.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mAP for the multi-label classification task on [COCO2017](https://cocodataset.org/#home). ## [Pedestrian Attribute Module](../module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.en.md)
Model Name mA (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-LCNet_x1_0_pedestrian_attribute 92.2 3.84845 9.23735 6.7 M PP-LCNet_x1_0_pedestrian_attribute.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mA on PaddleX's internal self-built dataset. ## [Vehicle Attribute Module](../module_usage/tutorials/cv_modules/vehicle_attribute_recognition.en.md)
Model Name mA (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-LCNet_x1_0_vehicle_attribute 91.7 3.84845 9.23735 6.7 M PP-LCNet_x1_0_vehicle_attribute.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mA on the VeRi dataset. ## [Image Feature Module](../module_usage/tutorials/cv_modules/image_feature.en.md)
Model Name recall@1 (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-ShiTuV2_rec 84.2 5.23428 19.6005 16.3 M PP-ShiTuV2_rec.yaml Inference Model/Trained Model
PP-ShiTuV2_rec_CLIP_vit_base 88.69 13.1957 285.493 306.6 M PP-ShiTuV2_rec_CLIP_vit_base.yaml Inference Model/Trained Model
PP-ShiTuV2_rec_CLIP_vit_large 91.03 51.1284 1131.28 1.05 G PP-ShiTuV2_rec_CLIP_vit_large.yaml Inference Model/Trained Model
Note: The above accuracy metrics are recall@1 on AliProducts. ## [Document Orientation Classification Module](../module_usage/tutorials/ocr_modules/doc_img_orientation_classification.en.md)
Model Name Top-1 Acc (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-LCNet_x1_0_doc_ori 99.26 3.84845 9.23735 7.1 M PP-LCNet_x1_0_doc_ori.yaml Inference Model/Trained Model
Note: The above accuracy metrics are Top-1 Acc on PaddleX's internal self-built dataset. ## [Face Feature Module](../module_usage/tutorials/cv_modules/face_feature.en.md)
Model Name Output Feature Dimension Acc (%)
AgeDB-30/CFP-FP/LFW		 GPU Inference Time (ms) CPU Inference Time (ms) Model Size (M) YAML File Model Download Link
MobileFaceNet 128 96.28/96.71/99.58 4.1 MobileFaceNet.yaml Inference Model/Trained Model
ResNet50_face 512 98.12/98.56/99.77 87.2 ResNet50_face.yaml Inference Model/Trained Model
Note: The above accuracy metrics are Accuracy scores measured on the AgeDB-30, CFP-FP, and LFW datasets, respectively. ## [Main Body Detection Module](../module_usage/tutorials/cv_modules/mainbody_detection.en.md)
Model Name mAP (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-ShiTuV2_det 41.5 33.7426 537.003 27.6 M PP-ShiTuV2_det.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mAP(0.5:0.95) on the [PaddleClas main body detection dataset](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.5/docs/zh_CN/training/PP-ShiTu/mainbody_detection.md). ## [Object Detection Module](../module_usage/tutorials/cv_modules/object_detection.en.md)
Model Name mAP (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
Cascade-FasterRCNN-ResNet50-FPN 41.1 - - 245.4 M Cascade-FasterRCNN-ResNet50-FPN.yaml Inference Model/Trained Model
Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN 45.0 - - 246.2 M Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml Inference Model/Trained Model
CenterNet-DLA-34 37.6 - - 75.4 M CenterNet-DLA-34.yaml Inference Model/Trained Model
CenterNet-ResNet50 38.9 - - 319.7 M CenterNet-ResNet50.yaml Inference Model/Trained Model
DETR-R50 42.3 59.2132 5334.52 159.3 M DETR-R50.yaml Inference Model/Trained Model
FasterRCNN-ResNet34-FPN 37.8 - - 137.5 M FasterRCNN-ResNet34-FPN.yaml Inference Model/Trained Model
FasterRCNN-ResNet50-FPN 38.4 - - 148.1 M FasterRCNN-ResNet50-FPN.yaml Inference Model/Trained Model
FasterRCNN-ResNet50-vd-FPN 39.5 - - 148.1 M FasterRCNN-ResNet50-vd-FPN.yaml Inference Model/Trained Model
FasterRCNN-ResNet50-vd-SSLDv2-FPN 41.4 - - 148.1 M FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml Inference Model/Trained Model
FasterRCNN-ResNet50 36.7 - - 120.2 M FasterRCNN-ResNet50.yaml Inference Model/Trained Model
FasterRCNN-ResNet101-FPN 41.4 - - 216.3 M FasterRCNN-ResNet101-FPN.yaml Inference Model/Trained Model
FasterRCNN-ResNet101 39.0 - - 188.1 M FasterRCNN-ResNet101.yaml Inference Model/Trained Model
FasterRCNN-ResNeXt101-vd-FPN 43.4 - - 360.6 M FasterRCNN-ResNeXt101-vd-FPN.yaml Inference Model/Trained Model
FasterRCNN-Swin-Tiny-FPN 42.6 - - 159.8 M FasterRCNN-Swin-Tiny-FPN.yaml Inference Model/Trained Model
FCOS-ResNet50 39.6 103.367 3424.91 124.2 M FCOS-ResNet50.yaml Inference Model/Trained Model
PicoDet-L 42.6 16.6715 169.904 20.9 M PicoDet-L.yaml Inference Model/Trained Model
PicoDet-M 37.5 16.2311 71.7257 16.8 M PicoDet-M.yaml Inference Model/Trained Model
PicoDet-S 29.1 14.097 37.6563 4.4 M PicoDet-S.yaml Inference Model/Trained Model
PicoDet-XS 26.2 13.8102 48.3139 5.7M PicoDet-XS.yaml Inference Model/Trained Model
PP-YOLOE_plus-L 52.9 33.5644 814.825 185.3 M PP-YOLOE_plus-L.yaml Inference Model/Trained Model
PP-YOLOE_plus-M 49.8 19.843 449.261 83.2 M PP-YOLOE_plus-M.yaml Inference Model/Trained Model
PP-YOLOE_plus-S 43.7 16.8884 223.059 28.3 M PP-YOLOE_plus-S.yaml Inference Model/Trained Model
PP-YOLOE_plus-X 54.7 57.8995 1439.93 349.4 M PP-YOLOE_plus-X.yaml Inference Model/Trained Model
RT-DETR-H 56.3 114.814 3933.39 435.8 M RT-DETR-H.yaml Inference Model/Trained Model
RT-DETR-L 53.0 34.5252 1454.27 113.7 M RT-DETR-L.yaml Inference Model/Trained Model
RT-DETR-R18 46.5 19.89 784.824 70.7 M RT-DETR-R18.yaml Inference Model/Trained Model
RT-DETR-R50 53.1 41.9327 1625.95 149.1 M RT-DETR-R50.yaml Inference Model/Trained Model
RT-DETR-X 54.8 61.8042 2246.64 232.9 M RT-DETR-X.yaml Inference Model/Trained Model
YOLOv3-DarkNet53 39.1 40.1055 883.041 219.7 M YOLOv3-DarkNet53.yaml Inference Model/Trained Model
YOLOv3-MobileNetV3 31.4 18.6692 267.214 83.8 M YOLOv3-MobileNetV3.yaml Inference Model/Trained Model
YOLOv3-ResNet50_vd_DCN 40.6 31.6276 856.047 163.0 M YOLOv3-ResNet50_vd_DCN.yaml Inference Model/Trained Model
YOLOX-L 50.1 185.691 1250.58 192.5 M YOLOX-L.yaml Inference Model/Trained Model
YOLOX-M 46.9 123.324 688.071 90.0 M YOLOX-M.yaml Inference Model/Trained Model
YOLOX-N 26.1 79.1665 155.59 3.4 M YOLOX-N.yaml Inference Model/Trained Model
YOLOX-S 40.4 184.828 474.446 32.0 M YOLOX-S.yaml Inference Model/Trained Model
YOLOX-T 32.9 102.748 212.52 18.1 M YOLOX-T.yaml Inference Model/Trained Model
YOLOX-X 51.8 227.361 2067.84 351.5 M YOLOX-X.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mAP(0.5:0.95) on the [COCO2017](https://cocodataset.org/#home) validation set. ## [Small Object Detection Module](../module_usage/tutorials/cv_modules/small_object_detection.en.md)
Model Name mAP (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-YOLOE_plus_SOD-S 25.1 65.4608 324.37 77.3 M PP-YOLOE_plus_SOD-S.yaml Inference Model/Trained Model
PP-YOLOE_plus_SOD-L 31.9 57.1448 1006.98 325.0 M PP-YOLOE_plus_SOD-L.yaml Inference Model/Trained Model
PP-YOLOE_plus_SOD-largesize-L 42.7 458.521 11172.7 340.5 M PP-YOLOE_plus_SOD-largesize-L.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mAP(0.5:0.95) on the [VisDrone-DET](https://github.com/VisDrone/VisDrone-Dataset) validation set. ## [Pedestrian Detection Module](../module_usage/tutorials/cv_modules/human_detection.en.md)
Model Name mAP (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-YOLOE-L_human 48.0 32.7754 777.691 196.1 M PP-YOLOE-L_human.yaml Inference Model/Trained Model
PP-YOLOE-S_human 42.5 15.0118 179.317 28.8 M PP-YOLOE-S_human.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mAP(0.5:0.95) on the [CrowdHuman](https://bj.bcebos.com/v1/paddledet/data/crowdhuman.zip) validation set. ## [Vehicle Detection Module](../module_usage/tutorials/cv_modules/vehicle_detection.en.md)
Model Name mAP (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-YOLOE-L_vehicle 63.9 32.5619 775.633 196.1 M PP-YOLOE-L_vehicle.yaml Inference Model/Trained Model
PP-YOLOE-S_vehicle 61.3 15.3787 178.441 28.8 M PP-YOLOE-S_vehicle.yaml Inference Model/Trained Model
Note: The above accuracy metrics are mAP(0.5:0.95) on the [PPVehicle](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppvehicle) validation set. ## [Face Detection Module](../module_usage/tutorials/cv_modules/face_detection.en.md)
Model AP (%)
Easy/Medium/Hard		 GPU Inference Time (ms) CPU Inference Time (ms) Model Size (M) YAML File Model Download Link
BlazeFace 77.7/73.4/49.5 0.447 BlazeFace.yaml Inference Model/Trained Model
BlazeFace-FPN-SSH 83.2/80.5/60.5 0.606 BlazeFace-FPN-SSH.yaml Inference Model/Trained Model
PicoDet_LCNet_x2_5_face 93.7/90.7/68.1 28.9 PicoDet_LCNet_x2_5_face.yaml Inference Model/Trained Model
PP-YOLOE_plus-S_face 93.9/91.8/79.8 26.5 PP-YOLOE_plus-S_face Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on the WIDER-FACE validation set with an input size of 640*640. ## [Abnormality Detection Module](../module_usage/tutorials/cv_modules/anomaly_detection.en.md)
Model Name Avg (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
STFPM 96.2 - - 21.5 M STFPM.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on the [MVTec AD](https://www.mvtec.com/company/research/datasets/mvtec-ad) dataset using the average anomaly score. ## [Semantic Segmentation Module](../module_usage/tutorials/cv_modules/semantic_segmentation.en.md)
Model Name mIoU (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
Deeplabv3_Plus-R50 80.36 61.0531 1513.58 94.9 M Deeplabv3_Plus-R50.yaml Inference Model/Trained Model
Deeplabv3_Plus-R101 81.10 100.026 2460.71 162.5 M Deeplabv3_Plus-R101.yaml Inference Model/Trained Model
Deeplabv3-R50 79.90 82.2631 1735.83 138.3 M Deeplabv3-R50.yaml Inference Model/Trained Model
Deeplabv3-R101 80.85 121.492 2685.51 205.9 M Deeplabv3-R101.yaml Inference Model/Trained Model
OCRNet_HRNet-W18 80.67 48.2335 906.385 43.1 M OCRNet_HRNet-W18.yaml Inference Model/Trained Model
OCRNet_HRNet-W48 82.15 78.9976 2226.95 249.8 M OCRNet_HRNet-W48.yaml Inference Model/Trained Model
PP-LiteSeg-T 73.10 7.6827 138.683 28.5 M PP-LiteSeg-T.yaml Inference Model/Trained Model
PP-LiteSeg-B 75.25 10.9935 194.727 47.0 M PP-LiteSeg-B.yaml Inference Model/Trained Model
SegFormer-B0 (slice) 76.73 11.1946 268.929 13.2 M SegFormer-B0.yaml Inference Model/Trained Model
SegFormer-B1 (slice) 78.35 17.9998 403.393 48.5 M SegFormer-B1.yaml Inference Model/Trained Model
SegFormer-B2 (slice) 81.60 48.0371 1248.52 96.9 M SegFormer-B2.yaml Inference Model/Trained Model
SegFormer-B3 (slice) 82.47 64.341 1666.35 167.3 M SegFormer-B3.yaml Inference Model/Trained Model
SegFormer-B4 (slice) 82.38 82.4336 1995.42 226.7 M SegFormer-B4.yaml Inference Model/Trained Model
SegFormer-B5 (slice) 82.58 97.3717 2420.19 229.7 M SegFormer-B5.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on the [Cityscapes](https://www.cityscapes-dataset.com/) dataset using mIoU.
Model Name mIoU (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
SeaFormer_base(slice) 40.92 24.4073 397.574 30.8 M SeaFormer_base.yaml Inference Model/Trained Model
SeaFormer_large (slice) 43.66 27.8123 550.464 49.8 M SeaFormer_large.yaml Inference Model/Trained Model
SeaFormer_small (slice) 38.73 19.2295 358.343 14.3 M SeaFormer_small.yaml Inference Model/Trained Model
SeaFormer_tiny (slice) 34.58 13.9496 330.132 6.1 M SeaFormer_tiny.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on the [ADE20k](https://groups.csail.mit.edu/vision/datasets/ADE20K/) dataset. "slice" indicates that the input image has been cropped. ## [Instance Segmentation Module](../module_usage/tutorials/cv_modules/instance_segmentation.en.md)
Model Name Mask AP GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
Mask-RT-DETR-H 50.6 132.693 4896.17 449.9 M Mask-RT-DETR-H.yaml Inference Model/Trained Model
Mask-RT-DETR-L 45.7 46.5059 2575.92 113.6 M Mask-RT-DETR-L.yaml Inference Model/Trained Model
Mask-RT-DETR-M 42.7 36.8329 - 66.6 M Mask-RT-DETR-M.yaml Inference Model/Trained Model
Mask-RT-DETR-S 41.0 33.5007 - 51.8 M Mask-RT-DETR-S.yaml Inference Model/Trained Model
Mask-RT-DETR-X 47.5 75.755 3358.04 237.5 M Mask-RT-DETR-X.yaml Inference Model/Trained Model
Cascade-MaskRCNN-ResNet50-FPN 36.3 - - 254.8 M Cascade-MaskRCNN-ResNet50-FPN.yaml Inference Model/Trained Model
Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN 39.1 - - 254.7 M Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml Inference Model/Trained Model
MaskRCNN-ResNet50-FPN 35.6 - - 157.5 M MaskRCNN-ResNet50-FPN.yaml Inference Model/Trained Model
MaskRCNN-ResNet50-vd-FPN 36.4 - - 157.5 M MaskRCNN-ResNet50-vd-FPN.yaml Inference Model/Trained Model
MaskRCNN-ResNet50 32.8 - - 127.8 M MaskRCNN-ResNet50.yaml Inference Model/Trained Model
MaskRCNN-ResNet101-FPN 36.6 - - 225.4 M MaskRCNN-ResNet101-FPN.yaml Inference Model/Trained Model
MaskRCNN-ResNet101-vd-FPN 38.1 - - 225.1 M MaskRCNN-ResNet101-vd-FPN.yaml Inference Model/Trained Model
MaskRCNN-ResNeXt101-vd-FPN 39.5 - - 370.0 M MaskRCNN-ResNeXt101-vd-FPN.yaml Inference Model/Trained Model
PP-YOLOE_seg-S 32.5 - - 31.5 M PP-YOLOE_seg-S.yaml Inference Model/Trained Model
|SOLOv2| 35.5|-|-|179.1 M|[SOLOv2.yaml](https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/configs/instance_segmentation/SOLOv2.yaml) Note: The above accuracy metrics are evaluated on the [COCO2017](https://cocodataset.org/#home) validation set using Mask AP(0.5:0.95). ## [Text Detection Module](../module_usage/tutorials/ocr_modules/text_detection.en.md)
Model Name Detection Hmean (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-OCRv4_mobile_det 77.79 10.6923 120.177 4.2 M PP-OCRv4_mobile_det.yaml Inference Model/Trained Model
PP-OCRv4_server_det 82.69 83.3501 2434.01 100.1M PP-OCRv4_server_det.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on a self-built Chinese dataset by PaddleOCR, covering street scenes, web images, documents, and handwritten texts, with 500 images for detection. ## [Seal Text Detection Module](../module_usage/tutorials/ocr_modules/seal_text_detection.en.md)
Model Name Detection Hmean (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-OCRv4_mobile_seal_det 96.47 10.5878 131.813 4.7 M PP-OCRv4_mobile_seal_det.yaml Inference Model/Trained Model
PP-OCRv4_server_seal_det 98.21 84.341 2425.06 108.3 M PP-OCRv4_server_seal_det.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on a self-built seal dataset by PaddleX, containing 500 seal images. ## [Text Recognition Module](../module_usage/tutorials/ocr_modules/text_recognition.en.md)
Model Name Recognition Avg Accuracy (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PP-OCRv4_mobile_rec 78.20 7.95018 46.7868 10.6 M PP-OCRv4_mobile_rec.yaml Inference Model/Trained Model
PP-OCRv4_server_rec 79.20 7.19439 140.179 71.2 M PP-OCRv4_server_rec.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on a self-built Chinese dataset by PaddleOCR, covering street scenes, web images, documents, and handwritten texts, with 11,000 images for text recognition.
Model Name Recognition Avg Accuracy (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
ch_SVTRv2_rec 68.81 8.36801 165.706 73.9 M ch_SVTRv2_rec.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on [PaddleOCR Algorithm Model Challenge - Task 1: OCR End-to-End Recognition](https://aistudio.baidu.com/competition/detail/1131/0/introduction) A-Rank.
Model Name Recognition Avg Accuracy (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
ch_RepSVTR_rec 65.07 10.5047 51.5647 22.1 M ch_RepSVTR_rec.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on [PaddleOCR Algorithm Model Challenge - Task 1: OCR End-to-End Recognition](https://aistudio.baidu.com/competition/detail/1131/0/introduction) B-Rank. ## [Formula Recognition Module](../module_usage/tutorials/ocr_modules/formula_recognition.en.md)
Model Name BLEU Score Normed Edit Distance ExpRate (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
LaTeX_OCR_rec 0.8821 0.0823 40.01 - - 89.7 M LaTeX_OCR_rec.yaml Inference Model/Trained Model
Note: The above accuracy metrics are measured on the [LaTeX-OCR formula recognition test set](https://drive.google.com/drive/folders/13CA4vAmOmD_I_dSbvLp-Lf0s6KiaNfuO). ## [Table Structure Recognition Module](../module_usage/tutorials/ocr_modules/table_structure_recognition.en.md)
Model Name Accuracy (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
SLANet 59.52 522.536 1845.37 6.9 M SLANet.yaml Inference Model/Trained Model
SLANet_plus 63.69 522.536 1845.37 6.9 M SLANet_plus.yaml Inference Model/Trained Model
Note: The above accuracy metrics are evaluated on a self-built English table recognition dataset by PaddleX. ## [Image Rectification Module](../module_usage/tutorials/ocr_modules/text_image_unwarping.en.md)
Model Name MS-SSIM (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
UVDoc 54.40 - - 30.3 M UVDoc.yaml Inference Model/Trained Model
Note: The above accuracy metrics are measured on a self-built image rectification dataset by PaddleX. ## [Layout Detection Module](../module_usage/tutorials/ocr_modules/layout_detection.en.md)
Model Name mAP (%) GPU Inference Time (ms) CPU Inference Time (ms) Model Size YAML File Model Download Link
PicoDet_layout_1x 86.8 13.036 91.2634 7.4 M PicoDet_layout_1x.yaml Inference Model/Trained Model
PicoDet_layout_1x_table 95.7 12.623 90.8934 7.4 M PicoDet_layout_1x_table.yaml Inference Model/Trained Model
PicoDet-S_layout_3cls 87.1 13.521 45.7633 4.8 M PicoDet-S_layout_3cls.yaml Inference Model/Trained Model
PicoDet-S_layout_17cls 70.3 13.5632 46.2059 4.8 M PicoDet-S_layout_17cls.yaml Inference Model/Trained Model
PicoDet-L_layout_3cls 89.3 15.7425 159.771 22.6 M PicoDet-L_layout_3cls.yaml Inference Model/Trained Model
PicoDet-L_layout_17cls 79.9 17.1901 160.262 22.6 M PicoDet-L_layout_17cls.yaml Inference Model/Trained Model
RT-DETR-H_layout_3cls 95.9 114.644 3832.62 470.1 M RT-DETR-H_layout_3cls.yaml Inference Model/Trained Model
RT-DETR-H_layout_17cls 92.6 115.126 3827.25 470.2 M RT-DETR-H_layout_17cls.yaml Inference Model/Trained Model
Note: The evaluation set for the above accuracy metrics is the PaddleX self-built Layout Detection Dataset, containing 10,000 images. ## [Time Series Forecasting Module](../module_usage/tutorials/time_series_modules/time_series_forecasting.en.md)
Model Name mse mae Model Size YAML File Model Download Link
DLinear 0.382 0.394 72 K DLinear.yaml Inference Model/Trained Model
NLinear 0.386 0.392 40 K NLinear.yaml Inference Model/Trained Model
Nonstationary 0.600 0.515 55.5 M Nonstationary.yaml Inference Model/Trained Model
PatchTST 0.385 0.397 2.0 M PatchTST.yaml Inference Model/Trained Model
RLinear 0.384 0.392 40 K RLinear.yaml Inference Model/Trained Model
TiDE 0.405 0.412 31.7 M TiDE.yaml Inference Model/Trained Model
TimesNet 0.417 0.431 4.9 M TimesNet.yaml Inference Model/Trained Model
Note: The above accuracy metrics are measured on the [ETTH1](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/Etth1.tar) dataset (evaluation results on the test set test.csv). ## [Time Series Anomaly Detection Module](../module_usage/tutorials/time_series_modules/time_series_anomaly_detection.en.md)
Model Name Precision Recall f1_score Model Size YAML File Model Download Link
AutoEncoder_ad 99.36 84.36 91.25 52 K AutoEncoder_ad.yaml Inference Model/Trained Model
DLinear_ad 98.98 93.96 96.41 112 K DLinear_ad.yaml Inference Model/Trained Model
Nonstationary_ad 98.55 88.95 93.51 1.8 M Nonstationary_ad.yaml Inference Model/Trained Model
PatchTST_ad 98.78 90.70 94.57 320 K PatchTST_ad.yaml Inference Model/Trained Model
TimesNet_ad 98.37 94.80 96.56 1.3 M TimesNet_ad.yaml Inference Model/Trained Model
Note: The above accuracy metrics are measured on the [PSM](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ts_anomaly_examples.tar) dataset. ## [Time Series Classification Module](../module_usage/tutorials/time_series_modules/time_series_classification.en.md)
Model Name acc (%) Model Size YAML File Model Download Link
TimesNet_cls 87.5 792 K TimesNet_cls.yaml Inference Model/Trained Model
Note: The above accuracy metrics are measured on the [UWaveGestureLibrary](https://paddlets.bj.bcebos.com/classification/UWaveGestureLibrary_TEST.csv) dataset. >Note: All GPU inference times for the above models are based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speeds are based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.