PaddlePaddle · cuicheng01 · Dec 15, 2021 · Dec 13, 2021 · Dec 14, 2021 · Dec 14, 2021
diff --git a/docs/zh_CN/algorithm_introduction/ImageNet_models.md b/docs/zh_CN/algorithm_introduction/ImageNet_models.md
diff --git a/docs/zh_CN/images/10w_cls.png b/docs/zh_CN/images/10w_cls.png
diff --git a/docs/zh_CN/images/PP-LCNet/PP-LCNet-Acc.png b/docs/zh_CN/images/PP-LCNet/PP-LCNet-Acc.png
diff --git a/docs/zh_CN/images/PP-LCNet/PP-LCNet.png b/docs/zh_CN/images/PP-LCNet/PP-LCNet.png
diff --git a/docs/zh_CN/images/VisualDL/train_loss.png b/docs/zh_CN/images/VisualDL/train_loss.png
diff --git a/docs/zh_CN/images/algorithm_introduction/fpgm.png b/docs/zh_CN/images/algorithm_introduction/fpgm.png
diff --git a/docs/zh_CN/images/algorithm_introduction/quantization.jpg b/docs/zh_CN/images/algorithm_introduction/quantization.jpg
diff --git a/docs/zh_CN/images/algorithm_introduction/quantization_formula.png b/docs/zh_CN/images/algorithm_introduction/quantization_formula.png
diff --git a/docs/zh_CN/images/algorithm_introduction/quantization_formula_slim.png b/docs/zh_CN/images/algorithm_introduction/quantization_formula_slim.png
diff --git a/docs/zh_CN/images/det/PaddleDetection_config.png b/docs/zh_CN/images/det/PaddleDetection_config.png
diff --git a/docs/zh_CN/images/det/pssdet.png b/docs/zh_CN/images/det/pssdet.png
diff --git a/docs/zh_CN/images/distillation/22k_1k_val_compare_w_sift.png b/docs/zh_CN/images/distillation/22k_1k_val_compare_w_sift.png
diff --git a/docs/zh_CN/images/distillation/distillation_perform.png b/docs/zh_CN/images/distillation/distillation_perform.png
diff --git a/docs/zh_CN/images/distillation/distillation_perform_s.jpg b/docs/zh_CN/images/distillation/distillation_perform_s.jpg
diff --git a/docs/zh_CN/images/distillation/ppcls_distillation.png b/docs/zh_CN/images/distillation/ppcls_distillation.png
diff --git a/docs/zh_CN/images/distillation/ppcls_distillation_s.jpg b/docs/zh_CN/images/distillation/ppcls_distillation_s.jpg
diff --git a/docs/zh_CN/images/faq/ACNetFusion.png b/docs/zh_CN/images/faq/ACNetFusion.png
diff --git a/docs/zh_CN/images/faq/ACNetReParams.png b/docs/zh_CN/images/faq/ACNetReParams.png
diff --git a/docs/zh_CN/images/faq/DeployedACNet.png b/docs/zh_CN/images/faq/DeployedACNet.png
diff --git a/docs/zh_CN/images/faq/HRNet.png b/docs/zh_CN/images/faq/HRNet.png
diff --git a/docs/zh_CN/images/faq/HRNet_block.png b/docs/zh_CN/images/faq/HRNet_block.png
diff --git a/docs/zh_CN/images/faq/HorizontalKernel.png b/docs/zh_CN/images/faq/HorizontalKernel.png
diff --git a/docs/zh_CN/images/faq/MemoryOccupation.png b/docs/zh_CN/images/faq/MemoryOccupation.png
diff --git a/docs/zh_CN/images/faq/RepVGG.png b/docs/zh_CN/images/faq/RepVGG.png
diff --git a/docs/zh_CN/images/faq/RepVGGReParams.png b/docs/zh_CN/images/faq/RepVGGReParams.png
diff --git a/docs/zh_CN/images/faq/ResNet_vabcd_structure.png b/docs/zh_CN/images/faq/ResNet_vabcd_structure.png
diff --git a/docs/zh_CN/images/faq/SE_structure.png b/docs/zh_CN/images/faq/SE_structure.png
diff --git a/docs/zh_CN/images/faq/TrainingtimeACNet.png b/docs/zh_CN/images/faq/TrainingtimeACNet.png
diff --git a/docs/zh_CN/images/faq/Transformer_input.png b/docs/zh_CN/images/faq/Transformer_input.png
diff --git a/docs/zh_CN/images/faq/ViT.png b/docs/zh_CN/images/faq/ViT.png
diff --git a/docs/zh_CN/images/faq/ViT_structure.png b/docs/zh_CN/images/faq/ViT_structure.png
diff --git a/docs/zh_CN/images/faq/momentum.jpeg b/docs/zh_CN/images/faq/momentum.jpeg
diff --git a/docs/zh_CN/images/feature_maps/feature_visualization_input.jpg b/docs/zh_CN/images/feature_maps/feature_visualization_input.jpg
diff --git a/docs/zh_CN/images/feature_maps/feature_visualization_output.jpg b/docs/zh_CN/images/feature_maps/feature_visualization_output.jpg
diff --git a/docs/zh_CN/images/icartoon1.png b/docs/zh_CN/images/icartoon1.png
diff --git a/docs/zh_CN/images/icartoon2.jpeg b/docs/zh_CN/images/icartoon2.jpeg
diff --git a/docs/zh_CN/images/image_aug/gridmask-0.png b/docs/zh_CN/images/image_aug/gridmask-0.png
diff --git a/docs/zh_CN/images/image_aug/hide-and-seek-visual.png b/docs/zh_CN/images/image_aug/hide-and-seek-visual.png
diff --git a/docs/zh_CN/images/image_aug/image_aug_samples.png b/docs/zh_CN/images/image_aug/image_aug_samples.png
diff --git a/docs/zh_CN/images/image_aug/image_aug_samples_s.jpg b/docs/zh_CN/images/image_aug/image_aug_samples_s.jpg
diff --git a/docs/zh_CN/images/image_aug/image_aug_samples_s_en.jpg b/docs/zh_CN/images/image_aug/image_aug_samples_s_en.jpg
diff --git a/docs/zh_CN/images/image_aug/main_image_aug.png b/docs/zh_CN/images/image_aug/main_image_aug.png
diff --git a/docs/zh_CN/images/image_aug/main_image_aug_s.jpg b/docs/zh_CN/images/image_aug/main_image_aug_s.jpg
diff --git a/docs/zh_CN/images/image_aug/test_autoaugment.jpeg b/docs/zh_CN/images/image_aug/test_autoaugment.jpeg
diff --git a/docs/zh_CN/images/image_aug/test_baseline.jpeg b/docs/zh_CN/images/image_aug/test_baseline.jpeg
diff --git a/docs/zh_CN/images/image_aug/test_cutmix.png b/docs/zh_CN/images/image_aug/test_cutmix.png
diff --git a/docs/zh_CN/images/image_aug/test_cutout.jpeg b/docs/zh_CN/images/image_aug/test_cutout.jpeg
diff --git a/docs/zh_CN/images/image_aug/test_gridmask.jpeg b/docs/zh_CN/images/image_aug/test_gridmask.jpeg
diff --git a/docs/zh_CN/images/image_aug/test_hideandseek.jpeg b/docs/zh_CN/images/image_aug/test_hideandseek.jpeg
diff --git a/docs/zh_CN/images/image_aug/test_mixup.png b/docs/zh_CN/images/image_aug/test_mixup.png
diff --git a/docs/zh_CN/images/image_aug/test_randaugment.jpeg b/docs/zh_CN/images/image_aug/test_randaugment.jpeg
diff --git a/docs/zh_CN/images/image_aug/test_randomerassing.jpeg b/docs/zh_CN/images/image_aug/test_randomerassing.jpeg
diff --git a/docs/zh_CN/images/inference_deployment/cpp_infer_result.png b/docs/zh_CN/images/inference_deployment/cpp_infer_result.png
diff --git a/docs/zh_CN/images/inference_deployment/lite_demo_result.png b/docs/zh_CN/images/inference_deployment/lite_demo_result.png
diff --git a/docs/zh_CN/images/inference_deployment/vs2019_step1.png b/docs/zh_CN/images/inference_deployment/vs2019_step1.png
diff --git a/docs/zh_CN/images/inference_deployment/vs2019_step2.png b/docs/zh_CN/images/inference_deployment/vs2019_step2.png
diff --git a/docs/zh_CN/images/inference_deployment/vs2019_step3.png b/docs/zh_CN/images/inference_deployment/vs2019_step3.png
diff --git a/docs/zh_CN/images/inference_deployment/vs2019_step4.png b/docs/zh_CN/images/inference_deployment/vs2019_step4.png
diff --git a/docs/zh_CN/images/inference_deployment/vs2019_step5.png b/docs/zh_CN/images/inference_deployment/vs2019_step5.png
diff --git a/docs/zh_CN/images/inference_deployment/vs2019_step6.png b/docs/zh_CN/images/inference_deployment/vs2019_step6.png
diff --git a/docs/zh_CN/images/inference_deployment/whl_demo.jpg b/docs/zh_CN/images/inference_deployment/whl_demo.jpg
diff --git a/docs/zh_CN/images/joinus.png b/docs/zh_CN/images/joinus.png
diff --git a/docs/zh_CN/images/logo.png b/docs/zh_CN/images/logo.png
diff --git a/docs/zh_CN/images/logo/logodet3k.jpg b/docs/zh_CN/images/logo/logodet3k.jpg
diff --git a/docs/zh_CN/images/main_features.png b/docs/zh_CN/images/main_features.png
diff --git a/docs/zh_CN/images/main_features_s.png b/docs/zh_CN/images/main_features_s.png
diff --git a/docs/zh_CN/images/main_features_s_en.png b/docs/zh_CN/images/main_features_s_en.png
diff --git a/docs/zh_CN/images/mainpage/cartoon_vis_en_v1.0.gif b/docs/zh_CN/images/mainpage/cartoon_vis_en_v1.0.gif
diff --git a/docs/zh_CN/images/mainpage/cartoon_vis_v1.0.gif b/docs/zh_CN/images/mainpage/cartoon_vis_v1.0.gif
diff --git a/docs/zh_CN/images/mainpage/logo_vis_en_v1.0.gif b/docs/zh_CN/images/mainpage/logo_vis_en_v1.0.gif
diff --git a/docs/zh_CN/images/mainpage/logo_vis_v1.0.gif b/docs/zh_CN/images/mainpage/logo_vis_v1.0.gif
diff --git a/docs/zh_CN/images/mainpage/product_vis_en_v1.0.gif b/docs/zh_CN/images/mainpage/product_vis_en_v1.0.gif
diff --git a/docs/zh_CN/images/mainpage/product_vis_v1.0.gif b/docs/zh_CN/images/mainpage/product_vis_v1.0.gif
diff --git a/docs/zh_CN/images/mainpage/recognition_pipeline_en.png b/docs/zh_CN/images/mainpage/recognition_pipeline_en.png
diff --git a/docs/zh_CN/images/mainpage/vehicle_vis_en_v1.0.gif b/docs/zh_CN/images/mainpage/vehicle_vis_en_v1.0.gif
diff --git a/docs/zh_CN/images/ml_illustration.jpg b/docs/zh_CN/images/ml_illustration.jpg
diff --git a/docs/zh_CN/images/ml_pipeline.jpg b/docs/zh_CN/images/ml_pipeline.jpg
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs1.EfficientNet.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs1.EfficientNet.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.DPN.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.DPN.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.HRNet.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.HRNet.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.Inception.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.Inception.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.ResNet.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.ResNet.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.SeResNeXt.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp16.bs4.SeResNeXt.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs1.EfficientNet.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs1.EfficientNet.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs1.main_fps_top1.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs1.main_fps_top1.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.DPN.flops.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.DPN.flops.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.DPN.params.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.DPN.params.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.DPN.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.DPN.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.EfficientNet.flops.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.EfficientNet.flops.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.EfficientNet.params.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.EfficientNet.params.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.HRNet.flops.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.HRNet.flops.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.HRNet.params.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.HRNet.params.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.HRNet.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.HRNet.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.Inception.flops.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.Inception.flops.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.Inception.params.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.Inception.params.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.Inception.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.Inception.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.ResNet.flops.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.ResNet.flops.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.ResNet.params.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.ResNet.params.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.ResNet.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.ResNet.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.SeResNeXt.flops.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.SeResNeXt.flops.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.SeResNeXt.params.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.SeResNeXt.params.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.SeResNeXt.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.SeResNeXt.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.main_fps_top1.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.main_fps_top1.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.mobile_trt.flops.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.mobile_trt.flops.png
diff --git a/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.mobile_trt.params.png b/docs/zh_CN/images/models/T4_benchmark/t4.fp32.bs4.mobile_trt.params.png
diff --git a/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.DPN.png b/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.DPN.png
diff --git a/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.EfficientNet.png b/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.EfficientNet.png
diff --git a/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.HRNet.png b/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.HRNet.png
diff --git a/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.Inception.png b/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.Inception.png
diff --git a/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.ResNet.png b/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.ResNet.png
diff --git a/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.SeResNeXt.png b/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.SeResNeXt.png
diff --git a/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.main_fps_top1_s.jpg b/docs/zh_CN/images/models/V100_benchmark/v100.fp32.bs1.main_fps_top1_s.jpg
diff --git a/docs/zh_CN/images/models/lr_decay.jpeg b/docs/zh_CN/images/models/lr_decay.jpeg
diff --git a/docs/zh_CN/images/models/mobile_arm_storage.png b/docs/zh_CN/images/models/mobile_arm_storage.png
diff --git a/docs/zh_CN/images/models/mobile_arm_top1.png b/docs/zh_CN/images/models/mobile_arm_top1.png
diff --git a/docs/zh_CN/images/paddlepaddle.jpg b/docs/zh_CN/images/paddlepaddle.jpg
diff --git a/docs/zh_CN/images/product/aliproduct.png b/docs/zh_CN/images/product/aliproduct.png
diff --git a/docs/zh_CN/images/product/inshop.png b/docs/zh_CN/images/product/inshop.png
diff --git a/docs/zh_CN/images/qq_group.png b/docs/zh_CN/images/qq_group.png
diff --git a/docs/zh_CN/images/quick_start/Examples-Flower-102.png b/docs/zh_CN/images/quick_start/Examples-Flower-102.png
diff --git a/docs/zh_CN/images/quick_start/all_acc.png b/docs/zh_CN/images/quick_start/all_acc.png
diff --git a/docs/zh_CN/images/quick_start/community/001_fork.png b/docs/zh_CN/images/quick_start/community/001_fork.png
diff --git a/docs/zh_CN/images/quick_start/community/002_clone.png b/docs/zh_CN/images/quick_start/community/002_clone.png
diff --git a/docs/zh_CN/images/quick_start/community/003_precommit_pass.png b/docs/zh_CN/images/quick_start/community/003_precommit_pass.png
diff --git a/docs/zh_CN/images/quick_start/community/004_create_pr.png b/docs/zh_CN/images/quick_start/community/004_create_pr.png
diff --git a/docs/zh_CN/images/quick_start/community/code_framework.png b/docs/zh_CN/images/quick_start/community/code_framework.png
diff --git a/docs/zh_CN/images/quick_start/community/train_framework.png b/docs/zh_CN/images/quick_start/community/train_framework.png
diff --git a/docs/zh_CN/images/quick_start/flowers102/image_06739.jpg b/docs/zh_CN/images/quick_start/flowers102/image_06739.jpg
diff --git a/docs/zh_CN/images/quick_start/flowers102/image_06767.jpg b/docs/zh_CN/images/quick_start/flowers102/image_06767.jpg
diff --git a/docs/zh_CN/images/quick_start/flowers102/image_06773.jpg b/docs/zh_CN/images/quick_start/flowers102/image_06773.jpg
diff --git a/docs/zh_CN/images/quick_start/r50_vd_acc.png b/docs/zh_CN/images/quick_start/r50_vd_acc.png
diff --git a/docs/zh_CN/images/quick_start/r50_vd_pretrained_acc.png b/docs/zh_CN/images/quick_start/r50_vd_pretrained_acc.png
diff --git a/docs/zh_CN/images/recognition.gif b/docs/zh_CN/images/recognition.gif
diff --git a/docs/zh_CN/images/recognition/logo_demo/gallery/logo_gallery_demo.png b/docs/zh_CN/images/recognition/logo_demo/gallery/logo_gallery_demo.png
diff --git a/docs/zh_CN/images/recognition/logo_demo/query/logo_auxx-1.jpg b/docs/zh_CN/images/recognition/logo_demo/query/logo_auxx-1.jpg
diff --git a/docs/zh_CN/images/recognition/logo_demo/query/logo_cola.jpg b/docs/zh_CN/images/recognition/logo_demo/query/logo_cola.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/001.jpg b/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/001.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/002.jpg b/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/002.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/003.jpg b/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/003.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/004.jpg b/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/004.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/005.jpg b/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/005.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/006.jpg b/docs/zh_CN/images/recognition/product_demo/gallery/anmuxi/006.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/query/anmuxi.jpg b/docs/zh_CN/images/recognition/product_demo/query/anmuxi.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/query/daoxiangcunjinzhubing_6.jpg b/docs/zh_CN/images/recognition/product_demo/query/daoxiangcunjinzhubing_6.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/result/anmuxi.jpg b/docs/zh_CN/images/recognition/product_demo/result/anmuxi.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/result/anmuxi_en.jpg b/docs/zh_CN/images/recognition/product_demo/result/anmuxi_en.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/result/daoxiangcunjinzhubing_6.jpg b/docs/zh_CN/images/recognition/product_demo/result/daoxiangcunjinzhubing_6.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/result/daoxiangcunjinzhubing_6_en.jpg b/docs/zh_CN/images/recognition/product_demo/result/daoxiangcunjinzhubing_6_en.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/wangzai.jpg b/docs/zh_CN/images/recognition/product_demo/wangzai.jpg
diff --git a/docs/zh_CN/images/recognition/product_demo/wangzai_det_result.jpg b/docs/zh_CN/images/recognition/product_demo/wangzai_det_result.jpg
diff --git a/docs/zh_CN/images/recognition/rec_pipeline.png b/docs/zh_CN/images/recognition/rec_pipeline.png
diff --git a/docs/zh_CN/images/recognition/vehicle/CompCars.png b/docs/zh_CN/images/recognition/vehicle/CompCars.png
diff --git a/docs/zh_CN/images/recognition/vehicle/cars.JPG b/docs/zh_CN/images/recognition/vehicle/cars.JPG
diff --git a/docs/zh_CN/images/recognition_en.gif b/docs/zh_CN/images/recognition_en.gif
diff --git a/docs/zh_CN/images/structure.png b/docs/zh_CN/images/structure.png
diff --git a/docs/zh_CN/images/whl/demo.jpg b/docs/zh_CN/images/whl/demo.jpg
diff --git a/docs/zh_CN/images/wx_group.png b/docs/zh_CN/images/wx_group.png
diff --git a/docs/zh_CN/introduction/more_demo/more_demo.md b/docs/zh_CN/introduction/more_demo/more_demo.md
@@ -28,7 +28,7 @@
 <div align="center"> <img src="https://user-images.githubusercontent.com/12560511/140096767-e8f701eb-d0e8-4304-b031-e2bff8c199f3.jpeg" width = "400" /> </div>
 
 
-[更多效果图](../../images/recognition/more_demo_images/logo.md)
+[更多效果图](logo.md)
 
 
 - 车辆识别

diff --git a/docs/zh_CN/models/DLA.md b/docs/zh_CN/models/DLA.md
@@ -3,6 +3,7 @@
 ## 目录
 * [1. 概述](#1)
 * [2. 精度、FLOPS 和参数量](#2)
+* [3. 基于 V100 GPU 的预测速度](#3)
 
 <a name='1'></a>
 
@@ -25,4 +26,20 @@ DLA(Deep Layer Aggregation)。 视觉识别需要丰富的表示形式，其范
 | DLA102 | 33.3 | 7.2 | 78.93 | 94.52 |
 | DLA102x | 26.4 | 5.9 | 78.10 | 94.00 |
 | DLA102x2 | 41.4 | 9.3 | 78.85 | 94.45 |
-| DLA169 | 53.5 | 11.6 | 78.09 | 94.09 |
+| DLA169 | 53.5 | 11.6 | 78.09 | 94.09 |
+
+<a name='3'></a>
+
+## 3. 基于 V100 GPU 的预测速度
+
+| 模型 | Crop Size | Resize Short Size | FP32<br/>Batch Size=1<br/>(ms) | FP32<br/>Batch Size=4<br/>(ms) | FP32<br/>Batch Size=8<br/>(ms) |
+| -------- | --------- | ----------------- | ------------------------------ | ------------------------------ | ------------------------------ |
+| DLA102 | 224 | 256 | 4.95 | 8.08 | 12.40 |
+| DLA102x2 | 224 | 256 | 19.58 | 23.97 | 31.37 |
+| DLA102x | 224 | 256 | 11.12 | 15.60 | 20.37 |
+| DLA169 | 224 | 256 | 7.70 | 12.25 | 18.90 |
+| DLA34 | 224 | 256 | 1.83 | 3.37 | 5.98 |
+| DLA46_c | 224 | 256 | 1.06 | 2.08 | 3.23 |
+| DLA60 | 224 | 256 | 2.78 | 5.36 | 8.29 |
+| DLA60x_c | 224 | 256 | 1.79 | 3.68 | 5.19 |
+| DLA60x | 224 | 256 | 5.98 | 9.24 | 12.52 |
diff --git a/docs/zh_CN/models/DPN_DenseNet.md b/docs/zh_CN/models/DPN_DenseNet.md
@@ -12,7 +12,7 @@
 ## 1. 概述
 DenseNet 是 2017 年 CVPR best paper 提出的一种新的网络结构，该网络设计了一种新的跨层连接的 block，即 dense-block。相比 ResNet 中的 bottleneck，dense-block 设计了一个更激进的密集连接机制，即互相连接所有的层，每个层都会接受其前面所有层作为其额外的输入。DenseNet 将所有的 dense-block 堆叠，组合成了一个密集连接型网络。密集的连接方式使得 DenseNe 更容易进行梯度的反向传播，使得网络更容易训练。
 DPN 的全称是 Dual Path Networks，即双通道网络。该网络是由 DenseNet 和 ResNeXt 结合的一个网络，其证明了 DenseNet 能从靠前的层级中提取到新的特征，而 ResNeXt 本质上是对之前层级中已提取特征的复用。作者进一步分析发现，ResNeXt 对特征有高复用率，但冗余度低，DenseNet 能创造新特征，但冗余度高。结合二者结构的优势，作者设计了 DPN 网络。最终 DPN 网络在同样 FLOPS 和参数量下，取得了比 ResNeXt 与 DenseNet 更好的结果。
- 
+
 该系列模型的 FLOPS、参数量以及 T4 GPU 上的预测耗时如下图所示。
 
 ![](../../images/models/T4_benchmark/t4.fp32.bs4.DPN.flops.png)
@@ -48,18 +48,18 @@ DPN 的全称是 Dual Path Networks，即双通道网络。该网络是由 Dense
  <a name='3'></a>
 ## 3. 基于 V100 GPU 的预测速度
 
-| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
-|-------------|-----------|-------------------|--------------------------|
-| DenseNet121 | 224 | 256 | 4.371 |
-| DenseNet161 | 224 | 256 | 8.863 |
-| DenseNet169 | 224 | 256 | 6.391 |
-| DenseNet201 | 224 | 256 | 8.173 |
-| DenseNet264 | 224 | 256 | 11.942 |
-| DPN68 | 224 | 256 | 11.805 |
-| DPN92 | 224 | 256 | 17.840 |
-| DPN98 | 224 | 256 | 21.057 |
-| DPN107 | 224 | 256 | 28.685 |
-| DPN131 | 224 | 256 | 28.083 |
+| Models | Crop Size | Resize Short Size | FP32<br/>Batch Size=1<br/>(ms) | FP32<br/>Batch Size=4<br/>(ms) | FP32<br/>Batch Size=8<br/>(ms) |
+|-------------|-----------|-------------------|-------------------|-------------------|-------------------|
+| DenseNet121 | 224 | 256 | 3.40  | 6.94 | 9.17 |
+| DenseNet161 | 224 | 256 | 7.06  | 14.37 | 19.55 |
+| DenseNet169 | 224 | 256 | 5.00  | 10.29 | 12.84 |
+| DenseNet201 | 224 | 256 | 6.38  | 13.72 | 17.17 |
+| DenseNet264 | 224 | 256 | 9.34  | 20.95 | 25.41 |
+| DPN68 | 224 | 256 | 8.18 | 11.40  | 14.82 |
+| DPN92 | 224 | 256 | 12.48  | 20.04 | 25.10 |
+| DPN98 | 224 | 256 | 14.70  | 25.55 | 35.12 |
+| DPN107 | 224 | 256 | 19.46  | 35.62 | 50.22 |
+| DPN131 | 224 | 256 | 19.64  | 34.60 | 47.42 |
 
 
 <a name='4'></a>

diff --git a/docs/zh_CN/models/EfficientNet_and_ResNeXt101_wsl.md b/docs/zh_CN/models/EfficientNet_and_ResNeXt101_wsl.md
@@ -50,22 +50,22 @@ ResNeXt 是 facebook 于 2016 年提出的一种对 ResNet 的改进版网络。
 
 ## 3. 基于 V100 GPU 的预测速度
 
-| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
-|-------------------------------|-----------|-------------------|--------------------------|
-| ResNeXt101_<br>32x8d_wsl | 224 | 256 | 19.127  |
-| ResNeXt101_<br>32x16d_wsl | 224 | 256 | 23.629  |
-| ResNeXt101_<br>32x32d_wsl | 224 | 256 | 40.214  |
-| ResNeXt101_<br>32x48d_wsl | 224 | 256 | 59.714  |
-| Fix_ResNeXt101_<br>32x48d_wsl | 320 | 320 | 82.431  |
-| EfficientNetB0 | 224 | 256 | 2.449  |
-| EfficientNetB1 | 240 | 272 | 3.547  |
-| EfficientNetB2 | 260 | 292 | 3.908  |
-| EfficientNetB3 | 300 | 332 | 5.145  |
-| EfficientNetB4 | 380 | 412 | 7.609  |
-| EfficientNetB5 | 456 | 488 | 12.078  |
-| EfficientNetB6 | 528 | 560 | 18.381  |
-| EfficientNetB7 | 600 | 632 | 27.817  |
-| EfficientNetB0_<br>small | 224 | 256 | 1.692  |
+| Models | Crop Size | Resize Short Size | FP32<br/>Batch Size=1<br/>(ms) | FP32<br/>Batch Size=4<br/>(ms) | FP32<br/>Batch Size=8<br/>(ms) |
+|-------------------------------|-----------|-------------------|-------------------------------|-------------------------------|-------------------------------|
+| ResNeXt101_<br>32x8d_wsl | 224 | 256 | 13.55 | 23.39 | 36.18 |
+| ResNeXt101_<br>32x16d_wsl | 224 | 256 | 21.96 | 38.35 | 63.29 |
+| ResNeXt101_<br>32x32d_wsl | 224 | 256 | 37.28 | 76.50 | 121.56 |
+| ResNeXt101_<br>32x48d_wsl | 224 | 256 | 55.07 | 124.39 | 205.01 |
+| Fix_ResNeXt101_<br>32x48d_wsl | 320 | 320 | 55.01 | 122.63 | 204.66 |
+| EfficientNetB0 | 224 | 256 | 1.96 | 3.71 | 5.56 |
+| EfficientNetB1 | 240 | 272 | 2.88 | 5.40 | 7.63 |
+| EfficientNetB2 | 260 | 292 | 3.26 | 6.20 | 9.17 |
+| EfficientNetB3 | 300 | 332 | 4.52 | 8.85 | 13.54 |
+| EfficientNetB4 | 380 | 412 | 6.78 | 15.47 | 24.95 |
+| EfficientNetB5 | 456 | 488 | 10.97 | 27.24 | 45.93 |
+| EfficientNetB6 | 528 | 560 | 17.09 | 43.32 | 76.90 |
+| EfficientNetB7 | 600 | 632 | 25.91 | 71.23 | 128.20 |
+| EfficientNetB0_<br>small | 224 | 256 | 1.24 | 2.59 | 3.92 |
 
 
 <a name='4'></a>

diff --git a/docs/zh_CN/models/HRNet.md b/docs/zh_CN/models/HRNet.md
@@ -43,17 +43,17 @@ HRNet 是 2019 年由微软亚洲研究院提出的一种全新的神经网络
  <a name='3'></a>
 ## 3. 基于 V100 GPU 的预测速度
 
-| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
-|-------------|-----------|-------------------|--------------------------|
-| HRNet_W18_C | 224 | 256 | 7.368 |
-| HRNet_W18_C_ssld | 224 | 256 | 7.368 |
-| HRNet_W30_C | 224 | 256 | 9.402 |
-| HRNet_W32_C | 224 | 256 | 9.467 |
-| HRNet_W40_C | 224 | 256 | 10.739 |
-| HRNet_W44_C | 224 | 256 | 11.497 |
-| HRNet_W48_C | 224 | 256 | 12.165 |
-| HRNet_W48_C_ssld | 224 | 256 | 12.165 |
-| HRNet_W64_C | 224 | 256 | 15.003 |
+| Models | Crop Size | Resize Short Size | FP32<br/>Batch Size=1<br/>(ms) | FP32<br/>Batch Size=4<br/>(ms) | FP32<br/>Batch Size=8<br/>(ms) |
+|-------------|-----------|-------------------|-------------------|-------------------|-------------------|
+| HRNet_W18_C | 224 | 256 | 6.66  | 8.94 | 11.95 |
+| HRNet_W18_C_ssld | 224 | 256 | 6.66  | 8.92 | 11.93 |
+| HRNet_W30_C | 224 | 256 | 8.61  | 11.40 | 15.23 |
+| HRNet_W32_C | 224 | 256 | 8.54  | 11.58 | 15.57 |
+| HRNet_W40_C | 224 | 256 | 9.83  | 15.02 | 20.92 |
+| HRNet_W44_C | 224 | 256 | 10.62  | 16.18 | 25.92 |
+| HRNet_W48_C | 224 | 256 | 11.07  | 17.06 | 27.28 |
+| HRNet_W48_C_ssld | 224 | 256 | 11.09 | 17.04 | 27.28  |
+| HRNet_W64_C | 224 | 256 | 13.82  | 21.15 | 35.51 |
 
 
  <a name='4'></a>

diff --git a/docs/zh_CN/models/HarDNet.md b/docs/zh_CN/models/HarDNet.md
@@ -4,6 +4,7 @@
 
 * [1. 概述](#1)
 * [2. 精度、FLOPS 和参数量](#2)
+* [3. 基于 V100 GPU 的预测速度](#3)
 
  <a name='1'></a>
 ## 1. 概述
@@ -20,3 +21,15 @@ HarDNet（Harmonic DenseNet）是 2019 年由国立清华大学提出的一种
 | HarDNet85 | 36.7 | 9.1 | 77.44 | 93.55 |
 | HarDNet39_ds | 3.5 | 0.4 | 71.33 | 89.98 |
 | HarDNet68_ds | 4.2 | 0.8 | 73.62 | 91.52 |
+
+<a name='3'></a>
+
+## 3. 基于 V100 GPU 的预测速度
+
+| Models | Crop Size | Resize Short Size | FP32<br/>Batch Size=1<br/>(ms) | FP32<br/>Batch Size=4<br/>(ms) | FP32<br/>Batch Size=8<br/>(ms) |
+| ------------ | --------- | ----------------- | ------------------------------ | ------------------------------ | ------------------------------ |
+| HarDNet68 | 224 | 256 | 3.58 | 8.53 | 11.58 |
+| HarDNet85 | 224 | 256 | 6.24 | 14.85 | 20.57 |
+| HarDNet39_ds | 224 | 256 | 1.40 | 2.30 | 3.33 |
+| HarDNet68_ds | 224 | 256 | 2.26 | 3.34 | 5.06 |
+
diff --git a/docs/zh_CN/models/Inception.md b/docs/zh_CN/models/Inception.md
@@ -53,15 +53,15 @@ InceptionV4 是 2016 年由 Google 设计的新的神经网络，当时残差结
 
 ## 3. 基于 V100 GPU 的预测速度
 
-| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
-|------------------------|-----------|-------------------|--------------------------|
-| GoogLeNet | 224 | 256 | 1.807  |
-| Xception41 | 299 | 320 | 3.972  |
-| Xception41_<br>deeplab | 299 | 320 | 4.408  |
-| Xception65 | 299 | 320 | 6.174  |
-| Xception65_<br>deeplab | 299 | 320 | 6.464  |
-| Xception71 | 299 | 320 | 6.782  |
-| InceptionV4 | 299 | 320 | 11.141  |
+| Models | Crop Size | Resize Short Size | FP32<br/>Batch Size=1<br/>(ms) | FP32<br/>Batch Size=4<br/>(ms) | FP32<br/>Batch Size=8<br/>(ms) |
+|------------------------|-----------|-------------------|------------------------|------------------------|------------------------|
+| GoogLeNet | 224 | 256 | 1.41 | 3.25 | 5.00 |
+| Xception41 | 299 | 320 | 3.58 | 8.76 | 16.61 |
+| Xception41_<br>deeplab | 299 | 320 | 3.81 | 9.16 | 17.20 |
+| Xception65 | 299 | 320 | 5.45 | 12.78 | 24.53 |
+| Xception65_<br>deeplab | 299 | 320 | 5.65 | 13.08 | 24.61 |
+| Xception71 | 299 | 320 | 6.19 | 15.34 | 29.21 |
+| InceptionV4 | 299 | 320 | 8.93 | 15.17 | 21.56 |
 
 
  <a name='4'></a>

diff --git a/docs/zh_CN/models/MixNet.md b/docs/zh_CN/models/MixNet.md
@@ -4,6 +4,7 @@
 
 * [1. 概述](#1)
 * [2. 精度、FLOPS 和参数量](#2)
+* [3. 基于 V100 GPU 的预测速度](#3)
 
 <a name='1'></a>
 
@@ -26,4 +27,14 @@ MixNet 是谷歌出的一篇关于轻量级网络的文章，主要工作就在
 | MixNet_M | 77.67 | 93.64 | 77.0 | 357.119 | 5.065 |
 | MixNet_L | 78.60 | 94.37 | 78.9 | 579.017 | 7.384 |
 
+<a name='3'></a>
+
+## 3. 基于 V100 GPU 的预测速度
+
+| Models | Crop Size | Resize Short Size | FP32<br/>Batch Size=1<br/>(ms) | FP32<br/>Batch Size=4<br/>(ms) | FP32<br/>Batch Size=8<br/>(ms) |
+| -------- | --------- | ----------------- | ------------------------------ | ------------------------------ | ------------------------------ |
+| MixNet_S | 224 | 256 | 2.31 | 3.63 | 5.20 |
+| MixNet_M | 224 | 256 | 2.84 | 4.60 | 6.62 |
+| MixNet_L | 224 | 256 | 3.16 | 5.55 | 8.03 |
+
 关于 Inference speed 等信息，敬请期待。