关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
PaddlePaddle
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas
Not watched
5
1
Fork 5
Code
Releases 11 Wiki Activity
Issues 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
2147 Commits
19 Branches
760 MiB
832 Download
 
 
 
 
 
 
Tree: 2.2.0
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '2.2.0'
${ noResults }
Wei Shengyu a6d927a122
Merge pull request #869 from PaddlePaddle/develop 		2 years ago
.travis add hook 4 years ago
dataset/flowers102 rename datasets->dataset 2 years ago
deploy Update build_gallery.py 2 years ago
docs Update getting_started.md 2 years ago
ppcls Merge pull request #867 from cuicheng01/develop 2 years ago
tools merge develop (#859) 2 years ago
.clang_format.hook polish dygraph doc and deploy 3 years ago
.gitignore move files 3 years ago
.pre-commit-config.yaml add dataloader inferface 3 years ago
LICENSE Initial commit 4 years ago
MANIFEST.in support bs>1 (#651) 3 years ago
README.md Update README 2 years ago
README_cn.md Merge pull request #858 from cuicheng01/develop_reg 2 years ago
__init__.py PaddleClas-whl (#536) 3 years ago
hubconf.py update comments 3 years ago
paddleclas.py Add __init__.py (#750) 3 years ago
requirements.txt Add SwinTransformer (#721) 3 years ago
setup.py PaddleClas-whl (#536) 3 years ago

README.md

简体中文 | English

PaddleClas

Introduction

PaddleClas is a toolset for image classification tasks prepared for the industry and academia. It helps users train better computer vision models and apply them in real scenarios.

Recent update

  • 2021.06.16 PaddleClas release/2.2.
    • Add metric learning and vector search module.
    • Add product recognition, cartoon character recognition, car recognition and logo recognition.
    • Added 30 pretrained models of LeViT, Twins, TNT, DLA, HarDNet, and RedNet, and the accuracy is roughly the same as that of the paper.
  • more

Features

  • Rich model zoo. Based on the ImageNet-1k classification dataset, PaddleClas provides 29 series of classification network structures and training configurations, 134 models' pretrained weights and their evaluation metrics.

  • SSLD Knowledge Distillation. Based on this SSLD distillation strategy, the top-1 acc of the distilled model is generally increased by more than 3%.

  • Data augmentation: PaddleClas provides detailed introduction of 8 data augmentation algorithms such as AutoAugment, Cutout, Cutmix, code reproduction and effect evaluation in a unified experimental environment.

  • Pretrained model with 100,000 categories: Based on ResNet50_vd model, Baidu open sourced the ResNet50_vd pretrained model trained on a 100,000-category dataset. In some practical scenarios, the accuracy based on the pretrained weights can be increased by up to 30%.

  • A variety of training modes, including multi-machine training, mixed precision training, etc.

  • A variety of inference and deployment solutions, including TensorRT inference, Paddle-Lite inference, model service deployment, model quantification, Paddle Hub, etc.

  • Support Linux, Windows, macOS and other systems.

Community

  • Scan the QR code below with your Wechat and send the message 分类 out, then you will be invited into the official technical exchange group.
  • You can also scan the QQ group QR code to enter the PaddleClas QQ group. Look forward to your participation.

Tutorials

Model zoo overview

Based on the ImageNet-1k classification dataset, the 24 classification network structures supported by PaddleClas and the corresponding 122 image classification pretrained models are shown below. Training trick, a brief introduction to each series of network structures, and performance evaluation will be shown in the corresponding chapters. The evaluation environment is as follows.

  • CPU evaluation environment is based on Snapdragon 855 (SD855).
  • The GPU evaluation speed is measured by running 500 times under the FP32+TensorRT configuration (excluding the warmup time of the first 10 times).

Curves of accuracy to the inference time of common server-side models are shown as follows.

Curves of accuracy to the inference time and storage size of common mobile-side models are shown as follows.

SSLD pretrained models

Accuracy and inference time of the prtrained models based on SSLD distillation are as follows. More detailed information can be refered to SSLD distillation tutorial.

  • Server-side distillation pretrained models
Model Top-1 Acc Reference
Top-1 Acc		 Acc gain time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
ResNet34_vd_ssld 0.797 0.760 0.037 2.434 6.222 7.39 21.82 Download link
ResNet50_vd_
ssld		 0.824 0.791 0.033 3.531 8.090 8.67 25.58 Download link
ResNet50_vd_
ssld_v2		 0.830 0.792 0.039 3.531 8.090 8.67 25.58 Download link
ResNet101_vd_
ssld		 0.837 0.802 0.035 6.117 13.762 16.1 44.57 Download link
Res2Net50_vd_
26w_4s_ssld		 0.831 0.798 0.033 4.527 9.657 8.37 25.06 Download link
Res2Net101_vd_
26w_4s_ssld		 0.839 0.806 0.033 8.087 17.312 16.67 45.22 Download link
Res2Net200_vd_
26w_4s_ssld		 0.851 0.812 0.049 14.678 32.350 31.49 76.21 Download link
HRNet_W18_C_ssld 0.812 0.769 0.043 7.406 13.297 4.14 21.29 Download link
HRNet_W48_C_ssld 0.836 0.790 0.046 13.707 34.435 34.58 77.47 Download link
SE_HRNet_W64_C_ssld 0.848 - - 31.697 94.995 57.83 128.97 Download link
  • Mobile-side distillation pretrained models
Model Top-1 Acc Reference
Top-1 Acc		 Acc gain SD855 time(ms)
bs=1		 Flops(G) Params(M) Model size(M) Download Address
MobileNetV1_
ssld		 0.779 0.710 0.069 32.523 1.11 4.19 16 Download link
MobileNetV2_
ssld		 0.767 0.722 0.045 23.318 0.6 3.44 14 Download link
MobileNetV3_
small_x0_35_ssld		 0.556 0.530 0.026 2.635 0.026 1.66 6.9 Download link
MobileNetV3_
large_x1_0_ssld		 0.790 0.753 0.036 19.308 0.45 5.47 21 Download link
MobileNetV3_small_
x1_0_ssld		 0.713 0.682 0.031 6.546 0.123 2.94 12 Download link
GhostNet_
x1_3_ssld		 0.794 0.757 0.037 19.983 0.44 7.3 29 Download link
  • Note: Reference Top-1 Acc means accuracy of pretrained models which are trained on ImageNet1k dataset.

ResNet and Vd series

Accuracy and inference time metrics of ResNet and Vd series models are shown as follows. More detailed information can be refered to ResNet and Vd series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
ResNet18 0.7098 0.8992 1.45606 3.56305 3.66 11.69 Download link
ResNet18_vd 0.7226 0.9080 1.54557 3.85363 4.14 11.71 Download link
ResNet34 0.7457 0.9214 2.34957 5.89821 7.36 21.8 Download link
ResNet34_vd 0.7598 0.9298 2.43427 6.22257 7.39 21.82 Download link
ResNet34_vd_ssld 0.7972 0.9490 2.43427 6.22257 7.39 21.82 Download link
ResNet50 0.7650 0.9300 3.47712 7.84421 8.19 25.56 Download link
ResNet50_vc 0.7835 0.9403 3.52346 8.10725 8.67 25.58 Download link
ResNet50_vd 0.7912 0.9444 3.53131 8.09057 8.67 25.58 Download link
ResNet50_vd_v2 0.7984 0.9493 3.53131 8.09057 8.67 25.58 Download link
ResNet101 0.7756 0.9364 6.07125 13.40573 15.52 44.55 Download link
ResNet101_vd 0.8017 0.9497 6.11704 13.76222 16.1 44.57 Download link
ResNet152 0.7826 0.9396 8.50198 19.17073 23.05 60.19 Download link
ResNet152_vd 0.8059 0.9530 8.54376 19.52157 23.53 60.21 Download link
ResNet200_vd 0.8093 0.9533 10.80619 25.01731 30.53 74.74 Download link
ResNet50_vd_
ssld		 0.8239 0.9610 3.53131 8.09057 8.67 25.58 Download link
ResNet50_vd_
ssld_v2		 0.8300 0.9640 3.53131 8.09057 8.67 25.58 Download link
ResNet101_vd_
ssld		 0.8373 0.9669 6.11704 13.76222 16.1 44.57 Download link

Mobile series

Accuracy and inference time metrics of Mobile series models are shown as follows. More detailed information can be refered to Mobile series tutorial.

Model Top-1 Acc Top-5 Acc SD855 time(ms)
bs=1		 Flops(G) Params(M) Model storage size(M) Download Address
MobileNetV1_
x0_25		 0.5143 0.7546 3.21985 0.07 0.46 1.9 Download link
MobileNetV1_
x0_5		 0.6352 0.8473 9.579599 0.28 1.31 5.2 Download link
MobileNetV1_
x0_75		 0.6881 0.8823 19.436399 0.63 2.55 10 Download link
MobileNetV1 0.7099 0.8968 32.523048 1.11 4.19 16 Download link
MobileNetV1_
ssld		 0.7789 0.9394 32.523048 1.11 4.19 16 Download link
MobileNetV2_
x0_25		 0.5321 0.7652 3.79925 0.05 1.5 6.1 Download link
MobileNetV2_
x0_5		 0.6503 0.8572 8.7021 0.17 1.93 7.8 Download link
MobileNetV2_
x0_75		 0.6983 0.8901 15.531351 0.35 2.58 10 Download link
MobileNetV2 0.7215 0.9065 23.317699 0.6 3.44 14 Download link
MobileNetV2_
x1_5		 0.7412 0.9167 45.623848 1.32 6.76 26 Download link
MobileNetV2_
x2_0		 0.7523 0.9258 74.291649 2.32 11.13 43 Download link
MobileNetV2_
ssld		 0.7674 0.9339 23.317699 0.6 3.44 14 Download link
MobileNetV3_
large_x1_25		 0.7641 0.9295 28.217701 0.714 7.44 29 Download link
MobileNetV3_
large_x1_0		 0.7532 0.9231 19.30835 0.45 5.47 21 Download link
MobileNetV3_
large_x0_75		 0.7314 0.9108 13.5646 0.296 3.91 16 Download link
MobileNetV3_
large_x0_5		 0.6924 0.8852 7.49315 0.138 2.67 11 Download link
MobileNetV3_
large_x0_35		 0.6432 0.8546 5.13695 0.077 2.1 8.6 Download link
MobileNetV3_
small_x1_25		 0.7067 0.8951 9.2745 0.195 3.62 14 Download link
MobileNetV3_
small_x1_0		 0.6824 0.8806 6.5463 0.123 2.94 12 Download link
MobileNetV3_
small_x0_75		 0.6602 0.8633 5.28435 0.088 2.37 9.6 Download link
MobileNetV3_
small_x0_5		 0.5921 0.8152 3.35165 0.043 1.9 7.8 Download link
MobileNetV3_
small_x0_35		 0.5303 0.7637 2.6352 0.026 1.66 6.9 Download link
MobileNetV3_
small_x0_35_ssld		 0.5555 0.7771 2.6352 0.026 1.66 6.9 Download link
MobileNetV3_
large_x1_0_ssld		 0.7896 0.9448 19.30835 0.45 5.47 21 Download link
MobileNetV3_small_
x1_0_ssld		 0.7129 0.9010 6.5463 0.123 2.94 12 Download link
ShuffleNetV2 0.6880 0.8845 10.941 0.28 2.26 9 Download link
ShuffleNetV2_
x0_25		 0.4990 0.7379 2.329 0.03 0.6 2.7 Download link
ShuffleNetV2_
x0_33		 0.5373 0.7705 2.64335 0.04 0.64 2.8 Download link
ShuffleNetV2_
x0_5		 0.6032 0.8226 4.2613 0.08 1.36 5.6 Download link
ShuffleNetV2_
x1_5		 0.7163 0.9015 19.3522 0.58 3.47 14 Download link
ShuffleNetV2_
x2_0		 0.7315 0.9120 34.770149 1.12 7.32 28 Download link
ShuffleNetV2_
swish		 0.7003 0.8917 16.023151 0.29 2.26 9.1 Download link
GhostNet_
x0_5		 0.6688 0.8695 5.7143 0.082 2.6 10 Download link
GhostNet_
x1_0		 0.7402 0.9165 13.5587 0.294 5.2 20 Download link
GhostNet_
x1_3		 0.7579 0.9254 19.9825 0.44 7.3 29 Download link
GhostNet_
x1_3_ssld		 0.7938 0.9449 19.9825 0.44 7.3 29 Download link

SEResNeXt and Res2Net series

Accuracy and inference time metrics of SEResNeXt and Res2Net series models are shown as follows. More detailed information can be refered to SEResNext and_Res2Net series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
Res2Net50_
26w_4s		 0.7933 0.9457 4.47188 9.65722 8.52 25.7 Download link
Res2Net50_vd_
26w_4s		 0.7975 0.9491 4.52712 9.93247 8.37 25.06 Download link
Res2Net50_
14w_8s		 0.7946 0.9470 5.4026 10.60273 9.01 25.72 Download link
Res2Net101_vd_
26w_4s		 0.8064 0.9522 8.08729 17.31208 16.67 45.22 Download link
Res2Net200_vd_
26w_4s		 0.8121 0.9571 14.67806 32.35032 31.49 76.21 Download link
Res2Net200_vd_
26w_4s_ssld		 0.8513 0.9742 14.67806 32.35032 31.49 76.21 Download link
ResNeXt50_
32x4d		 0.7775 0.9382 7.56327 10.6134 8.02 23.64 Download link
ResNeXt50_vd_
32x4d		 0.7956 0.9462 7.62044 11.03385 8.5 23.66 Download link
ResNeXt50_
64x4d		 0.7843 0.9413 13.80962 18.4712 15.06 42.36 Download link
ResNeXt50_vd_
64x4d		 0.8012 0.9486 13.94449 18.88759 15.54 42.38 Download link
ResNeXt101_
32x4d		 0.7865 0.9419 16.21503 19.96568 15.01 41.54 Download link
ResNeXt101_vd_
32x4d		 0.8033 0.9512 16.28103 20.25611 15.49 41.56 Download link
ResNeXt101_
64x4d		 0.7835 0.9452 30.4788 36.29801 29.05 78.12 Download link
ResNeXt101_vd_
64x4d		 0.8078 0.9520 30.40456 36.77324 29.53 78.14 Download link
ResNeXt152_
32x4d		 0.7898 0.9433 24.86299 29.36764 22.01 56.28 Download link
ResNeXt152_vd_
32x4d		 0.8072 0.9520 25.03258 30.08987 22.49 56.3 Download link
ResNeXt152_
64x4d		 0.7951 0.9471 46.7564 56.34108 43.03 107.57 Download link
ResNeXt152_vd_
64x4d		 0.8108 0.9534 47.18638 57.16257 43.52 107.59 Download link
SE_ResNet18_vd 0.7333 0.9138 1.7691 4.19877 4.14 11.8 Download link
SE_ResNet34_vd 0.7651 0.9320 2.88559 7.03291 7.84 21.98 Download link
SE_ResNet50_vd 0.7952 0.9475 4.28393 10.38846 8.67 28.09 Download link
SE_ResNeXt50_
32x4d		 0.7844 0.9396 8.74121 13.563 8.02 26.16 Download link
SE_ResNeXt50_vd_
32x4d		 0.8024 0.9489 9.17134 14.76192 10.76 26.28 Download link
SE_ResNeXt101_
32x4d		 0.7939 0.9443 18.82604 25.31814 15.02 46.28 Download link
SENet154_vd 0.8140 0.9548 53.79794 66.31684 45.83 114.29 Download link

DPN and DenseNet series

Accuracy and inference time metrics of DPN and DenseNet series models are shown as follows. More detailed information can be refered to DPN and DenseNet series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
DenseNet121 0.7566 0.9258 4.40447 9.32623 5.69 7.98 Download link
DenseNet161 0.7857 0.9414 10.39152 22.15555 15.49 28.68 Download link
DenseNet169 0.7681 0.9331 6.43598 12.98832 6.74 14.15 Download link
DenseNet201 0.7763 0.9366 8.20652 17.45838 8.61 20.01 Download link
DenseNet264 0.7796 0.9385 12.14722 26.27707 11.54 33.37 Download link
DPN68 0.7678 0.9343 11.64915 12.82807 4.03 10.78 Download link
DPN92 0.7985 0.9480 18.15746 23.87545 12.54 36.29 Download link
DPN98 0.8059 0.9510 21.18196 33.23925 22.22 58.46 Download link
DPN107 0.8089 0.9532 27.62046 52.65353 35.06 82.97 Download link
DPN131 0.8070 0.9514 28.33119 46.19439 30.51 75.36 Download link

HRNet series

Accuracy and inference time metrics of HRNet series models are shown as follows. More detailed information can be refered to Mobile series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
HRNet_W18_C 0.7692 0.9339 7.40636 13.29752 4.14 21.29 Download link
HRNet_W18_C_ssld 0.81162 0.95804 7.40636 13.29752 4.14 21.29 Download link
HRNet_W30_C 0.7804 0.9402 9.57594 17.35485 16.23 37.71 Download link
HRNet_W32_C 0.7828 0.9424 9.49807 17.72921 17.86 41.23 Download link
HRNet_W40_C 0.7877 0.9447 12.12202 25.68184 25.41 57.55 Download link
HRNet_W44_C 0.7900 0.9451 13.19858 32.25202 29.79 67.06 Download link
HRNet_W48_C 0.7895 0.9442 13.70761 34.43572 34.58 77.47 Download link
HRNet_W48_C_ssld 0.8363 0.9682 13.70761 34.43572 34.58 77.47 Download link
HRNet_W64_C 0.7930 0.9461 17.57527 47.9533 57.83 128.06 Download link
SE_HRNet_W64_C_ssld 0.8475  0.9726 31.69770 94.99546 57.83 128.97 Download link

Inception series

Accuracy and inference time metrics of Inception series models are shown as follows. More detailed information can be refered to Inception series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
GoogLeNet 0.7070 0.8966 1.88038 4.48882 2.88 8.46 Download link
Xception41 0.7930 0.9453 4.96939 17.01361 16.74 22.69 Download link
Xception41_deeplab 0.7955 0.9438 5.33541 17.55938 18.16 26.73 Download link
Xception65 0.8100 0.9549 7.26158 25.88778 25.95 35.48 Download link
Xception65_deeplab 0.8032 0.9449 7.60208 26.03699 27.37 39.52 Download link
Xception71 0.8111 0.9545 8.72457 31.55549 31.77 37.28 Download link
InceptionV3 0.7914 0.9459 6.64054 13.53630 11.46 23.83 Download link
InceptionV4 0.8077 0.9526 12.99342 25.23416 24.57 42.68 Download link

EfficientNet and ResNeXt101_wsl series

Accuracy and inference time metrics of EfficientNet and ResNeXt101_wsl series models are shown as follows. More detailed information can be refered to EfficientNet and ResNeXt101_wsl series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
ResNeXt101_
32x8d_wsl		 0.8255 0.9674 18.52528 34.25319 29.14 78.44 Download link
ResNeXt101_
32x16d_wsl		 0.8424 0.9726 25.60395 71.88384 57.55 152.66 Download link
ResNeXt101_
32x32d_wsl		 0.8497 0.9759 54.87396 160.04337 115.17 303.11 Download link
ResNeXt101_
32x48d_wsl		 0.8537 0.9769 99.01698256 315.91261 173.58 456.2 Download link
Fix_ResNeXt101_
32x48d_wsl		 0.8626 0.9797 160.0838242 595.99296 354.23 456.2 Download link
EfficientNetB0 0.7738 0.9331 3.442 6.11476 0.72 5.1 Download link
EfficientNetB1 0.7915 0.9441 5.3322 9.41795 1.27 7.52 Download link
EfficientNetB2 0.7985 0.9474 6.29351 10.95702 1.85 8.81 Download link
EfficientNetB3 0.8115 0.9541 7.67749 16.53288 3.43 11.84 Download link
EfficientNetB4 0.8285 0.9623 12.15894 30.94567 8.29 18.76 Download link
EfficientNetB5 0.8362 0.9672 20.48571 61.60252 19.51 29.61 Download link
EfficientNetB6 0.8400 0.9688 32.62402 - 36.27 42 Download link
EfficientNetB7 0.8430 0.9689 53.93823 - 72.35 64.92 Download link
EfficientNetB0_
small		 0.7580 0.9258 2.3076 4.71886 0.72 4.65 Download link

ResNeSt and RegNet series

Accuracy and inference time metrics of ResNeSt and RegNet series models are shown as follows. More detailed information can be refered to ResNeSt and RegNet series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
ResNeSt50_
fast_1s1x64d		 0.8035 0.9528 3.45405 8.72680 8.68 26.3 Download link
ResNeSt50 0.8083 0.9542 6.69042 8.01664 10.78 27.5 Download link
RegNetX_4GF 0.785 0.9416 6.46478 11.19862 8 22.1 Download link

ViT and DeiT series

Accuracy and inference time metrics of ViT and DeiT series models are shown as follows. More detailed information can be refered to ViT and DeiT series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
ViT_small_
patch16_224		 0.7769 0.9342 - - Download link
ViT_base_
patch16_224		 0.8195 0.9617 - - 86 Download link
ViT_base_
patch16_384		 0.8414 0.9717 - - Download link
ViT_base_
patch32_384		 0.8176 0.9613 - - Download link
ViT_large_
patch16_224		 0.8323 0.9650 - - 307 Download link
ViT_large_
patch16_384		 0.8513 0.9736 - - Download link
ViT_large_
patch32_384		 0.8153 0.9608 - - Download link
Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
DeiT_tiny_
patch16_224		 0.718 0.910 - - 5 Download link
DeiT_small_
patch16_224		 0.796 0.949 - - 22 Download link
DeiT_base_
patch16_224		 0.817 0.957 - - 86 Download link
DeiT_base_
patch16_384		 0.830 0.962 - - 87 Download link
DeiT_tiny_
distilled_patch16_224		 0.741 0.918 - - 6 Download link
DeiT_small_
distilled_patch16_224		 0.809 0.953 - - 22 Download link
DeiT_base_
distilled_patch16_224		 0.831 0.964 - - 87 Download link
DeiT_base_
distilled_patch16_384		 0.851 0.973 - - 88 Download link

RepVGG

Accuracy and inference time metrics of RepVGG series models are shown as follows. More detailed information can be refered to RepVGG series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
RepVGG_A0 0.7131 0.9016 Download link
RepVGG_A1 0.7380 0.9146 Download link
RepVGG_A2 0.7571 0.9264 Download link
RepVGG_B0 0.7450 0.9213 Download link
RepVGG_B1 0.7773 0.9385 Download link
RepVGG_B2 0.7813 0.9410 Download link
RepVGG_B1g2 0.7732 0.9359 Download link
RepVGG_B1g4 0.7675 0.9335 Download link
RepVGG_B2g4 0.7881 0.9448 Download link
RepVGG_B3g4 0.7965 0.9485 Download link

MixNet

Accuracy and inference time metrics of MixNet series models are shown as follows. More detailed information can be refered to MixNet series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(M) Params(M) Download Address
MixNet_S 0.7628 0.9299 252.977 4.167 Download link
MixNet_M 0.7767 0.9364 357.119 5.065 Download link
MixNet_L 0.7860 0.9437 579.017 7.384 Download link

ReXNet

Accuracy and inference time metrics of ReXNet series models are shown as follows. More detailed information can be refered to ReXNet series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
ReXNet_1_0 0.7746 0.9370 0.415 4.838 Download link
ReXNet_1_3 0.7913 0.9464 0.683 7.611 Download link
ReXNet_1_5 0.8006 0.9512 0.900 9.791 Download link
ReXNet_2_0 0.8122 0.9536 1.561 16.449 Download link
ReXNet_3_0 0.8209 0.9612 3.445 34.833 Download link

SwinTransformer

Accuracy and inference time metrics of SwinTransformer series models are shown as follows. More detailed information can be refered to SwinTransformer series tutorial.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
SwinTransformer_tiny_patch4_window7_224 0.8069 0.9534 4.5 28 Download link
SwinTransformer_small_patch4_window7_224 0.8275 0.9613 8.7 50 Download link
SwinTransformer_base_patch4_window7_224 0.8300 0.9626 15.4 88 Download link
SwinTransformer_base_patch4_window12_384 0.8439 0.9693 47.1 88 Download link
SwinTransformer_base_patch4_window7_224[1] 0.8487 0.9746 15.4 88 Download link
SwinTransformer_base_patch4_window12_384[1] 0.8642 0.9807 47.1 88 Download link
SwinTransformer_large_patch4_window7_224[1] 0.8596 0.9783 34.5 197 Download link
SwinTransformer_large_patch4_window12_384[1] 0.8719 0.9823 103.9 197 Download link

[1]: Based on imagenet22k dataset pre-training, and then in imagenet1k dataset transfer learning.

Others

Accuracy and inference time metrics of AlexNet, SqueezeNet series, VGG series and DarkNet53 models are shown as follows. More detailed information can be refered to Others.

Model Top-1 Acc Top-5 Acc time(ms)
bs=1		 time(ms)
bs=4		 Flops(G) Params(M) Download Address
AlexNet 0.567 0.792 1.44993 2.46696 1.370 61.090 Download link
SqueezeNet1_0 0.596 0.817 0.96736 2.53221 1.550 1.240 Download link
SqueezeNet1_1 0.601 0.819 0.76032 1.877 0.690 1.230 Download link
VGG11 0.693 0.891 3.90412 9.51147 15.090 132.850 Download link
VGG13 0.700 0.894 4.64684 12.61558 22.480 133.030 Download link
VGG16 0.720 0.907 5.61769 16.40064 30.810 138.340 Download link
VGG19 0.726 0.909 6.65221 20.4334 39.130 143.650 Download link
DarkNet53 0.780 0.941 4.10829 12.1714 18.580 41.600 Download link

License

PaddleClas is released under the Apache 2.0 license

Contribution

Contributions are highly welcomed and we would really appreciate your feedback!!

  • Thank nblib to fix bug of RandErasing.
  • Thank chenpy228 to fix some typos PaddleClas.
  • Thank jm12138 to add ViT, DeiT models and RepVGG models into PaddleClas.
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

A treasure chest for visual classification and recognition powered by PaddlePaddle

Python Text C++ Shell Markdown other

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit