Based on the ImageNet-1k classification dataset, the 35 classification network structures supported by PaddleClas and the corresponding 164 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.
## Catalogue
* CPU evaluation environment is based on Snapdragon 855 (SD855).
-[1. Model library overview diagram](#1)
* The GPU evaluation speed is measured by running 500 times under the FP32+TensorRT configuration (excluding the warmup time of the first 10 times).
-[10. EfficientNet ans ResNeXt101_wsl series](#10)
-[11. ResNeSt and RegNet series](#11)
-[12. ViT and DeiT series](#12)
-[13. RepVGG series](#13)
-[14. MixNet series](#14)
-[15. ReXNet series](#15)
-[16. SwinTransformer series](#16)
-[17. LeViT series](#17)
-[18. Twins series](#18)
-[19. HarDNet series](#19)
-[20. DLA series](#20)
-[21. RedNet series](#21)
-[22. TNT series](#22)
-[23. Other models](#23)
<aname="1"></a>
## 1. Model library overview diagram
Based on the ImageNet-1k classification dataset, the 37 classification network structures supported by PaddleClas and the corresponding 217 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.
* Arm CPU evaluation environment is based on Snapdragon 855 (SD855).
* Intel CPU evaluation environment is based on Intel(R) Xeon(R) Gold 6148.
* The GPU evaluation speed is measured by running 2100 times under the FP32+TensorRT configuration (excluding the warmup time of the first 100 times).
* FLOPs and Params are calculated by `paddle.flops()` (PaddlePaddle version is 2.2)
Curves of accuracy to the inference time of common server-side models are shown as follows.
Curves of accuracy to the inference time of common server-side models are shown as follows.
...
@@ -17,457 +51,470 @@ Curves of accuracy to the inference time and storage size of common mobile-side
...
@@ -17,457 +51,470 @@ Curves of accuracy to the inference time and storage size of common mobile-side


<aname="SSLD_pretrained_series"></a>
<aname="2"></a>
### SSLD pretrained models
## 2. 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](../en/advanced_tutorials/distillation/distillation_en.md).
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](../en/advanced_tutorials/distillation/distillation_en.md).
* Note: `Reference Top-1 Acc` means the accuracy of the pre-trained model obtained by PaddleClas based on ImageNet1k dataset training.
Accuracy and inference time metrics of PPLCNet series models are shown as follows. More detailed information can be refered to [PPLCNet series tutorial](../en/models/PP-LCNet_en.md).
The accuracy and speed indicators of the PP-LCNet series models are shown in the following table. For more information about this series of models, please refer to: [PP-LCNet series model documents](../models/PP-LCNet.md)。
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](../en/models/ResNet_and_vd_en.md).
The accuracy and speed indicators of ResNet and ResNet_vd series models are shown in the following table. For more information about this series of models, please refer to: [ResNet and ResNet_vd series model documents](../models/ResNet_and_vd.md)。
Accuracy and inference time metrics of Mobile series models are shown as follows. More detailed information can be refered to [Mobile series tutorial](../en/models/Mobile_en.md).
The accuracy and speed indicators of the mobile series models are shown in the following table. For more information about this series, please refer to: [Mobile series model documents](../models/Mobile.md)。
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](../en/models/SEResNext_and_Res2Net_en.md).
The accuracy and speed indicators of the SEResNeXt and Res2Net series models are shown in the following table. For more information about the models of this series, please refer to: [SEResNeXt and Res2Net series model documents](../models/SEResNext_and_Res2Net.md).
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](../en/models/DPN_DenseNet_en.md).
The accuracy and speed indicators of the DPN and DenseNet series models are shown in the following table. For more information about the models of this series, please refer to: [DPN and DenseNet series model documents](../models/DPN_DenseNet.md).
Accuracy and inference time metrics of HRNet series models are shown as follows. More detailed information can be refered to [Mobile series tutorial](../en/models/HRNet_en.md).
The accuracy and speed indicators of the HRNet series models are shown in the following table. For more information about the models of this series, please refer to: [HRNet series model documents](../models/HRNet.md).
Accuracy and inference time metrics of Inception series models are shown as follows. More detailed information can be refered to [Inception series tutorial](../en/models/Inception_en.md).
The accuracy and speed indicators of the Inception series models are shown in the following table. For more information about this series of models, please refer to: [Inception series model documents](../models/Inception.md).
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
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](../en/models/EfficientNet_and_ResNeXt101_wsl_en.md).
The accuracy and speed indicators of the EfficientNet and ResNeXt101_wsl series models are shown in the following table. For more information about this series of models, please refer to: [EfficientNet and ResNeXt101_wsl series model documents](../models/EfficientNet_and_ResNeXt101_wsl.md).
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
The accuracy and speed indicators of the ResNeSt and RegNet series models are shown in the following table. For more information about the models of this series, please refer to: [ResNeSt and RegNet series model documents](../models/ResNeSt_RegNet.md).
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
The accuracy and speed indicators of ViT (Vision Transformer) and DeiT (Data-efficient Image Transformers) series models are shown in the following table. For more information about this series of models, please refer to: [ViT_and_DeiT series model documents](../models/ViT_and_DeiT.md).
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
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](../en/models/ResNeSt_RegNet_en.md).
Accuracy and inference time metrics of ViT and DeiT series models are shown as follows. More detailed information can be refered to [Transformer series tutorial](../en/models/ViT_and_DeiT_en.md).
The accuracy and speed indicators of RepVGG series models are shown in the following table. For more introduction, please refer to: [RepVGG series model documents](../models/RepVGG.md).
The accuracy and speed indicators of the MixNet series models are shown in the following table. For more introduction, please refer to: [MixNet series model documents](../models/MixNet.md).
Accuracy and inference time metrics of RepVGG series models are shown as follows. More detailed information can be refered to [RepVGG series tutorial](../en/models/RepVGG_en.md).
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(M) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
The accuracy and speed indicators of ReXNet series models are shown in the following table. For more introduction, please refer to: [ReXNet series model documents](../models/ReXNet.md).
### MixNet
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
Accuracy and inference time metrics of MixNet series models are shown as follows. More detailed information can be refered to [MixNet series tutorial](../en/models/MixNet_en.md).
The accuracy and speed indicators of SwinTransformer series models are shown in the following table. For more introduction, please refer to: [SwinTransformer series model documents](../models/SwinTransformer.md).
### ReXNet
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(G) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
Accuracy and inference time metrics of ReXNet series models are shown as follows. More detailed information can be refered to [ReXNet series tutorial](../en/models/ReXNet_en.md).
[1]:It is pre-trained based on the ImageNet22k dataset, and then transferred and learned from the ImageNet1k dataset.
The accuracy and speed indicators of LeViT series models are shown in the following table. For more introduction, please refer to: [LeViT series model documents](../models/LeViT.md).
### SwinTransformer
Accuracy and inference time metrics of SwinTransformer series models are shown as follows. More detailed information can be refered to[SwinTransformer series tutorial](../en/models/SwinTransformer_en.md).
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | time(ms)<br/>bs=8 | FLOPs(M) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
[1] Based on the pre-trained model of the ImageNet22k dataset, it is obtained by finetuning from the ImageNet1k data set.
<aname="18"></a>
<aname="LeViT_series"></a>
## 18. Twins series
### LeViT
Accuracy and inference time metrics of LeViT series models are shown as follows. More detailed information can be refered to[LeViT series tutorial](../en/models/LeViT_en.md).
The accuracy and speed indicators of Twins series models are shown in the following table. For more introduction, please refer to: [Twins series model documents](../models/Twins.md).
**Note**:The difference in accuracy from Reference is due to the difference in data preprocessing and the absence of distilled head as output.
**Note**: The accuracy difference with Reference is due to the difference in data preprocessing.
<aname="Twins_series"></a>
<aname="19"></a>
### Twins
Accuracy and inference time metrics of Twins series models are shown as follows. More detailed information can be refered to[Twins series tutorial](../en/models/Twins_en.md).
The accuracy and speed indicators of HarDNet series models are shown in the following table. For more introduction, please refer to: [HarDNet series model documents](../models/HarDNet.md).
Accuracy and inference time metrics of HarDNet series models are shown as follows. More detailed information can be refered to[HarDNet series tutorial](../en/models/HarDNet_en.md).
## 20. DLA series
The accuracy and speed indicators of DLA series models are shown in the following table. For more introduction, please refer to: [DLA series model documents](../models/DLA.md).
Accuracy and inference time metrics of DLA series models are shown as follows. More detailed information can be refered to[DLA series tutorial](../en/models/DLA_en.md).
The accuracy and speed indicators of RedNet series models are shown in the following table. For more introduction, please refer to: [RedNet series model documents](../models/RedNet.md).
Accuracy and inference time metrics of RedNet series models are shown as follows. More detailed information can be refered to[RedNet series tutorial](../en/models/RedNet_en.md).
The accuracy and speed indicators of TNT series models are shown in the following table. For more introduction, please refer to: [TNT series model documents](../models/TNT.md).
### TNT
Accuracy and inference time metrics of TNT series models are shown as follows. More detailed information can be refered to[TNT series tutorial](../en/models/TNT_en.md).
| Model | Top-1 Acc | Top-5 Acc | time(ms)<br>bs=1 | time(ms)<br>bs=4 | FLOPs(G) | Params(M) | Pretrained Model Download Address | Inference Model Download Address |
**Note**:The `mean` and `std` in `NormalizeImage` in the data preprocessing part of the TNT model are both 0.5.
<aname="23"></a>
### Others
## 23. Other models
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](../en/models/Others_en.md).
The accuracy and speed indicators of AlexNet, SqueezeNet series, VGG series, DarkNet53 and other models are shown in the following table. For more information, please refer to: [Other model documents](../models/Others.md).
Experience the training, evaluation, and prediction of multi-label classification based on the [NUS-WIDE-SCENE](https://lms.comp.nus.edu.sg/wp-content/uploads/2019/research/nuswide/NUS-WIDE.html) dataset, which is a subset of the NUS-WIDE dataset. Please first install PaddlePaddle and PaddleClas, see [Paddle Installation](https://github.com/PaddlePaddle/PaddleClas/blob/develop/docs/zh_CN/installation) and [PaddleClas installation](https://github.com/PaddlePaddle/PaddleClas/blob/develop/docs/zh_CN/installation/install_ paddleclas.md) for more details.
Experience the training, evaluation, and prediction of multi-label classification based on the [NUS-WIDE-SCENE](https://lms.comp.nus.edu.sg/wp-content/uploads/2019/research/nuswide/NUS-WIDE.html) dataset, which is a subset of the NUS-WIDE dataset. Please first install PaddlePaddle and PaddleClas, see [Paddle Installation](https://github.com/PaddlePaddle/PaddleClas/blob/develop/docs/zh_CN/installation) and [PaddleClas installation](https://github.com/PaddlePaddle/PaddleClas/blob/develop/docs/zh_CN/installation/install_ paddleclas.md) for more details.
## Contents
## Catalogue
-[1. Data and Model Preparation](#1)
-[1. Data and Model Preparation](#1)
-[2. Model Training](#2)
-[2. Model Training](#2)
...
@@ -114,4 +114,4 @@ Obtain an output silimar to the following:
...
@@ -114,4 +114,4 @@ Obtain an output silimar to the following: