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.
<aname="SSLD_pretrained_series"></a>
### 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).
* Note: `Reference Top-1 Acc` means accuracy of pretrained models which are trained on ImageNet1k dataset.
<aname="ResNet_and_Vd_series"></a>
### 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](../en/models/ResNet_and_vd_en.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).
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).
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).
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).
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).
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).
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/Transformer_en.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).
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).
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).
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 inference model (the model saved by `paddle.jit.save`) is generally a solidified model saved after the model training is completed, and is mostly used to give prediction in deployment.
The model saved during the training process is the checkpoints model, which saves the parameters of the model and is mostly used to resume training.
Compared with the checkpoints model, the inference model will additionally save the structural information of the model. Therefore, it is easier to deploy because the model structure and model parameters are already solidified in the inference model file, and is suitable for integration with actual systems.
Next, we first introduce how to convert a trained model into an inference model, and then we will introduce mainbody detection, feature extraction based on inference model,
then we introduce a recognition pipeline consist of mainbody detection, feature extraction and vector search. At last, we introduce classification base on inference model.
-[CONVERT TRAINING MODEL TO INFERENCE MODEL](#CONVERT)
-[Convert feature extraction model to inference model](#Convert_feature_extraction)
-[Convert classification model to inference model](#Convert_class)
-[MAINBODY DETECTION MODEL INFERENCE](#DETECTION_MODEL_INFERENCE)
-[FEATURE EXTRACTION MODEL INFERENCE](#FEATURE_EXTRACTION_MODEL_INFERENCE)
-[CONCATENATION OF MAINBODY DETECTION, FEATURE EXTRACTION AND VECTOR SEARCH](#CONCATENATION)
-[CLASSIFICATION MODEL INFERENCE](#CLASSIFICATION)
<aname="CONVERT"></a>
## CONVERT TRAINING MODEL TO INFERENCE MODEL
<aname="Convert_feature_extraction"></a>
### Convert feature extraction model to inference model
First please enter the root folder of PaddleClas. Download the product feature extraction model:
The above model is trained on AliProduct with ResNet50_vd as backbone. To convert the trained model into an inference model, just run the following command:
```
# -c Set the training algorithm yml configuration file
# -o Set optional parameters
# Global.pretrained_model parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams.
# Global.save_inference_dir Set the address where the converted model will be saved.
When converting to an inference model, the configuration file used is the same as the configuration file used during training. In addition, you also need to set the `Global.pretrained_model` parameter in the configuration file.
After the conversion is successful, there are three files in the model save directory:
```
├── product_ResNet50_vd_aliproduct_v1.0_infer
│ ├── inference.pdiparams
│ ├── inference.pdiparams.info
│ └── inference.pdmodel
```
<aname="Convert_class"></a>
### Convert classification model to inference model
