-[3. Model evaluation and inference deployment](#3-model-evaluation-and-inference-deployment)
-[3.1 Model Evaluation](#31-model-evaluation)
-[3.1 Model Inference and Deployment](#31-model-inference-and-deployment)
-[3.1.1 Inference model preparation](#311-inference-model-preparation)
-[3.1.2 Inference based on Python prediction engine](#312-inference-based-on-python-prediction-engine)
-[3.1.3 Inference based on C++ prediction engine](#313-inference-based-on-c-prediction-engine)
-[3.2 Service Deployment](#32-service-deployment)
-[3.3 Device side deployment](#33-device-side-deployment)
-[3.4 Paddle2ONNX model conversion and prediction](#34-paddle2onnx-model-conversion-and-prediction)
-[4. Summary](#4-summary)
-[4.1 Method summary and comparison](#41-method-summary-and-comparison)
-[4.2 Usage advice/FAQ](#42-usage-advicefaq)
-[4. References](#4-references)
### 1. Introduction to algorithms/application scenarios
Pedestrian re-identification (Person re-identification), also known as pedestrian re-identification, is the use of [computer vision](https://baike.baidu.com/item/computervision/2803351) technology to judge [image](https://baike.baidu.com/item/image/773234) or whether there is a technique of a particular pedestrian in the video sequence. Widely regarded as a sub-problem of [Image Retrieval](https://baike.baidu.com/item/image_retrieval/1150910). Given a surveillance pedestrian image, retrieve the pedestrian image across devices. It aims to make up for the visual limitations of fixed cameras, and can be combined with [pedestrian detection](https://baike.baidu.com/item/pedestriandetection/20590256)/pedestrian tracking technology, which can be widely used in [intelligent video surveillance](https://baike.baidu.com/item/intelligentvideosurveillance/10717227), intelligent security and other fields.
Pedestrian re-identification, also known as pedestrian re-identification, is a technology that uses computer vision technology to determine whether there is a specific pedestrian in an image or video sequence. Widely regarded as a sub-problem of image retrieval. Given a surveillance pedestrian image, retrieve the pedestrian image across devices. It is designed to make up for the visual limitations of fixed cameras, and can be combined with pedestrian detection/pedestrian tracking technology, which can be widely used in intelligent video surveillance, intelligent security and other fields.
The common person re-identification method extracts the local/global, single-granularity/multi-granularity features of the input image through the feature extraction module, and then obtains a high-dimensional feature vector through the fusion module. Use the classification head to convert the feature vector into the probability of each category during training to optimize the feature extraction model in the way of classification tasks; directly use the high-dimensional feature vector as the image description vector in the retrieval vector library during testing or inference search to get the search results. The ReID strong-baseline algorithm proposes several methods to effectively optimize training and retrieval to improve the overall model performance.
Note: The above reference indicators are obtained by using the author's open source code to train on our equipment for many times. Due to different system environment, torch version, CUDA version and other reasons, there may be slight differences with the indicators provided by the author.
Note: The above reference indicators are obtained by using the author's open source code to train on our equipment for many times. Due to different system environments, torch versions, and CUDA versions, there may be slight differences with the indicators provided by the author.
Next, we mainly take the `softmax_triplet_with_center.yaml` configuration and trained model file as an example to show the process of training, testing, and inference on the Market1501 dataset.
...
...
@@ -72,15 +73,15 @@ Download the [Market-1501-v15.09.15.zip](https://pan.baidu.com/s/1ntIi2Op?_at_=1
```shell
PaddleClas/dataset/market1501
└── Market-1501-v15.09.15/
├── bounding_box_test/
├── bounding_box_train/
├── bounding_box_test/# gallery set pictures
├── bounding_box_train/# training set image
├── gt_bbox/
├── gt_query/
├── query/
├── query/# query set image
├── generate_anno.py
├── bounding_box_test.txt
├── bounding_box_train.txt
├── query.txt
├── bounding_box_test.txt# gallery set path
├── bounding_box_train.txt# training set path
├── query.txt# query set path
└── readme.txt
```
...
...
@@ -88,19 +89,40 @@ Download the [Market-1501-v15.09.15.zip](https://pan.baidu.com/s/1ntIi2Op?_at_=1
1. Execute the following command to start training
2. View training logs and saved model parameter files
During the training process, indicator information such as loss will be printed on the screen in real time, and the log file `train.log`, model parameter file `*.pdparams`, optimizer parameter file `*.pdopt` and other contents will be saved to `Global.output_dir` `Under the specified folder, the default is under the `PaddleClas/output/RecModel/` folder.
##### 2.1.5 Model Evaluation
### 3. Model evaluation and inference deployment
Prepare the `*.pdparams` model parameter file for evaluation. You can use the trained model or the model saved in [2.1.4 Model training](#214-model-training).
#### 3.1 Model Evaluation
Prepare the `*.pdparams` model parameter file for evaluation. You can use the trained model or the model saved in [2.1.4 Model training] (#214-model training).
- Take the `latest.pdparams` saved during training as an example, execute the following command to evaluate.
...
...
@@ -110,19 +132,19 @@ Prepare the `*.pdparams` model parameter file for evaluation. You can use the tr
-Take the trained model as an example, download [reid_strong_baseline_softmax_with_center.epoch_120.pdparams](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/reid/pretrain/reid_strong_baseline_softmax_with_center.epoch_120.pdparams) Go to the `PaddleClas/pretrained_models` folder and execute the following command to evaluate.
-to train wellTake the model as an example, download [softmax_triplet_with_center_pretrained.pdparams](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/reid/pretrain/softmax_triplet_with_center_pretrained.pdparams) to `PaddleClas/ In the pretrained_models` folder, execute the following command to evaluate.
Note: The address filled after `pretrained_model` does not need to be suffixed with `.pdparams`, it will be added automatically when the program is running.
...
...
@@ -130,6 +152,8 @@ Prepare the `*.pdparams` model parameter file for evaluation. You can use the tr
```log
...
...
ppcls INFO: unique_endpoints {''}
ppcls INFO: Found /root/.paddleclas/weights/resnet50-19c8e357_torch2paddle.pdparams
The default evaluation log is saved in `PaddleClas/output/RecModel/eval.log`. You can see that the evaluation metrics of the `reid_strong_baseline_softmax_with_center.epoch_120.pdparams` model we provided on the Market1501 dataset are recall@1=0.94270, recall@5 =0.98189, mAP=0.85799
The default evaluation log is saved in `PaddleClas/output/RecModel/eval.log`. You can see that the evaluation metrics of the `softmax_triplet_with_center_pretrained.pdparams` model we provided on the Market1501 dataset are recall@1=0.94507, recall@5 =0.98248, mAP=0.85827
#### 3.1 Model Inference and Deployment
##### 2.1.6 Model Inference Deployment
##### 3.1.1 Inference model preparation
###### 2.1.6.1 Inference model preparation
You can choose to use the model file saved during the training process to convert into an inference model and inference, or use the converted inference model we provide for direct inference
- Convert the model file saved during the training process into an inference model, also take `latest.pdparams` as an example, execute the following command to convert
You can convert the model file saved during training into an inference model and inference, or use the converted inference model we provide for direct inference
- Convert the model file saved during the training process to an inference model, also take `latest.pdparams` as an example, execute the following command to convert
###### 2.1.6.2 Inference based on Python prediction engine
##### 3.1.2 Inference based on Python prediction engine
1. Modify `PaddleClas/deploy/configs/inference_rec.yaml`. Change the field after `infer_imgs:` to any image path under the query folder in Market1501 (the code below uses the image path of `0294_c1s1_066631_00.jpg`); change the field after `rec_inference_model_dir:` to the extracted one reid_srong_baseline_softmax_with_center folder path; change the preprocessing configuration under the `transform_ops` field to the preprocessing configuration under `Eval.Query.dataset` in `softmax_triplet_with_center.yaml`. As follows
1. Modify `PaddleClas/deploy/configs/inference_rec.yaml`. Change the field after `infer_imgs:` to any image path under the query folder in Market1501 (the configuration below uses the path of the `0294_c1s1_066631_00.jpg` image); change the field after `rec_inference_model_dir:` to extract it softmax_triplet_with_center_infer folder path; change the preprocessing configuration under the `transform_ops` field to the preprocessing configuration under `Eval.Query.dataset` in `softmax_triplet_with_center.yaml`. As follows
@@ -209,44 +234,43 @@ You can choose to use the model file saved during the training process to conver
3. Check the output result, the actual result is a vector of length 2048, which represents the feature vector obtained after the input image is transformed by the model
The output vector for inference is stored in the `result_dict` variable in [predict_rec.py](../../../deploy/python/predict_rec.py#L134-L135).
4. Batch prediction
Change the path after `infer_imgs:` in the configuration file to a folder, such as `../dataset/market1501/Market-1501-v15.09.15/query`, it will predict and output all images under query. Feature vector.
4. For batch prediction, change the path after `infer_imgs:` in the configuration file to a folder, such as `../dataset/market1501/Market-1501-v15.09.15/query`, it will predict and output The feature vector of all images under query.
###### 2.1.6.3 Inference based on C++ prediction engine
##### 3.1.3 Inference based on C++ prediction engine
PaddleClas provides an example of inference based on the C++ prediction engine, you can refer to [Server-side C++ prediction](../inference_deployment/cpp_deploy_en.md) to complete the corresponding inference deployment. If you are using the Windows platform, you can refer to the Visual Studio 2019 Community CMake Compilation Guide to complete the corresponding prediction library compilation and model prediction work.
PaddleClas provides an example of inference based on C++ prediction engine, you can refer to [C++ prediction](../inference_deployment/cpp_deploy_en.md) to complete the corresponding inference deployment. If you are using the Windows platform, you can refer to the Visual Studio 2019 Community CMake Compilation Guide to complete the corresponding prediction library compilation and model prediction work.
##### 2.1.7 Service deployment
##### 3.2 Service Deployment
Paddle Serving provides high-performance, flexible and easy-to-use industrial-grade online inference services. Paddle Serving supports RESTful, gRPC, bRPC and other protocols, and provides inference solutions in a variety of heterogeneous hardware and operating system environments. For more introduction to Paddle Serving, please refer to the Paddle Serving code repository.
PaddleClas provides an example of model serving deployment based on Paddle Serving. You can refer to [Model serving deployment](../inference_deployment/paddle_serving_deploy_en.md) to complete the corresponding deployment.
PaddleClas provides an example of model serving deployment based on Paddle Serving. You can refer to [Model serving deployment](../inference_deployment/paddle_serving_deploy_en.md) to complete the corresponding deployment work.
##### 2.1.8 Device side deployment
##### 3.3 Lite deployment
Paddle Lite is a high-performance, lightweight, flexible and easily extensible deep learning inference framework, positioned to support multiple hardware platforms including mobile, embedded and server. For more introduction to Paddle Lite, please refer to the Paddle Lite code repository.
Paddle Lite is a high-performance, lightweight, flexible and easily extensible deep learning inference framework, positioned to support mobileMultiple hardware platforms including client, embedded and server. For more introduction to Paddle Lite, please refer to the Paddle Lite code repository.
PaddleClas provides an example of deploying models based on Paddle Lite. You can refer to [Deployment](../inference_deployment/paddle_lite_deploy_en.md) to complete the corresponding deployment.
##### 2.1.9 Paddle2ONNX Model Conversion and Prediction
##### 3.4 Paddle2ONNX model conversion and prediction
Paddle2ONNX supports converting PaddlePaddle model format to ONNX model format. The deployment of Paddle models to various inference engines can be completed through ONNX, including TensorRT/OpenVINO/MNN/TNN/NCNN, and other inference engines or hardware that support the ONNX open source format. For more information about Paddle2ONNX, please refer to the Paddle2ONNX code repository.
Paddle2ONNX supports converting PaddlePaddle model format to ONNX model format. The deployment of Paddle models to various inference engines can be completed through ONNX, including TensorRT/OpenVINO/MNN/TNN/NCNN, as well as other inference engines or hardware that support the ONNX open source format. For more information about Paddle2ONNX, please refer to the Paddle2ONNX code repository.
PaddleClas provides an example of converting an inference model to an ONNX model and making inference prediction based on Paddle2ONNX. You can refer to [Paddle2ONNX model conversion and prediction](../../../deploy/paddle2onnx/readme.md) to complete the corresponding deployment work.
### 3. Summary
### 4. Summary
#### 3.1 Method summary and comparison
#### 4.1 Method summary and comparison
The above algorithm can be quickly migrated to most ReID models, which can further improve the performance of ReID models.
#### 3.2 Usage advice/FAQ
#### 4.2 Usage advice/FAQ
The Market1501 dataset is relatively small, so you can try to train multiple times to get the highest accuracy.
...
...
@@ -254,5 +278,5 @@ The Market1501 dataset is relatively small, so you can try to train multiple tim
1.[Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://openaccess.thecvf.com/content_CVPRW_2019/papers/TRMTMCT/Luo_Bag_of_Tricks_and_a_Strong_Baseline_for_Deep_Person_CVPRW_2019_paper.pdf)
3.[Pedestrian Re-ID dataset Market1501Data set _star_function's blog - CSDN blog _market1501 data set](https://blog.csdn.net/qq_39220334/article/details/121470106)
3.[Pedestrian Re-ID dataset Market1501 dataset _star_function blog-CSDN blog _market1501 dataset](https://blog.csdn.net/qq_39220334/article/details/121470106)
4.[Deep Learning for Person Re-identification: A Survey and Outlook](https://arxiv.org/abs/2001.04193)
PaddleClas 提供了基于 C++ 预测引擎推理的示例，您可以参考[服务器端 C++ 预测](../inference_deployment/cpp_deploy.md)来完成相应的推理部署。如果您使用的是 Windows 平台，可以参考基于 Visual Studio 2019 Community CMake 编译指南完成相应的预测库编译和模型预测工作。
