## linux or mac, $path_to_PaddleClas indicates the root directory of PaddleClas, which the user needs to modify according to their real directory
cd$path_to_PaddleClas
```
* Please go to the `dataset` catalog. In order to quickly experiment the image retrieval module of PaddleClas, the dataset we used is [CUB_200_2011](http://vision.ucsd.edu/sites/default/files/WelinderEtal10_CUB-200.pdf), which is a fine grid dataset with 200 different types of birds. Firstly, we need to download the dataset. For download, please refer to [Official Website](http://www.vision.caltech.edu/visipedia/CUB-200-2011.html).
```shell
# linux or mac
cd dataset
# Copy the downloaded data into a directory.
cp{Data storage path}/CUB_200_2011.tgz .
# Unzip
tar-xzvf CUB_200_2011.tgz
#go to `CUB_200_2011`
cd CUB_200_2011
```
When using the dataset for image retrieval, we usually use the first 100 classes as the training set, and the last 100 classes as the testing set, so we need to process those data so as to adapt the model training of image retrival.
```shell
#Create train and test directories
mkdir train &&mkdir test
#Divide data into training set with the first 100 classes and testing set with the last 100 classes.
ls images | awk-F"."'{if(int($1)<101)print "mv images/"$0" train/"int($1)}' | sh
ls images | awk-F"."'{if(int($1)>100)print "mv images/"$0" test/"int($1)}' | sh
So far, we have the training set (in the `train` catalog) and testing set (in the `test` catalog) of `CUB_200_2011`.
After data preparation, the `train` directory of `CUB_200_2011` should be:
```
├── 1
│ ├── Black_Footed_Albatross_0001_796111.jpg
│ ├── Black_Footed_Albatross_0002_55.jpg
...
├── 10
│ ├── Red_Winged_Blackbird_0001_3695.jpg
│ ├── Red_Winged_Blackbird_0005_5636.jpg
...
```
`train_list.txt` Should be：
```
train/99/Ovenbird_0137_92639.jpg 99 1
train/99/Ovenbird_0136_92859.jpg 99 2
train/99/Ovenbird_0135_93168.jpg 99 3
train/99/Ovenbird_0131_92559.jpg 99 4
train/99/Ovenbird_0130_92452.jpg 99 5
...
```
The separators are shown as spaces, and the meaning of those three columns of data are the directory of training set, labels of training set and unique ids of training set.
The format of testing set is the same as the one of training set.
**Note**：
* When the gallery dataset and query dataset are the same, in order to remove the first data retrieved (the retrieved images themselves do not need to be evaluated), each data needs to correspond to a unique id for subsequent evaluation of metrics such as mAP, recall@1, etc. Please refer to [Introduction to image retrieval datasets](#Introduction to image retrieval datasets) for the analysis of gallery datasets and query datasets, and [Image retrieval evaluation metrics](#Image retrieval evaluation metrics) for the evaluation of mAP, recall@1, etc.
For training and evaluation on a single GPU, the `tools/train.py` and `tools/eval.py` scripts are recommended.
<aname="Model-Training"></a>
### 2.1 Model Training
Once you have prepared the configuration file, you can start training the image retrieval task in the following way. the method used by PaddleClas to train the image retrieval is metric learning, refering to [metric learning](#Metric-Learning) for an explanation of metric learning.
`-c` is used to specify the path to the configuration file, and `-o` is used to specify the parameters that need to be modified or added, where `-o Arch.Backbone.pretrained=True` indicates that the Backbone part uses the pre-trained model, in addition, `Arch.Backbone.pretrained` can also specify backbone.`pretrained` can also specify the address of a specific model weight file, which needs to be replaced with the path to your own pre-trained model weight file when using it. `-o Global.device=gpu` indicates that the GPU is used for training. If you want to use a CPU for training, you need to set `Global.device` to `cpu`.
For more detailed training configuration, you can also modify the corresponding configuration file of the model directly. Refer to the [configuration document](config_en.md) for specific configuration parameters.
Run the above commands to check the output log, an example is as follows:
The Backbone here is MobileNetV1, if you want to use other backbone, you can rewrite the parameter `Arch.Backbone.name`, for example by adding `-o Arch.Backbone.name={other Backbone}` to the command. In addition, as the input dimension of the `Neck` section differs between models, replacing a Backbone may require rewriting the input size here in a similar way to replacing the Backbone's name.
In the Training Loss section, [CELoss](../../../ppcls/loss/celoss.py) and [TripletLossV2](../../../ppcls/loss/triplet.py) is used here with the following configuration files.
```
Loss:
Train:
- CELoss:
weight: 1.0
- TripletLossV2:
weight: 1.0
margin: 0.5
```
The final total Loss is a weighted sum of all Losses, where weight defines the weight of a particular Loss in the final total. If you want to replace other Losses, you can also change the Loss field in the configuration file, for the currently supported Losses please refer to [Loss](../../../ppcls/loss).
<aname="Resume-Training"></a>
### 2.2 Resume Training
If the training task is terminated for some reasons, it can be recovered by loading the checkpoints weights file and continue training.
There is no need to modify the configuration file, just set the `Global.checkpoints` parameter when continuing training, indicating the path to the loaded breakpoint weights file, using this parameter will load both the saved checkpoints weights and information about the learning rate, optimizer, etc.
**Note**：
* The `-o Global.checkpoints` parameter need not contain the suffix name of the checkpoint weights file, the above training command will generate the breakpoint weights file as shown below during training, if you want to continue training from breakpoint `5` then the `Global.checkpoints` parameter just needs to be set to `". /output/RecModel/epoch_5"` and PaddleClas will automatically supplement the suffix name.
```shell
output/
└── RecModel
├── best_model.pdopt
├── best_model.pdparams
├── best_model.pdstates
├── epoch_1.pdopt
├── epoch_1.pdparams
├── epoch_1.pdstates
.
.
.
```
<aname="Model-Evaluation"></a>
### 2.3 Model Evaluation
Model evaluation can be carried out with the following commands.
The above command will use `. /configs/quick_start/MobileNetV1_retrieval.yaml` as a configuration file to evaluate the model obtained from the above training `. /output/RecModel/best_model` for evaluation. You can also set up the evaluation by changing the parameters in the configuration file, or you can update the configuration with the `-o` parameter, as shown above.
Some of the configurable evaluation parameters are introduced as follows.
*`Arch.name`: the name of the model
*`Global.pretrained_model`: path to the pre-trained model file of the model to be evaluated, unlike `Global.Backbone.pretrained` where the pre-trained model is the weight of the whole model, whereas `Global.Backbone.pretrained` is only the Backbone.`pretrained` is only the weight of the Backbone part. When it is time to do model evaluation, the weights of the whole model need to be loaded.
*`Metric.Eval`: the metric to be evaluated, by default evaluates recall@1, recall@5, mAP. when you are not going to evaluate a metric, you can remove the corresponding trial marker from the configuration file; when you want to add a certain evaluation metric, you can also refer to [Metric](../../../ppcls/metric/metrics.py) section to add the relevant metric to the configuration file `Metric.Eval`.
**Note：**
* When loading the model to be evaluated, the path to the model file needs to be specified, but it is not necessary to include the file suffix, PaddleClas will automatically complete the `.pdparams` suffix, e.g. [2.2 Resume Training](#Resume-Training).
* Metric learning are generally not evaluated for TopkAcc.
<aname="Export-Inference-Model"></a>
## 3. Export Inference Model
By exporting the inference model, PaddlePaddle supports the transformation of the trained model using prediction with inference engine.
`Global.pretrained_model` is used to specify the model file path, which still does not need to contain the model file suffix (e.g. [2.2 Model recovery training](#Model recovery training)). When executed, it will generate the `. /inference` directory, which contains the `inference.pdiparams`, `inference.pdiparams.info`, and `inference.pdmodel` files. `Global.save_inference_dir` allows you to specify the path to export the inference model. The inference model saved here is truncated at the embedding feature level, i.e. the final output of the model is n-dimensional embedding features.
The above command will generate the model structure file (`inference.pdmodel`) and the model weights file (`inference.pdiparams`), which can then be used for inference using the inference engine. The process of inference using the inference model can be found in [Predictive inference based on the Python prediction engine](@shengyu).
## Basic knowledge
Image retrieval refers to a query image given a specific instance (e.g. a specific target, scene, item, etc.) that contains the same instance from a database image. Unlike image classification, image retrieval solves an open set problem where the training set may not contain the class of the image being recognised. The overall process of image retrieval is: firstly, the images are represented in a suitable feature vector, secondly, a nearest neighbour search is performed on these image feature vectors using Euclidean or Cosine distances to find similar images in the base, and finally, some post-processing techniques can be used to fine-tune the retrieval results and determine information such as the category of the image being recognised. Therefore, the key to determining the performance of an image retrieval algorithm lies in the goodness of the feature vectors corresponding to the images.
<aname="Metric-Learning"></a>
- Metric Learning
Metric learning studies how to learn a distance function on a particular task so that the distance function can help nearest-neighbour based algorithms (kNN, k-means, etc.) to achieve better performance. Deep Metric Learning is a method of metric learning that aims to learn a mapping from the original features to a low-dimensional dense vector space (embedding space) such that similar objects on the embedding space are closer together using commonly used distance functions (Euclidean distance, cosine distance, etc.) ) on the embedding space, while the distances between objects of different classes are relatively close to each other. Deep metric learning has achieved very successful applications in the field of computer vision, such as face recognition, commodity recognition, image retrieval, pedestrian re-identification, etc.
<aname="Introduction to Image Retrieval Datasets"></a>
- Introduction to image retrieval datasets
- Training Dataset: used to train the model so that it can learn the image features of the collection.
- Gallery Dataset: used to provide the gallery data for the image retrieval task. The gallery dataset can be the same as the training set or the test set, or different.
- Test Set (Query Dataset): used to test the goodness of the model, usually each test image in the test set is extracted with features, and then matched with the features of the underlying data to obtain recognition results, and then the metrics of the whole test set are calculated based on the recognition results.
<aname="Image Retrieval Evaluation Metrics"></a>
- Image Retrieval Evaluation Metrics
<aname="Recall"></a>
- recall：indicates the number of predicted positive cases with positive labels / the number of cases with positive labels
- recall@1：Number of predicted positive cases in top-1 with positive label / Number of cases with positive label
- recall@5：Number of all predicted positive cases in top-5 retrieved with positive label / Number of cases with positive label
<aname="mean Average Precision"></a>
- mean Average Precision(mAP)
- AP: AP refers to the average precision on different recall rates
- mAP: Average of the APs for all images in the test set
@@ -34,32 +34,43 @@ If the image category already exists in the image index database, then you can t
The detection model with the recognition inference model for the 4 directions (Logo, Cartoon Face, Vehicle, Product), the address for downloading the test data and the address of the corresponding configuration file are as follows.
| Models Introduction | Recommended Scenarios | Test Data Address | inference Model | Predict Config File | Config File to Build Index Database |
**Attention**：If you do not have wget installed on Windows, you can download the model by copying the link into your browser and unzipping it in the appropriate folder; for Linux or macOS users, you can right-click and copy the download link to download it via the `wget` command.
Demo data in this tutorial can be downloaded here: [download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognition_demo_data_v1.0.tar).
* You can download and unzip the data and models by following the command below
**Attention**
1. If you do not have wget installed on Windows, you can download the model by copying the link into your browser and unzipping it in the appropriate folder; for Linux or macOS users, you can right-click and copy the download link to download it via the `wget` command.
2. If you want to install `wget` on macOS, you can run the following command.
```shell
mkdir dataset
cd dataset
# Download the demo data and unzip
wget {Data download link}&&tar-xf{Name of the tar archive}
3. If you want to isntall `wget` on Windows, you can refer to [link](https://www.cnblogs.com/jeshy/p/10518062.html). If you want to install `tar` on Windows, you can refer to [link](https://www.cnblogs.com/chooperman/p/14190107.html).
* You can download and unzip the data and models by following the command below
```shell
mkdir models
cd models
# Download and unzip the inference model
wget {Models download link}&&tar-xf{Name of the tar archive}
cd ..
# Download the demo data and unzip
wget {Data download link}&&tar-xf{Name of the tar archive}
Once unpacked, the `dataset` folder should have the following file structure.
Once unpacked, the `recognition_demo_data_v1.0` folder should have the following file structure.
```
├── product_demo_data_v1.0
│ ├── data_file.txt
│ ├── gallery
│ ├── index
│ └── query
├── recognition_demo_data_v1.0
│ ├── gallery_cartoon
│ ├── gallery_logo
│ ├── gallery_product
│ ├── gallery_vehicle
│ ├── test_cartoon
│ ├── test_logo
│ ├── test_product
│ └── test_vehicle
├── ...
```
The `data_file.txt` is images list used to build the index database, the `gallery` folder contains all the original images used to build the index database, the `index` folder contains the index files generated by building the index database, and the `query` is the demo image used to test the recognition effect.
here, original images to build index are in folder `gallery_xxx`, test images are in folder `test_xxx`. You can also access specific folder for more details.
The `models` folder should have the following file structure.
...
...
@@ -119,33 +131,39 @@ Take the product recognition demo as an example to show the recognition and retr
<aname="recognition_of_single_image"></a>
#### 2.2.1 Single Image Recognition
Run the following command to identify and retrieve the image `./dataset/product_demo_data_v1.0/query/wangzai.jpg` for recognition and retrieval
Run the following command to identify and retrieve the image `./recognition_demo_data_v1.0/test_product/daoxiangcunjinzhubing_6.jpg` for recognition and retrieval
**Note:** Program lib used to build index is compliled on our machine, if error occured because of the environment, you can refer to [vector search tutorial](../../../deploy/vector_search/README.md) to rebuild the lib.
where bbox indicates the location of the detected subject, rec_docs indicates the labels corresponding to a number of images in the index dabase that are most similar to the detected subject, and rec_scores indicates the corresponding similarity.
There are 4 `旺仔牛奶` results in 5, the recognition result is correct.
where bbox indicates the location of the detected object, rec_docs indicates the labels corresponding to the label in the index dabase that are most similar to the detected object, and rec_scores indicates the corresponding confidence.
The detection result is also saved in the folder `output`, which is shown as follows.
The detection result is also saved in the folder `output`, for this image, the visualization result is as follows.
@@ -155,34 +173,49 @@ The detection result is also saved in the folder `output`, which is shown as fol
If you want to predict the images in the folder, you can directly modify the `Global.infer_imgs` field in the configuration file, or you can also modify the corresponding configuration through the following `-o` parameter.
All the visualization results are also saved in folder `output`.
Furthermore, the recognition inference model path can be changed by modifying the `Global.rec_inference_model_dir` field, and the path of the index to the index databass can be changed by modifying the `IndexProcess.index_path` field.
Since the index infomation is not included in the corresponding index databse, the recognition results are not proper. At this time, we can complete the image recognition of unknown categories by constructing a new index database.
Since the index infomation is not included in the corresponding index databse, the recognition result is empty or not proper. At this time, we can complete the image recognition of unknown categories by constructing a new index database.
When the index database cannot cover the scenes we actually recognise, i.e. when predicting images of unknown categories, we need to add similar images of the corresponding categories to the index databasey, thus completing the recognition of images of unknown categories ，which does not require retraining.
...
...
@@ -192,28 +225,28 @@ When the index database cannot cover the scenes we actually recognise, i.e. when
First, you need to copy the images which are similar with the image to retrieval to the original images for the index database. The command is as follows.
Then you need to create a new label file which records the image path and label information. Use the following command to create a new file based on the original one.
Then add some new lines into the new label file, which is shown as follows.
```
gallery/anmuxi/001.jpg安慕希酸奶
gallery/anmuxi/002.jpg安慕希酸奶
gallery/anmuxi/003.jpg安慕希酸奶
gallery/anmuxi/004.jpg安慕希酸奶
gallery/anmuxi/005.jpg安慕希酸奶
gallery/anmuxi/006.jpg安慕希酸奶
gallery/anmuxi/001.jpg安慕希酸奶
gallery/anmuxi/002.jpg安慕希酸奶
gallery/anmuxi/003.jpg安慕希酸奶
gallery/anmuxi/004.jpg安慕希酸奶
gallery/anmuxi/005.jpg安慕希酸奶
gallery/anmuxi/006.jpg安慕希酸奶
```
Each line can be splited into two fields. The first field denotes the relative image path, and the second field denotes its label. The `delimiter` is `space` here.
Each line can be splited into two fields. The first field denotes the relative image path, and the second field denotes its label. The `delimiter` is `tab` here.
<aname="build_a_new_index_library"></a>
...
...
@@ -222,25 +255,30 @@ Each line can be splited into two fields. The first field denotes the relative i
Use the following command to build the index to accelerate the retrieval process after recognition.
Finally, the new index information is stored in the folder`./dataset/product_demo_data_v1.0/index_update`. Use the new index database for the above index.
Finally, the new index information is stored in the folder`./recognition_demo_data_v1.0/gallery_product/index_update`. Use the new index database for the above index.
