Skip to content

P
PaddleClas

PaddlePaddle / PaddleClas
大约 2 年 前同步成功

通知 118
Star 4999
Fork 1114
P
PaddleClas
未验证 提交 497eb40a 编写于 作者: W Walter 提交者： GitHub
浏览文件
操作

Merge pull request #1217 from RainFrost1/faiss 

fix quick_start_recognition docs
上级 1d7ffd15 7f5efeac
隐藏空白更改
内联 并排
Showing with 52 addition and 40 deletion
docs/en/tutorials/quick_start_recognition_en.md
浏览文件 @ 497eb40a
...@@ -90,13 +90,13 @@ wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/infere ...@@ -90,13 +90,13 @@ wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/infere
cd .. cd ..
# Download the demo data and unzip it # Download the demo data and unzip it
wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognition_demo_data_en_v1.0.tar && tar -xf recognition_demo_data_en_v1.0.tar wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognition_demo_data_en_v1.1.tar && tar -xf recognition_demo_data_en_v1.1.tar
``` ```
Once unpacked, the `recognition_demo_data_v1.0` folder should have the following file structure. Once unpacked, the `recognition_demo_data_v1.1` folder should have the following file structure.
``` ```
├── recognition_demo_data_v1.0 ├── recognition_demo_data_v1.1
│ ├── gallery_cartoon │ ├── gallery_cartoon
│ ├── gallery_logo │ ├── gallery_logo
│ ├── gallery_product │ ├── gallery_product
...@@ -126,13 +126,21 @@ The `models` folder should have the following file structure. ...@@ -126,13 +126,21 @@ The `models` folder should have the following file structure.
<a name="Product_recognition_and_retrival"></a> <a name="Product_recognition_and_retrival"></a>
### 2.2 Product Recognition and Retrieval ### 2.2 Product Recognition and Retrieval
Take the product recognition demo as an example to show the recognition and retrieval process (if you wish to try other scenarios of recognition and retrieval, replace the corresponding configuration file after downloading and unzipping the corresponding demo data and model to complete the prediction)。 Take the product recognition demo as an example to show the recognition and retrieval process (if you wish to try other scenarios of recognition and retrieval, replace the corresponding configuration file after downloading and unzipping the corresponding demo data and model to complete the prediction).
**Note:** `faiss` is used as search library. The installation method is as follows：
```
pip install faiss-cpu==1.7.1post2
```
If error happens when using `import faiss`, please uninstall `faiss` and reinstall it, especially on `Windows`.
<a name="recognition_of_single_image"></a> <a name="recognition_of_single_image"></a>
#### 2.2.1 Single Image Recognition #### 2.2.1 Single Image Recognition
Run the following command to identify and retrieve the image `./recognition_demo_data_v1.0/test_product/daoxiangcunjinzhubing_6.jpg` for recognition and retrieval Run the following command to identify and retrieve the image `./recognition_demo_data_v1.1/test_product/daoxiangcunjinzhubing_6.jpg` for recognition and retrieval
```shell ```shell
# use the following command to predict using GPU. # use the following command to predict using GPU.
...@@ -141,8 +149,6 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml ...@@ -141,8 +149,6 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.use_gpu=False python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.use_gpu=False
``` ```
**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.
The image to be retrieved is shown below. The image to be retrieved is shown below.
...@@ -175,7 +181,7 @@ If you want to predict the images in the folder, you can directly modify the `Gl ...@@ -175,7 +181,7 @@ If you want to predict the images in the folder, you can directly modify the `Gl
```shell ```shell
# using the following command to predict using GPU, you can append `-o Global.use_gpu=False` to predict using CPU. # using the following command to predict using GPU, you can append `-o Global.use_gpu=False` to predict using CPU.
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.0/test_product/" python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.1/test_product/"
``` ```
...@@ -195,16 +201,16 @@ The results on the screen are shown as following. ...@@ -195,16 +201,16 @@ The results on the screen are shown as following.
All the visualization results are also saved in folder `output`. 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. 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_dir` field.
<a name="unkonw_category_image_recognition_experience"></a> <a name="unkonw_category_image_recognition_experience"></a>
## 3. Recognize Images of Unknown Category ## 3. Recognize Images of Unknown Category
To recognize the image `./recognition_demo_data_v1.0/test_product/anmuxi.jpg`, run the command as follows: To recognize the image `./recognition_demo_data_v1.1/test_product/anmuxi.jpg`, run the command as follows:
```shell ```shell
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.0/test_product/anmuxi.jpg" python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.1/test_product/anmuxi.jpg"
``` ```
The image to be retrieved is shown below. The image to be retrieved is shown below.
...@@ -225,14 +231,14 @@ When the index database cannot cover the scenes we actually recognise, i.e. when ...@@ -225,14 +231,14 @@ 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. 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.
```shell ```shell
cp -r ../docs/images/recognition/product_demo/gallery/anmuxi ./recognition_demo_data_v1.0/gallery_product/gallery/ cp -r ../docs/images/recognition/product_demo/gallery/anmuxi ./recognition_demo_data_/gallery_product/gallery/
``` ```
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 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.
```shell ```shell
# copy the file # copy the file
cp recognition_demo_data_v1.0/gallery_product/data_file.txt recognition_demo_data_v1.0/gallery_product/data_file_update.txt cp recognition_demo_data_v1.1/gallery_product/data_file.txt recognition_demo_data_v1.1/gallery_product/data_file_update.txt
``` ```
Then add some new lines into the new label file, which is shown as follows. Then add some new lines into the new label file, which is shown as follows.
...@@ -255,20 +261,20 @@ Each line can be splited into two fields. The first field denotes the relative i ...@@ -255,20 +261,20 @@ 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. Use the following command to build the index to accelerate the retrieval process after recognition.
```shell ```shell
python3.7 python/build_gallery.py -c configs/build_product.yaml -o IndexProcess.data_file="./recognition_demo_data_v1.0/gallery_product/data_file_update.txt" -o IndexProcess.index_path="./recognition_demo_data_v1.0/gallery_product/index_update" python3.7 python/build_gallery.py -c configs/build_product.yaml -o IndexProcess.data_file="./recognition_demo_data_v1.1/gallery_product/data_file_update.txt" -o IndexProcess.index_dir="./recognition_demo_data_v1.1/gallery_product/index_update"
``` ```
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. Finally, the new index information is stored in the folder`./recognition_demo_data_v1.1/gallery_product/index_update`. Use the new index database for the above index.
<a name="Image_differentiation_based_on_the_new_index_library"></a> <a name="Image_differentiation_based_on_the_new_index_library"></a>
### 3.2 Recognize the Unknown Category Images ### 3.2 Recognize the Unknown Category Images
To recognize the image `./recognition_demo_data_v1.0/test_product/anmuxi.jpg`, run the command as follows. To recognize the image `./recognition_demo_data_v1.1/test_product/anmuxi.jpg`, run the command as follows.
```shell ```shell
# using the following command to predict using GPU, you can append `-o Global.use_gpu=False` to predict using CPU. # using the following command to predict using GPU, you can append `-o Global.use_gpu=False` to predict using CPU.
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.0/test_product/anmuxi.jpg" -o IndexProcess.index_path="./recognition_demo_data_v1.0/gallery_product/index_update" python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.1/test_product/anmuxi.jpg" -o IndexProcess.index_dir="./recognition_demo_data_v1.1/gallery_product/index_update"
``` ```
The output is as follows: The output is as follows:
......
docs/zh_CN/tutorials/quick_start_recognition.md
浏览文件 @ 497eb40a
...@@ -46,8 +46,8 @@ ...@@ -46,8 +46,8 @@
本章节demo数据下载地址如下: [数据下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognition_demo_data_v1.1.tar)。 本章节demo数据下载地址如下: [数据下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognition_demo_data_v1.1.tar)。
**注意** **注意**
1. windows 环境下如果没有安装wget,可以按照下面的步骤安装wget与tar命令，也可以在，下载模型时将链接复制到浏览器中下载，并解压放置在相应目录下；linux或者macOS用户可以右键点击，然后复制下载链接，即可通过`wget`命令下载。 1. windows 环境下如果没有安装wget,可以按照下面的步骤安装wget与tar命令，也可以在，下载模型时将链接复制到浏览器中下载，并解压放置在相应目录下；linux或者macOS用户可以右键点击，然后复制下载链接，即可通过`wget`命令下载。
2. 如果macOS环境下没有安装`wget`命令，可以运行下面的命令进行安装。 2. 如果macOS环境下没有安装`wget`命令，可以运行下面的命令进行安装。
...@@ -74,8 +74,8 @@ cd .. ...@@ -74,8 +74,8 @@ cd ..
wget {数据下载链接地址} && tar -xf {压缩包的名称} wget {数据下载链接地址} && tar -xf {压缩包的名称}
``` ```
<a name="下载、解压inference_模型与demo数据"></a> <a name="下载、解压inference_模型与demo数据"></a>
### 2.1 下载、解压inference 模型与demo数据 ### 2.1 下载、解压inference 模型与demo数据
以商品识别为例，下载demo数据集以及通用检测、识别模型，命令如下。 以商品识别为例，下载demo数据集以及通用检测、识别模型，命令如下。
...@@ -90,13 +90,13 @@ wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/infere ...@@ -90,13 +90,13 @@ wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/infere
cd ../ cd ../
# 下载demo数据并解压 # 下载demo数据并解压
wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognition_demo_data_v1.0.tar && tar -xf recognition_demo_data_v1.0.tar wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognition_demo_data_v1.1.tar && tar -xf recognition_demo_data_v1.1.tar
``` ```
解压完毕后，`recognition_demo_data_v1.0`文件夹下应有如下文件结构： 解压完毕后，`recognition_demo_data_v1.1`文件夹下应有如下文件结构：
``` ```
├── recognition_demo_data_v1.0 ├── recognition_demo_data_v1.1
│ ├── gallery_cartoon │ ├── gallery_cartoon
│ ├── gallery_logo │ ├── gallery_logo
│ ├── gallery_product │ ├── gallery_product
...@@ -129,11 +129,19 @@ wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognit ...@@ -129,11 +129,19 @@ wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/recognit
以商品识别demo为例，展示识别与检索过程（如果希望尝试其他方向的识别与检索效果，在下载解压好对应的demo数据与模型之后，替换对应的配置文件即可完成预测）。 以商品识别demo为例，展示识别与检索过程（如果希望尝试其他方向的识别与检索效果，在下载解压好对应的demo数据与模型之后，替换对应的配置文件即可完成预测）。
注意，此部分使用了`faiss`作为检索库，安装方法如下：
```python
pip install faiss-cpu==1.7.1post2
```
若使用时，不能正常引用，则`uninstall` 之后，重新`install`，尤其是windows下。
<a name="识别单张图像"></a> <a name="识别单张图像"></a>
#### 2.2.1 识别单张图像 #### 2.2.1 识别单张图像
运行下面的命令，对图像`./recognition_demo_data_v1.0/test_product/daoxiangcunjinzhubing_6.jpg`进行识别与检索 运行下面的命令，对图像`./recognition_demo_data_v1.1/test_product/daoxiangcunjinzhubing_6.jpg`进行识别与检索
```shell ```shell
# 使用下面的命令使用GPU进行预测 # 使用下面的命令使用GPU进行预测
...@@ -142,8 +150,6 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml ...@@ -142,8 +150,6 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.use_gpu=False python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.use_gpu=False
``` ```
注意：这里使用了默认编译生成的库文件进行特征索引，如果与您的环境不兼容，导致程序报错，可以参考[向量检索教程](../../../deploy/vector_search/README.md)重新编译库文件。
待检索图像如下所示。 待检索图像如下所示。
<div align="center"> <div align="center">
...@@ -173,7 +179,7 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.u ...@@ -173,7 +179,7 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.u
```shell ```shell
# 使用下面的命令使用GPU进行预测，如果希望使用CPU预测，可以在命令后面添加-o Global.use_gpu=False # 使用下面的命令使用GPU进行预测，如果希望使用CPU预测，可以在命令后面添加-o Global.use_gpu=False
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.0/test_product/" python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.1/test_product/"
``` ```
终端中会输出该文件夹内所有图像的识别结果，如下所示。 终端中会输出该文件夹内所有图像的识别结果，如下所示。
...@@ -193,17 +199,17 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.i ...@@ -193,17 +199,17 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.i
所有图像的识别结果可视化图像也保存在`output`文件夹内。 所有图像的识别结果可视化图像也保存在`output`文件夹内。
更多地，可以通过修改`Global.rec_inference_model_dir`字段来更改识别inference模型的路径，通过修改`IndexProcess.index_path`字段来更改索引库索引的路径。 更多地，可以通过修改`Global.rec_inference_model_dir`字段来更改识别inference模型的路径，通过修改`IndexProcess.index_dir`字段来更改索引库索引的路径。
<a name="未知类别的图像识别体验"></a> <a name="未知类别的图像识别体验"></a>
## 3. 未知类别的图像识别体验 ## 3. 未知类别的图像识别体验
对图像`./recognition_demo_data_v1.0/test_product/anmuxi.jpg`进行识别，命令如下 对图像`./recognition_demo_data_v1.1/test_product/anmuxi.jpg`进行识别，命令如下
```shell ```shell
# 使用下面的命令使用GPU进行预测，如果希望使用CPU预测，可以在命令后面添加-o Global.use_gpu=False # 使用下面的命令使用GPU进行预测，如果希望使用CPU预测，可以在命令后面添加-o Global.use_gpu=False
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.0/test_product/anmuxi.jpg" python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.1/test_product/anmuxi.jpg"
``` ```
待检索图像如下所示。 待检索图像如下所示。
...@@ -222,20 +228,20 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.i ...@@ -222,20 +228,20 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.i
<a name="准备新的数据与标签"></a> <a name="准备新的数据与标签"></a>
### 3.1 准备新的数据与标签 ### 3.1 准备新的数据与标签
首先需要将与待检索图像相似的图像列表拷贝到索引库原始图像的文件夹(`./recognition_demo_data_v1.0/gallery_product/gallery`)中，运行下面的命令拷贝相似图像。 首先需要将与待检索图像相似的图像列表拷贝到索引库原始图像的文件夹(`./recognition_demo_data_v1.1/gallery_product/gallery`)中，运行下面的命令拷贝相似图像。
```shell ```shell
cp -r ../docs/images/recognition/product_demo/gallery/anmuxi ./recognition_demo_data_v1.0/gallery_product/gallery/ cp -r ../docs/images/recognition/product_demo/gallery/anmuxi ./recognition_demo_data_v1.1/gallery_product/gallery/
``` ```
然后需要编辑记录了图像路径和标签信息的文本文件(`./recognition_demo_data_v1.0/gallery_product/data_file_update.txt`)，这里基于原始标签文件，新建一个文件。命令如下。 然后需要编辑记录了图像路径和标签信息的文本文件(`./recognition_demo_data_v1.1/gallery_product/data_file_update.txt`)，这里基于原始标签文件，新建一个文件。命令如下。
```shell ```shell
# 复制文件 # 复制文件
cp recognition_demo_data_v1.0/gallery_product/data_file.txt recognition_demo_data_v1.0/gallery_product/data_file_update.txt cp recognition_demo_data_v1.1/gallery_product/data_file.txt recognition_demo_data_v1.1/gallery_product/data_file_update.txt
``` ```
然后在文件`recognition_demo_data_v1.0/gallery_product/data_file_update.txt`中添加以下的信息， 然后在文件`recognition_demo_data_v1.1/gallery_product/data_file_update.txt`中添加以下的信息，
``` ```
gallery/anmuxi/001.jpg 安慕希酸奶 gallery/anmuxi/001.jpg 安慕希酸奶
...@@ -255,20 +261,20 @@ gallery/anmuxi/006.jpg 安慕希酸奶 ...@@ -255,20 +261,20 @@ gallery/anmuxi/006.jpg 安慕希酸奶
使用下面的命令构建index索引，加速识别后的检索过程。 使用下面的命令构建index索引，加速识别后的检索过程。
```shell ```shell
python3.7 python/build_gallery.py -c configs/build_product.yaml -o IndexProcess.data_file="./recognition_demo_data_v1.0/gallery_product/data_file_update.txt" -o IndexProcess.index_path="./recognition_demo_data_v1.0/gallery_product/index_update" python3.7 python/build_gallery.py -c configs/build_product.yaml -o IndexProcess.data_file="./recognition_demo_data_v1.1/gallery_product/data_file_update.txt" -o IndexProcess.index_dir="./recognition_demo_data_v1.1/gallery_product/index_update"
``` ```
最终新的索引信息保存在文件夹`./recognition_demo_data_v1.0/gallery_product/index_update`中。 最终新的索引信息保存在文件夹`./recognition_demo_data_v1.1/gallery_product/index_update`中。
<a name="基于新的索引库的图像识别"></a> <a name="基于新的索引库的图像识别"></a>
### 3.3 基于新的索引库的图像识别 ### 3.3 基于新的索引库的图像识别
使用新的索引库，对上述图像进行识别，运行命令如下。 使用新的索引库，对上述图像进行识别，运行命令如下。
```shell ```shell
# 使用下面的命令使用GPU进行预测，如果希望使用CPU预测，可以在命令后面添加-o Global.use_gpu=False # 使用下面的命令使用GPU进行预测，如果希望使用CPU预测，可以在命令后面添加-o Global.use_gpu=False
python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.0/test_product/anmuxi.jpg" -o IndexProcess.index_path="./recognition_demo_data_v1.0/gallery_product/index_update" python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.1/test_product/anmuxi.jpg" -o IndexProcess.index_dir="./recognition_demo_data_v1.1/gallery_product/index_update"
``` ```
输出结果如下。 输出结果如下。
......
requirements.txt
浏览文件 @ 497eb40a
...@@ -8,4 +8,4 @@ visualdl >= 2.0.0b ...@@ -8,4 +8,4 @@ visualdl >= 2.0.0b
scipy scipy
scikit-learn==0.23.2 scikit-learn==0.23.2
gast==0.3.3 gast==0.3.3
faiss-cpu==1.7.1 faiss-cpu==1.7.1.post2
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或