diff --git a/deploy/configs/inference_logo.yaml b/deploy/configs/inference_logo.yaml index 0385387f6..a98b6c387 100644 --- a/deploy/configs/inference_logo.yaml +++ b/deploy/configs/inference_logo.yaml @@ -1,5 +1,5 @@ Global: - infer_imgs: "./recognition_demo_data_v1.0/gallery/test_logo" + infer_imgs: "./recognition_demo_data_v1.0/test_logo" det_inference_model_dir: "./models/ppyolov2_r50vd_dcn_mainbody_v1.0_infer/" rec_inference_model_dir: "./models/logo_rec_ResNet50_Logo3K_v1.0_infer/" rec_nms_thresold: 0.05 diff --git a/deploy/utils/draw_bbox.py b/deploy/utils/draw_bbox.py index 8246fbf43..7c8044d1b 100644 --- a/deploy/utils/draw_bbox.py +++ b/deploy/utils/draw_bbox.py @@ -26,9 +26,9 @@ def draw_bbox_results(image, if isinstance(image, np.ndarray): image = Image.fromarray(image) draw = ImageDraw.Draw(image) - font = ImageFont.truetype(font_path, 20, encoding="utf-8") + font_size = 18 + font = ImageFont.truetype(font_path, font_size, encoding="utf-8") -# color = (0, 255, 0) color = (0, 102, 255) for result in results: @@ -38,15 +38,14 @@ def draw_bbox_results(image, xmin, ymin, xmax, ymax = result["bbox"] text = "{}, {:.2f}".format(result["rec_docs"], result["rec_scores"]) - th = 20 - tw = int(len(result["rec_docs"]) * 20) + 60 + th = font_size + tw = int(len(result["rec_docs"]) * font_size) + 60 start_y = max(0, ymin - th) - -# draw.rectangle( -# [(xmin + 1, start_y), (xmin + tw + 1, start_y + th)], -# outline=color) - draw.text((xmin + 1, start_y), text, fill=color, font=font) + draw.rectangle( + [(xmin + 1, start_y), (xmin + tw + 1, start_y + th)], fill=color) + + draw.text((xmin + 1, start_y), text, fill=(255, 255, 255), font=font) draw.rectangle( [(xmin, ymin), (xmax, ymax)], outline=(255, 0, 0), width=2) diff --git a/docs/en/tutorials/quick_start_recognition_en.md b/docs/en/tutorials/quick_start_recognition_en.md index fdd14589c..7d9925ceb 100644 --- a/docs/en/tutorials/quick_start_recognition_en.md +++ b/docs/en/tutorials/quick_start_recognition_en.md @@ -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 | -| ------------ | ------------- | ------- | -------- | ------- | -------- | -| Generic mainbody detection model | General Scenarios | - |[Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/ppyolov2_r50vd_dcn_mainbody_v1.0_infer.tar) | - | - | -| Logo Recognition Model | Logo Scenario | [Data Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/logo_demo_data_v1.0.tar) | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/logo_rec_ResNet50_Logo3K_v1.0_infer.tar) | [inference_logo.yaml](../../../deploy/configs/inference_logo.yaml) | [build_logo.yaml](../../../deploy/configs/build_logo.yaml) | -| Cartoon Face Recognition Model| Cartoon Face Scenario | [Data Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/cartoon_demo_data_v1.0.tar) | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/cartoon_rec_ResNet50_iCartoon_v1.0_infer.tar) | [inference_cartoon.yaml](../../../deploy/configs/inference_cartoon.yaml) | [build_cartoon.yaml](../../../deploy/configs/build_cartoon.yaml) | -| Vehicle Subclassification Model | Vehicle Scenario | [Data Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/vehicle_demo_data_v1.0.tar) | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/vehicle_cls_ResNet50_CompCars_v1.0_infer.tar) | [inference_vehicle.yaml](../../../deploy/configs/inference_vehicle.yaml) | [build_vehicle.yaml](../../../deploy/configs/build_vehicle.yaml) | -| Product Recignition Model | Product Scenario | [Data Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/product_demo_data_v1.0.tar) | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/product_ResNet50_vd_Inshop_v1.0_infer.tar) | [inference_inshop.yaml](../../../deploy/configs/) | [build_inshop.yaml](../../../deploy/configs/build_inshop.yaml) | +| Models Introduction | Recommended Scenarios | inference Model | Predict Config File | Config File to Build Index Database | +| ------------ | ------------- | -------- | ------- | -------- | +| Generic mainbody detection model | General Scenarios |[Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/ppyolov2_r50vd_dcn_mainbody_v1.0_infer.tar) | - | - | +| Logo Recognition Model | Logo Scenario | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/logo_rec_ResNet50_Logo3K_v1.0_infer.tar) | [inference_logo.yaml](../../../deploy/configs/inference_logo.yaml) | [build_logo.yaml](../../../deploy/configs/build_logo.yaml) | +| Cartoon Face Recognition Model| Cartoon Face Scenario | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/cartoon_rec_ResNet50_iCartoon_v1.0_infer.tar) | [inference_cartoon.yaml](../../../deploy/configs/inference_cartoon.yaml) | [build_cartoon.yaml](../../../deploy/configs/build_cartoon.yaml) | +| Vehicle Subclassification Model | Vehicle Scenario | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/vehicle_cls_ResNet50_CompCars_v1.0_infer.tar) | [inference_vehicle.yaml](../../../deploy/configs/inference_vehicle.yaml) | [build_vehicle.yaml](../../../deploy/configs/build_vehicle.yaml) | +| Product Recignition Model | Product Scenario | [Model Download Link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/product_ResNet50_vd_Inshop_v1.0_infer.tar) | [inference_inshop.yaml](../../../deploy/configs/) | [build_inshop.yaml](../../../deploy/configs/build_inshop.yaml) | -**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). + + +**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 +# install homebrew +ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"; +# install wget +brew install wget +``` + +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 dataset -cd dataset -# Download the demo data and unzip -wget {Data download link} && tar -xf {Name of the tar archive} -cd .. - 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} ``` @@ -75,27 +86,28 @@ cd models wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/ppyolov2_r50vd_dcn_mainbody_v1.0_infer.tar && tar -xf ppyolov2_r50vd_dcn_mainbody_v1.0_infer.tar # Download and unpack the inference model wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/inference/product_ResNet50_vd_aliproduct_v1.0_infer.tar && tar -xf product_ResNet50_vd_aliproduct_v1.0_infer.tar - cd .. -mkdir dataset -cd dataset + # Download the demo data and unzip it -wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/product_demo_data_v1.0.tar && tar -xf product_demo_data_v1.0.tar -cd .. +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 ``` -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 #### 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 ```shell +# use the following command to predict using GPU. +python3.7 python/predict_system.py -c configs/inference_product.yaml +# use the following command to predict using CPU python3.7 python/predict_system.py -c configs/inference_product.yaml ``` +**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 final output is shown below. ``` -[{'bbox': [305, 226, 776, 930], 'rec_docs': ['旺仔牛奶', '旺仔牛奶', '旺仔牛奶', '旺仔牛奶', '康师傅方便面'], 'rec_scores': array([1328.1072998 , 1185.92248535, 846.88220215, 746.28546143 622.2668457 ])} +[{'bbox': [287, 129, 497, 326], 'rec_docs': '稻香村金猪饼', 'rec_scores': 0.8309420943260193}, {'bbox': [99, 242, 313, 426], 'rec_docs': '稻香村金猪饼', 'rec_scores': 0.7245652079582214}] ``` -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. ```shell -python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./dataset/product_demo_data_v1.0/query/" +# 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/" ``` + +The results on the screen are shown as following. + +``` +... +[{'bbox': [37, 29, 123, 89], 'rec_docs': '香奈儿包', 'rec_scores': 0.6163763999938965}, {'bbox': [153, 96, 235, 175], 'rec_docs': '香奈儿包', 'rec_scores': 0.5279821157455444}] +[{'bbox': [735, 562, 1133, 851], 'rec_docs': '香奈儿包', 'rec_scores': 0.5588355660438538}] +[{'bbox': [124, 50, 230, 129], 'rec_docs': '香奈儿包', 'rec_scores': 0.6980369687080383}] +[{'bbox': [0, 0, 275, 183], 'rec_docs': '香奈儿包', 'rec_scores': 0.5818190574645996}] +[{'bbox': [400, 1179, 905, 1537], 'rec_docs': '香奈儿包', 'rec_scores': 0.9814301133155823}] +[{'bbox': [544, 4, 1482, 932], 'rec_docs': '香奈儿包', 'rec_scores': 0.5143815279006958}] +[{'bbox': [29, 42, 194, 183], 'rec_docs': '香奈儿包', 'rec_scores': 0.9543638229370117}] +... +``` + +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. ## 3. Recognize Images of Unknown Category -To recognize the image `./dataset/product_demo_data_v1.0/query/anmuxi.jpg`, run the command as follows: +To recognize the image `./recognition_demo_data_v1.0/test_product/anmuxi.jpg`, run the command as follows: ```shell -python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./dataset/product_demo_data_v1.0/query/anmuxi.jpg" +python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./recognition_demo_data_v1.0/test_product/anmuxi.jpg" ``` The image to be retrieved is shown below.
- +
-The output is as follows: +The output is empty. -``` -[{'bbox': [243, 80, 523, 522], 'rec_docs': ['娃哈哈AD钙奶', '旺仔牛奶', '娃哈哈AD钙奶', '农夫山泉矿泉水', '红牛'], 'rec_scores': array([548.33282471, 411.85687256, 408.39770508, 400.89404297, 360.41540527])}] -``` - -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. ```shell -cp -r ../docs/images/recognition/product_demo/gallery/anmuxi ./dataset/product_demo_data_v1.0/gallery/ +cp -r ../docs/images/recognition/product_demo/gallery/anmuxi ./recognition_demo_data_v1.0/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. ```shell # copy the file -cp dataset/product_demo_data_v1.0/data_file.txt dataset/product_demo_data_v1.0/data_file_update.txt +cp recognition_demo_data_v1.0/gallery_product/data_file.txt recognition_demo_data_v1.0/gallery_product/data_file_update.txt ``` 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. @@ -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. ```shell -python3.7 python/build_gallery.py -c configs/build_product.yaml -o IndexProcess.data_file="./dataset/product_demo_data_v1.0/data_file_update.txt" -o IndexProcess.index_path="./dataset/product_demo_data_v1.0/index_update" +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" ``` -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. ### 3.2 Recognize the Unknown Category Images -To recognize the image `./dataset/product_demo_data_v1.0/query/anmuxi.jpg`, run the command as follows. +To recognize the image `./recognition_demo_data_v1.0/test_product/anmuxi.jpg`, run the command as follows. ```shell -python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.infer_imgs="./dataset/product_demo_data_v1.0/query/anmuxi.jpg" -o IndexProcess.index_path="./dataset/product_demo_data_v1.0/index_update" +# 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" ``` The output is as follows: ``` -[{'bbox': [243, 80, 523, 522], 'rec_docs': ['安慕希酸奶', '娃哈哈AD钙奶', '安慕希酸奶', '安慕希酸奶', '安慕希酸奶'], 'rec_scores': array([1214.9597168 , 548.33282471, 547.82104492, 535.13201904, 471.52706909])}] +[{'bbox': [243, 80, 523, 522], 'rec_docs': '安慕希酸奶', 'rec_scores': 0.5570770502090454}] ``` -There are 4 `安慕希酸奶` results in 5, the recognition result is correct. +The final recognition result is `安慕希酸奶`, which is corrrect, the visualization result is as follows. + +
+ +
diff --git a/docs/images/recognition/product_demo/result/anmuxi.jpg b/docs/images/recognition/product_demo/result/anmuxi.jpg index 8749fe1cb..4b219e2b8 100644 Binary files a/docs/images/recognition/product_demo/result/anmuxi.jpg and b/docs/images/recognition/product_demo/result/anmuxi.jpg differ diff --git a/docs/images/recognition/product_demo/result/daoxiangcunjinzhubing_6.jpg b/docs/images/recognition/product_demo/result/daoxiangcunjinzhubing_6.jpg index babc6cea1..645ad6c87 100644 Binary files a/docs/images/recognition/product_demo/result/daoxiangcunjinzhubing_6.jpg and b/docs/images/recognition/product_demo/result/daoxiangcunjinzhubing_6.jpg differ diff --git a/docs/zh_CN/tutorials/quick_start_recognition.md b/docs/zh_CN/tutorials/quick_start_recognition.md index dc9fa2c0c..662b95d26 100644 --- a/docs/zh_CN/tutorials/quick_start_recognition.md +++ b/docs/zh_CN/tutorials/quick_start_recognition.md @@ -157,7 +157,7 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.u 其中bbox表示检测出的主体所在位置，rec_docs表示索引库中与检测框最为相似的类别，rec_scores表示对应的置信度。 -检测的可视化结果也保存在`output`文件夹下，对于本章图像，识别结果可视化如下所示。 +检测的可视化结果也保存在`output`文件夹下，对于本张图像，识别结果可视化如下所示。
@@ -236,12 +236,12 @@ cp recognition_demo_data_v1.0/gallery_product/data_file.txt recognition_demo_dat 然后在文件`recognition_demo_data_v1.0/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/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 ``` 每一行的文本中，第一个字段表示图像的相对路径，第二个字段表示图像对应的标签信息，中间用`tab`键分隔开（注意：有些编辑器会将`tab`自动转换为`空格`，这种情况下会导致文件解析报错）。 @@ -275,7 +275,7 @@ python3.7 python/predict_system.py -c configs/inference_product.yaml -o Global.i [{'bbox': [243, 80, 523, 522], 'rec_docs': '安慕希酸奶', 'rec_scores': 0.5570770502090454}] ``` -最终返回结果为`安慕希酸奶`，识别正确，识别结果可视化如下所示。 +最终识别结果为`安慕希酸奶`，识别正确，识别结果可视化如下所示。