Python Inference for PP-OCR Model Zoo¶
This article introduces the use of the Python inference engine for the PP-OCR model library. The content is in order of text detection, text recognition, direction classifier and the prediction method of the three in series on the CPU and GPU.
Text Detection Model Inference¶
The default configuration is based on the inference setting of the DB text detection model. For lightweight Chinese detection model inference, you can execute the following commands:
The visual text detection results are saved to the ./inference_results folder by default, and the name of the result file is prefixed with 'det_res'. Examples of results are as follows:
You can use the parameters limit_type and det_limit_side_len to limit the size of the input image,
The optional parameters of limit_type are [max, min], and
det_limit_size_len is a positive integer, generally set to a multiple of 32, such as 960.
The default setting of the parameters is limit_type='max', det_limit_side_len=960. Indicates that the longest side of the network input image cannot exceed 960,
If this value is exceeded, the image will be resized with the same width ratio to ensure that the longest side is det_limit_side_len.
Set as limit_type='min', det_limit_side_len=960, it means that the shortest side of the image is limited to 960.
If the resolution of the input picture is relatively large and you want to use a larger resolution prediction, you can set det_limit_side_len to the desired value, such as 1216:
If you want to use the CPU for prediction, execute the command as follows
Text Recognition Model Inference¶
1. Lightweight Chinese Recognition Model Inference¶
Note: The input shape used by the recognition model of PP-OCRv3 is 3, 48, 320. If you use other recognition models, you need to set the parameter --rec_image_shape according to the model. In addition, the rec_algorithm used by the recognition model of PP-OCRv3 is SVTR_LCNet by default. Note the difference from the original SVTR.
For lightweight Chinese recognition model inference, you can execute the following commands:
After executing the command, the prediction results (recognized text and score) of the above image will be printed on the screen.
2. English Recognition Model Inference¶
For English recognition model inference, you can execute the following commands,you need to specify the dictionary path used by --rec_char_dict_path:
After executing the command, the prediction result of the above figure is:
3. Multilingual Model Inference¶
If you need to predict other language models, when using inference model prediction, you need to specify the dictionary path used by --rec_char_dict_path. At the same time, in order to get the correct visualization results,
You need to specify the visual font path through --vis_font_path. There are small language fonts provided by default under the doc/fonts path, such as Korean recognition:
After executing the command, the prediction result of the above figure is:
Angle Classification Model Inference¶
For angle classification model inference, you can execute the following commands:
After executing the command, the prediction results (classification angle and score) of the above image will be printed on the screen.
Text Detection Angle Classification and Recognition Inference Concatenation¶
Note: The input shape used by the recognition model of PP-OCRv3 is 3, 48, 320. If you use other recognition models, you need to set the parameter --rec_image_shape according to the model. In addition, the rec_algorithm used by the recognition model of PP-OCRv3 is SVTR_LCNet by default. Note the difference from the original SVTR.
When performing prediction, you need to specify the path of a single image or a folder of images through the parameter image_dir, pdf file is also supported, the parameter det_model_dir specifies the path to detect the inference model, the parameter cls_model_dir specifies the path to angle classification inference model and the parameter rec_model_dir specifies the path to identify the inference model. The parameter use_angle_cls is used to control whether to enable the angle classification model. The parameter use_mp specifies whether to use multi-process to infer total_process_num specifies process number when using multi-process. The parameter . The visualized recognition results are saved to the ./inference_results folder by default.
After executing the command, the recognition result image is as follows:
For more configuration and explanation of inference parameters, please refer to：Model Inference Parameters Explained Tutorial。
TensorRT Inference¶
Paddle Inference ensembles TensorRT using subgraph mode. For GPU deployment scenarios, TensorRT can optimize some subgraphs, including horizontal and vertical integration of OPs, filter redundant OPs, and automatically select the optimal OP kernels for to speed up inference.
You need to do the following 2 steps for inference using TRT.
- (1) Collect the dynamic shape information of the model about a specific dataset and store it in a file.
- (2) Load the dynamic shape information file for TRT inference.
Taking the text detection model as an example. Firstly, you can use the following command to generate a dynamic shape file, which will eventually be named as det_trt_dynamic_shape.txt and stored in the ch_PP-OCRv3_det_infer folder.
The above command is only used to collect dynamic shape information, and TRT is not used during inference.
Then, you can use the following command to perform TRT inference.
Note:
- In the first step, if the dynamic shape information file already exists, it does not need to be collected again. If you want to regenerate the dynamic shape information file, you need to delete the dynamic shape information file in the model folder firstly, and then regenerate it.
- In general, dynamic shape information file only needs to be generated once. In the actual deployment process, it is recommended that the dynamic shape information file can be generated on offline validation set or test set, and then the file can be directly loaded for online TRT inference.