Generally, a more complex model would achive better performance in the task, but it also leads to some redundancy in the model. Model Pruning is a technique that reduces this redundancy by removing the sub-models in the neural network model, so as to reduce model calculation complexity and improve model inference performance.
This example uses PaddleSlim provided[APIs of Pruning](https://paddlepaddle.github.io/PaddleSlim/api/prune_api/) to compress the OCR model.
PaddleSlim (GitHub: https://github.com/PaddlePaddle/PaddleSlim), an open source library which integrates model pruning, quantization (including quantization training and offline quantization), distillation, neural network architecture search, and many other commonly used and leading model compression technique in the industry.
It is recommended that you could understand following pages before reading this example,：
...
...
@@ -146,7 +147,20 @@ python setup.py install
## Pruning sensitivity analysis
After the pre-training model is loaded, sensitivity analysis is performed on each network layer of the model to understand the redundancy of each network layer, thereby determining the pruning ratio of each network layer. For specific details of sensitivity analysis, see：[Sensitivity analysis](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md)
After the pre-training model is loaded, sensitivity analysis is performed on each network layer of the model to understand the redundancy of each network layer, and save a sensitivity file which named: sensitivities_0.data. After that, user could load the sensitivity file via the [methods provided by PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/sensitive.py#L221) and determining the pruning ratio of each network layer automatically. For specific details of sensitivity analysis, see：[Sensitivity analysis](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md)
The function would return a dict after loading the sensitivity file. The keys of the dict are name of parameters in each layer. And the value of key is the information about pruning sensitivity of correspoding layer. In example, pruning 10% filter of the layer corresponding to conv10_expand_weights would lead to 0.65% degradation of model performance. The details could be seen at: [Sensitivity analysis](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/zh_cn/algo/algo.md#2-%E5%8D%B7%E7%A7%AF%E6%A0%B8%E5%89%AA%E8%A3%81%E5%8E%9F%E7%90%86)
Enter the PaddleOCR root directory，perform sensitivity analysis on the model with the following command：
Generally, a more complex model would achive better performance in the task, but it also leads to some redundancy in the model. Quantization is a technique that reduces this redundancyby reducing the full precision data to a fixed number, so as to reduce model calculation complexity and improve model inference performance.
This example uses PaddleSlim provided [APIs of Quantization](https://paddlepaddle.github.io/PaddleSlim/api/quantization_api/) to compress the OCR model.
PaddleSlim (GitHub: https://github.com/PaddlePaddle/PaddleSlim), an open source library which integrates model pruning, quantization (including quantization training and offline quantization), distillation, neural network architecture search, and many other commonly used and leading model compression technique in the industry.
It is recommended that you could understand following pages before reading this example,：
@@ -10,7 +10,7 @@ The following list can be viewed via `--help`
## INTRODUCTION TO GLOBAL PARAMETERS OF CONFIGURATION FILE
Take `rec_chinese_lite_train.yml` as an example
Take `rec_chinese_lite_train_v1.1.yml` as an example
| Parameter | Use | Default | Note |
...
...
@@ -32,6 +32,7 @@ Take `rec_chinese_lite_train.yml` as an example
| loss_type | Set loss type | ctc | Supports two types of loss: ctc / attention |
| distort | Set use distort | false | Support distort type ,read [img_tools.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/rec/img_tools.py) |
| use_space_char | Wether to recognize space | false | Only support in character_type=ch mode |
label_list | Set the angle supported by the direction classifier | ['0','180'] | Only valid in the direction classifier |
| reader_yml | Set the reader configuration file | ./configs/rec/rec_icdar15_reader.yml | \ |
@@ -38,12 +38,14 @@ If you want to train PaddleOCR on other datasets, please build the annotation fi
## TRAINING
First download the pretrained model. The detection model of PaddleOCR currently supports two backbones, namely MobileNetV3 and ResNet50_vd. You can use the model in [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/tree/master/ppcls/modeling/architectures) to replace backbone according to your needs.
First download the pretrained model. The detection model of PaddleOCR currently supports 3 backbones, namely MobileNetV3, ResNet18_vd and ResNet50_vd. You can use the model in [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/tree/master/ppcls/modeling/architectures) to replace backbone according to your needs.
**Note**: The priority of `Global.checkpoints` is higher than that of `Global.pretrain_weights`, that is, when two parameters are specified at the same time, the model specified by `Global.checkpoints` will be loaded first. If the model path specified by `Global.checkpoints` is wrong, the one specified by `Global.pretrain_weights` will be loaded.
PaddleOCR calculates three indicators for evaluating performance of OCR detection task: Precision, Recall, and Hmean.
Run the following code to calculate the evaluation indicators. The result will be saved in the test result file specified by `save_res_path` in the configuration file `det_db_mv3.yml`
Run the following code to calculate the evaluation indicators. The result will be saved in the test result file specified by `save_res_path` in the configuration file `det_db_mv3_v1.1.yml`
When evaluating, set post-processing parameters `box_thresh=0.6`, `unclip_ratio=1.5`. If you use different datasets, different models for training, these two parameters should be adjusted for better result.
The model parameters during training are saved in the `Global.save_model_dir` directory by default. When evaluating indicators, you need to set `Global.checkpoints` to point to the saved parameter file.
For more software version requirements, please refer to the instructions in [Installation Document](https://www.paddlepaddle.org.cn/install/quick) for operation.
