From e5d7571503c0d8b82f42915ad4a9bde35a4c70a3 Mon Sep 17 00:00:00 2001 From: tink2123 Date: Mon, 21 Sep 2020 20:29:41 +0800 Subject: [PATCH] fix typo and add srn for inference,test=document_fix --- doc/doc_ch/inference.md | 21 +++++++++++++--- doc/doc_ch/recognition.md | 49 +++++++++++++++++++++++++++--------- doc/doc_en/inference_en.md | 28 ++++++++++++++++----- doc/doc_en/recognition_en.md | 35 +++++++++++++++++++++----- 4 files changed, 105 insertions(+), 28 deletions(-) diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md index 8f31c695..c775de57 100644 --- a/doc/doc_ch/inference.md +++ b/doc/doc_ch/inference.md @@ -23,8 +23,9 @@ inference 模型（`fluid.io.save_inference_model`保存的模型） - [1. 超轻量中文识别模型推理](#超轻量中文识别模型推理) - [2. 基于CTC损失的识别模型推理](#基于CTC损失的识别模型推理) - [3. 基于Attention损失的识别模型推理](#基于Attention损失的识别模型推理) - - [4. 自定义文本识别字典的推理](#自定义文本识别字典的推理) - - [5. 多语言模型的推理](#多语言模型的推理) + - [4. 基于SRN损失的识别模型推理](#基于SRN损失的识别模型推理) + - [5. 自定义文本识别字典的推理](#自定义文本识别字典的推理) + - [6. 多语言模型的推理](#多语言模型的推理) - [四、方向分类模型推理](#方向识别模型推理) - [1. 方向分类模型推理](#方向分类模型推理) @@ -297,9 +298,21 @@ Predicts of ./doc/imgs_words_en/word_336.png:['super', 0.9999555] self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz" dict_character = list(self.character_str) ``` + +### 4. 基于SRN损失的识别模型推理 + +基于SRN损失的识别模型，需要额外设置识别算法参数 --rec_algorithm="SRN"。 同时需要保证预测shape与训练时一致，如： --rec_image_shape="1, 64, 256" + +``` +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" \ + --rec_model_dir="./inference/srn/" \ + --rec_image_shape="1, 64, 256" \ + --rec_char_type="en" \ + --rec_algorithm="SRN" +``` -### 4. 自定义文本识别字典的推理 +### 5. 自定义文本识别字典的推理 如果训练时修改了文本的字典，在使用inference模型预测时，需要通过`--rec_char_dict_path`指定使用的字典路径 ``` @@ -307,7 +320,7 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png ``` -### 5. 多语言模型的推理 +### 6. 多语言模型的推理 如果您需要预测的是其他语言模型，在使用inference模型预测时，需要通过`--rec_char_dict_path`指定使用的字典路径, 同时为了得到正确的可视化结果， 需要通过 `--vis_font_path` 指定可视化的字体路径，`doc/` 路径下有默认提供的小语种字体，例如韩文识别： diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md index eeb937fc..1df5ac3d 100644 --- a/doc/doc_ch/recognition.md +++ b/doc/doc_ch/recognition.md @@ -1,5 +1,24 @@ ## 文字识别 + +- [一、数据准备](#数据准备) + - [数据下载](#数据下载) + - [自定义数据集](#自定义数据集) + - [字典](#字典) + - [支持空格](#支持空格) + +- [二、启动训练](#文本检测模型推理) + - [1. 数据增强](#数据增强) + - [2. 训练](#训练) + - [3. 小语种](#小语种) + +- [三、评估](#评估) + +- [四、预测](#预测) + - [1. 训练引擎预测](#训练引擎预测) + + + ### 数据准备 @@ -13,13 +32,14 @@ PaddleOCR 支持两种数据格式: `lmdb` 用于训练公开数据，调试算 ln -sf /train_data/dataset ``` - + * 数据下载 若您本地没有数据集，可以在官网下载 [icdar2015](http://rrc.cvc.uab.es/?ch=4&com=downloads) 数据，用于快速验证。也可以参考[DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here)，下载 benchmark 所需的lmdb格式数据集。 如果希望复现SRN的论文指标，需要下载离线[增广数据](https://pan.baidu.com/s/1-HSZ-ZVdqBF2HaBZ5pRAKA),提取码: y3ry。增广数据是由MJSynth和SynthText做旋转和扰动得到的。数据下载完成后请解压到 {your_path}/PaddleOCR/train_data/data_lmdb_release/training/ 路径下。 + * 使用自己数据集 若您希望使用自己的数据进行训练，请参考下文组织您的数据。 @@ -78,7 +98,7 @@ python gen_label.py --mode="rec" --input_path="{path/of/origin/label}" --output_ |- word_003.jpg | ... ``` - + - 字典 最后需要提供一个字典（{word_dict_name}.txt），使模型在训练时，可以将所有出现的字符映射为字典的索引。 @@ -119,13 +139,14 @@ word_dict.txt 每行有一个单字，将字符与数字索引映射在一起， 如需自定义dic文件，请在 `configs/rec/rec_icdar15_train.yml` 中添加 `character_dict_path` 字段, 指向您的字典路径。 并将 `character_type` 设置为 `ch`。 + - 添加空格类别 如果希望支持识别"空格"类别, 请将yml文件中的 `use_space_char` 字段设置为 `true`。 **注意：`use_space_char` 仅在 `character_type=ch` 时生效** - + ### 启动训练 PaddleOCR提供了训练脚本、评估脚本和预测脚本，本节将以 CRNN 识别模型为例： @@ -151,7 +172,7 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3 # 训练icdar15英文数据 并将训练日志保存为 tain_rec.log python3 tools/train.py -c configs/rec/rec_icdar15_train.yml 2>&1 | tee train_rec.log ``` - + - 数据增强 PaddleOCR提供了多种数据增强方式，如果您希望在训练时加入扰动，请在配置文件中设置 `distort: true`。 @@ -162,6 +183,7 @@ PaddleOCR提供了多种数据增强方式，如果您希望在训练时加入 *由于OpenCV的兼容性问题，扰动操作暂时只支持Linux* + - 训练 PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_train.yml` 中修改 `eval_batch_step` 设置评估频率，默认每500个iter评估一次。评估过程中默认将最佳acc模型，保存为 `output/rec_CRNN/best_accuracy` 。 @@ -224,17 +246,18 @@ Optimizer: ``` **注意，预测/评估时的配置文件请务必与训练一致。** + - 小语种 PaddleOCR也提供了多语言的， `configs/rec/multi_languages` 路径下的提供了多语言的配置文件，目前PaddleOCR支持的多语言算法有： -| 配置文件 | 算法名称 | backbone | trans | seq | pred | language ｜ -| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | -| rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 英语 ｜ -| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 ｜ -| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 ｜ -| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 日语 ｜ -| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 韩语 ｜ +| 配置文件 | 算法名称 | backbone | trans | seq | pred | language | +| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | +| rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 英语 | +| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 | +| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 | +| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 日语 | +| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 韩语 | 多语言模型训练方式与中文模型一致，训练数据集均为100w的合成数据，少量的字体可以在 [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 上下载，提取码：frgi。 @@ -269,7 +292,7 @@ TrainReader: ... ``` - + ### 评估 评估数据集可以通过 `configs/rec/rec_icdar15_reader.yml` 修改EvalReader中的 `label_file_path` 设置。 @@ -281,8 +304,10 @@ export CUDA_VISIBLE_DEVICES=0 python3 tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy ``` + ### 预测 + * 训练引擎的预测 使用 PaddleOCR 训练好的模型，可以通过以下脚本进行快速预测。 diff --git a/doc/doc_en/inference_en.md b/doc/doc_en/inference_en.md index 66f2e473..868d5793 100644 --- a/doc/doc_en/inference_en.md +++ b/doc/doc_en/inference_en.md @@ -26,8 +26,10 @@ Next, we first introduce how to convert a trained model into an inference model, - [1. LIGHTWEIGHT CHINESE MODEL](#LIGHTWEIGHT_RECOGNITION) - [2. CTC-BASED TEXT RECOGNITION MODEL INFERENCE](#CTC-BASED_RECOGNITION) - [3. ATTENTION-BASED TEXT RECOGNITION MODEL INFERENCE](#ATTENTION-BASED_RECOGNITION) - - [4. TEXT RECOGNITION MODEL INFERENCE USING CUSTOM CHARACTERS DICTIONARY](#USING_CUSTOM_CHARACTERS) - + - [4. SRN-BASED TEXT RECOGNITION MODEL INFERENCE](#SRN-BASED_RECOGNITION) + - [5. TEXT RECOGNITION MODEL INFERENCE USING CUSTOM CHARACTERS DICTIONARY](#USING_CUSTOM_CHARACTERS) + - [6. MULTILINGUAL MODEL INFERENCE](MULTILINGUAL_MODEL_INFERENCE) + - [ANGLE CLASSIFICATION MODEL INFERENCE](#ANGLE_CLASS_MODEL_INFERENCE) - [1. ANGLE CLASSIFICATION MODEL INFERENCE](#ANGLE_CLASS_MODEL_INFERENCE) @@ -299,17 +301,31 @@ self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz" dict_character = list(self.character_str) ``` + +### 4. SRN-BASED TEXT RECOGNITION MODEL INFERENCE + +The recognition model based on SRN requires additional setting of the recognition algorithm parameter --rec_algorithm="SRN". +At the same time, it is necessary to ensure that the predicted shape is consistent with the training, such as: --rec_image_shape="1, 64, 256" + +``` +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" \ + --rec_model_dir="./inference/srn/" \ + --rec_image_shape="1, 64, 256" \ + --rec_char_type="en" \ + --rec_algorithm="SRN" +``` + + -### 4. TEXT RECOGNITION MODEL INFERENCE USING CUSTOM CHARACTERS DICTIONARY +### 5. TEXT RECOGNITION MODEL INFERENCE USING CUSTOM CHARACTERS DICTIONARY If the chars dictionary is modified during training, you need to specify the new dictionary path by setting the parameter `rec_char_dict_path` when using your inference model to predict. ``` python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 32, 100" --rec_char_type="en" --rec_char_dict_path="your text dict path" ``` - - -### 5. Multilingual Model Reasoning + +### 6. MULTILINGAUL 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/` path, such as Korean recognition: diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md index 142bfdb8..61d829b8 100644 --- a/doc/doc_en/recognition_en.md +++ b/doc/doc_en/recognition_en.md @@ -1,5 +1,22 @@ ## TEXT RECOGNITION +- [DATA PREPARATION](#DATA_PREPARATION) + - [Dataset Download](#Dataset_download) + - [Costom Dataset](#Costom_Dataset) + - [Dictionary](#Dictionary) + - [Add Space Category](#Add_space_category) + +- [TRAINING](#TRAINING) + - [Data Augmentation](#Data_Augmentation) + - [Training](#Training) + - [Multi-language](#Multi_language) + +- [EVALUATION](#EVALUATION) + +- [PREDICTION](#PREDICTION) + - [Training engine prediction](#Training_engine_prediction) + + ### DATA PREPARATION @@ -13,13 +30,14 @@ The default storage path for training data is `PaddleOCR/train_data`, if you alr ln -sf /train_data/dataset ``` - + * Dataset download If you do not have a dataset locally, you can download it on the official website [icdar2015](http://rrc.cvc.uab.es/?ch=4&com=downloads). Also refer to [DTRB](https://github.com/clovaai/deep-text-recognition-benchmark#download-lmdb-dataset-for-traininig-and-evaluation-from-here)，download the lmdb format dataset required for benchmark If you want to reproduce the paper indicators of SRN, you need to download offline [augmented data](https://pan.baidu.com/s/1-HSZ-ZVdqBF2HaBZ5pRAKA), extraction code: y3ry. The augmented data is obtained by rotation and perturbation of mjsynth and synthtext. Please unzip the data to {your_path}/PaddleOCR/train_data/data_lmdb_Release/training/path. + * Use your own dataset: If you want to use your own data for training, please refer to the following to organize your data. @@ -72,7 +90,7 @@ Similar to the training set, the test set also needs to be provided a folder con |- word_003.jpg | ... ``` - + - Dictionary Finally, a dictionary ({word_dict_name}.txt) needs to be provided so that when the model is trained, all the characters that appear can be mapped to the dictionary index. @@ -114,12 +132,14 @@ To customize the dict file, please modify the `character_dict_path` field in `co If you need to customize dic file, please add character_dict_path field in configs/rec/rec_icdar15_train.yml to point to your dictionary path. And set character_type to ch. + - Add space category If you want to support the recognition of the `space` category, please set the `use_space_char` field in the yml file to `true`. **Note: use_space_char only takes effect when character_type=ch** + ### TRAINING PaddleOCR provides training scripts, evaluation scripts, and prediction scripts. In this section, the CRNN recognition model will be used as an example: @@ -143,7 +163,7 @@ export CUDA_VISIBLE_DEVICES=0,1,2,3 # Training icdar15 English data and saving the log as train_rec.log python3 tools/train.py -c configs/rec/rec_icdar15_train.yml 2>&1 | tee train_rec.log ``` - + - Data Augmentation PaddleOCR provides a variety of data augmentation methods. If you want to add disturbance during training, please set `distort: true` in the configuration file. @@ -152,7 +172,7 @@ The default perturbation methods are: cvtColor, blur, jitter, Gasuss noise, rand Each disturbance method is selected with a 50% probability during the training process. For specific code implementation, please refer to: [img_tools.py](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/ppocr/data/rec/img_tools.py) - + - Training PaddleOCR supports alternating training and evaluation. You can modify `eval_batch_step` in `configs/rec/rec_icdar15_train.yml` to set the evaluation frequency. By default, it is evaluated every 500 iter and the best acc model is saved under `output/rec_CRNN/best_accuracy` during the evaluation process. @@ -215,7 +235,8 @@ Optimizer: ``` **Note that the configuration file for prediction/evaluation must be consistent with the training.** --Minor language + +- Multi-language PaddleOCR also provides multi-language. The configuration file in `configs/rec/multi_languages` provides multi-language configuration files. Currently, the multi-language algorithms supported by PaddleOCR are: @@ -250,7 +271,7 @@ Global: ... ``` - + ### EVALUATION The evaluation data set can be modified via `configs/rec/rec_icdar15_reader.yml` setting of `label_file_path` in EvalReader. @@ -261,8 +282,10 @@ export CUDA_VISIBLE_DEVICES=0 python3 tools/eval.py -c configs/rec/rec_icdar15_reader.yml -o Global.checkpoints={path/to/weights}/best_accuracy ``` + ### PREDICTION + * Training engine prediction Using the model trained by paddleocr, you can quickly get prediction through the following script.