From 92b60117f0d52fa58afb6f71701d023a202c14f4 Mon Sep 17 00:00:00 2001
From: LDOUBLEV <liuvv0203@outlook.com>
Date: Wed, 17 Jun 2020 13:02:52 +0800
Subject: [PATCH] optimize doc and error message

---
 README.md                   |  1 +
 README_en.md                |  1 +
 doc/doc_ch/detection.md     | 13 +++++++++++--
 doc/doc_ch/inference.md     |  7 +++++++
 doc/doc_en/detection_en.md  | 11 +++++++++++
 doc/doc_en/inference_en.md  |  7 +++++++
 ppocr/data/rec/img_tools.py |  8 +++++++-
 7 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 5eb9ed8f..099bb284 100644
--- a/README.md
+++ b/README.md
@@ -250,3 +250,4 @@ PaddleOCR文本识别算法的训练和使用请参考文档教程中[文本识
 我们非常欢迎你为PaddleOCR贡献代码，也十分感谢你的反馈。
 
 - 非常感谢 [Khanh Tran](https://github.com/xxxpsyduck) 贡献了英文文档。
+- 非常感谢 [zhangxin](https://github.com/ZhangXinNan) 贡献新的可视化方式、添加.gitgnore、处理手动设置PYTHONPATH环境变量的问题
diff --git a/README_en.md b/README_en.md
index c64b65c4..21902996 100644
--- a/README_en.md
+++ b/README_en.md
@@ -255,3 +255,4 @@ This project is released under <a href="https://github.com/PaddlePaddle/PaddleOC
 We welcome all the contributions to PaddleOCR and appreciate for your feedback very much.
 
 - Many thanks to [Khanh Tran](https://github.com/xxxpsyduck) for contributing the English documentation.
+- Many thanks to [zhangxin](https://github.com/ZhangXinNan) for contributing the new visualize function、add .gitgnore and discard set PYTHONPATH manually.
diff --git a/doc/doc_ch/detection.md b/doc/doc_ch/detection.md
index fbff7075..2938ab2c 100644
--- a/doc/doc_ch/detection.md
+++ b/doc/doc_ch/detection.md
@@ -35,7 +35,7 @@ json.dumps编码前的图像标注信息是包含多个字典的list，字典中
 
 ## 快速启动训练
 
-首先下载pretrain model，PaddleOCR的检测模型目前支持两种backbone，分别是MobileNetV3、ResNet50_vd，
+首先下载模型backbone的retrain model，PaddleOCR的检测模型目前支持两种backbone，分别是MobileNetV3、ResNet50_vd，
 您可以根据需求使用[PaddleClas](https://github.com/PaddlePaddle/PaddleClas/tree/master/ppcls/modeling/architectures)中的模型更换backbone。
 ```
 cd PaddleOCR/
@@ -62,7 +62,7 @@ tar xf ./pretrain_models/MobileNetV3_large_x0_5_pretrained.tar ./pretrain_models
 *如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false*
 
 ```
-python3 tools/train.py -c configs/det/det_mv3_db.yml
+python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/
 ```
 
 上述指令中，通过-c 选择训练使用configs/det/det_db_mv3.yml配置文件。
@@ -73,6 +73,15 @@ python3 tools/train.py -c configs/det/det_mv3_db.yml
 python3 tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001
 ```
 
+**断点训练**
+
+如果训练程序中断，如果希望加载训练中断的模型从而恢复训练，可以通过指定Global.checkpoints指定要加载的模型路径：
+```
+python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=./your/trained/model
+```
+
+**注意**：Global.checkpoints的优先级高于Global.pretrain_weights的优先级，即同时指定两个参数时，优先加载Global.checkpoints指定的模型，如果Global.checkpoints指定的模型路径有误，会加载Global.pretrain_weights指定的模型。
+
 ## 指标评估
 
 PaddleOCR计算三个OCR检测相关的指标，分别是：Precision、Recall、Hmean。
diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md
index 8e1fa9ff..ea4bc756 100644
--- a/doc/doc_ch/inference.md
+++ b/doc/doc_ch/inference.md
@@ -192,6 +192,13 @@ self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
 dict_character = list(self.character_str)
 ```
 
+### 4.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
+
+```
+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"
+```
+
 ## 文本检测、识别串联推理
 
 ### 1.超轻量中文OCR模型推理
diff --git a/doc/doc_en/detection_en.md b/doc/doc_en/detection_en.md
index 619f2c01..7dc1fa20 100644
--- a/doc/doc_en/detection_en.md
+++ b/doc/doc_en/detection_en.md
@@ -69,6 +69,17 @@ You can also use the `-o` parameter to change the training parameters without mo
 python3 tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001
 ```
 
+**load trained model and conntinue training**
+If you expect to load trained model and continue the training again, you can specify the `Global.checkpoints` parameter as the model path to be loaded.
+
+For example:
+```
+python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=./your/trained/model
+```
+
+**Note**:The priority of Global.checkpoints is higher than the priority 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.
+
+
 ## Evaluation Indicator
 
 PaddleOCR calculates three indicators for evaluating performance of OCR detection task: Precision, Recall, and Hmean.
diff --git a/doc/doc_en/inference_en.md b/doc/doc_en/inference_en.md
index 3326bab8..8932eafc 100644
--- a/doc/doc_en/inference_en.md
+++ b/doc/doc_en/inference_en.md
@@ -182,6 +182,13 @@ self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
 dict_character = list(self.character_str)
 ```
 
+### 4.Recognition model inference using custom text dictionary file
+If the text dictionary is replaced during training, you need to specify the text 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"
+```
+
 ## Text detection and recognition inference concatenation
 
 ### 1. Ultra-lightweight Chinese OCR model inference
diff --git a/ppocr/data/rec/img_tools.py b/ppocr/data/rec/img_tools.py
index 57543293..d6e273cb 100755
--- a/ppocr/data/rec/img_tools.py
+++ b/ppocr/data/rec/img_tools.py
@@ -15,6 +15,8 @@
 import math
 import cv2
 import numpy as np
+from ppocr.utils.utility import initial_logger
+logger = initial_logger()
 
 
 def get_bounding_box_rect(pos):
@@ -101,9 +103,13 @@ def process_image(img,
         norm_img = resize_norm_img_chinese(img, image_shape)
     norm_img = norm_img[np.newaxis, :]
     if label is not None:
-        char_num = char_ops.get_char_num()
+        # char_num = char_ops.get_char_num()
         text = char_ops.encode(label)
         if len(text) == 0 or len(text) > max_text_length:
+            logger.info(
+                "Warning in ppocr/data/rec/img_tools.py:line106: Wrong data type."
+                "Excepted string with length between 0 and {}, but "
+                "got '{}' ".format(max_text_length, label))
             return None
         else:
             if loss_type == "ctc":
-- 
GitLab