Merge pull request #2357 from caopulan/fix_srn_post

fix srn_postprocess

deploy/cpp_infer/CMakeLists.txt

@@ -40,7 +40,6 @@ endif()
 if (WIN32)
   include_directories("${PADDLE_LIB}/paddle/fluid/inference")
   include_directories("${PADDLE_LIB}/paddle/include")
-  link_directories("${PADDLE_LIB}/paddle/lib")
   link_directories("${PADDLE_LIB}/paddle/fluid/inference")
   find_package(OpenCV REQUIRED PATHS ${OPENCV_DIR}/build/ NO_DEFAULT_PATH)
 
@@ -137,22 +136,22 @@ else()
   set(MATH_LIB ${PADDLE_LIB}/third_party/install/openblas/lib/libopenblas${CMAKE_STATIC_LIBRARY_SUFFIX})
 endif()
 
-# Note: libpaddle_inference_api.so/a must put before libpaddle_inference.so/a
+# Note: libpaddle_inference_api.so/a must put before libpaddle_fluid.so/a
 if(WITH_STATIC_LIB)
   if(WIN32)
     set(DEPS
-        ${PADDLE_LIB}/paddle/lib/paddle_inference${CMAKE_STATIC_LIBRARY_SUFFIX})
+        ${PADDLE_LIB}/paddle/lib/paddle_fluid${CMAKE_STATIC_LIBRARY_SUFFIX})
   else()
     set(DEPS
-        ${PADDLE_LIB}/paddle/lib/libpaddle_inference${CMAKE_STATIC_LIBRARY_SUFFIX})
+        ${PADDLE_LIB}/paddle/lib/libpaddle_fluid${CMAKE_STATIC_LIBRARY_SUFFIX})
   endif()
 else()
   if(WIN32)
     set(DEPS
-        ${PADDLE_LIB}/paddle/lib/paddle_inference${CMAKE_SHARED_LIBRARY_SUFFIX})
+        ${PADDLE_LIB}/paddle/lib/paddle_fluid${CMAKE_SHARED_LIBRARY_SUFFIX})
   else()
     set(DEPS
-        ${PADDLE_LIB}/paddle/lib/libpaddle_inference${CMAKE_SHARED_LIBRARY_SUFFIX})
+        ${PADDLE_LIB}/paddle/lib/libpaddle_fluid${CMAKE_SHARED_LIBRARY_SUFFIX})
   endif()
 endif(WITH_STATIC_LIB)
 

deploy/cpp_infer/readme.md

@@ -119,8 +119,7 @@ build/paddle_inference_install_dir/
 
 #### 1.2.2 直接下载安装
 
-* [Paddle预测库官网](https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/inference_deployment/inference/build_and_install_lib_cn.html)上提供了不同cuda版本的Linux预测库，可以在官网查看并选择合适的预测库版本（*建议选择paddle版本>=2.0.1版本的预测库* ）。
-
+* [Paddle预测库官网](https://www.paddlepaddle.org.cn/documentation/docs/zh/advanced_guide/inference_deployment/inference/build_and_install_lib_cn.html)上提供了不同cuda版本的Linux预测库，可以在官网查看并选择合适的预测库版本。
 
 * 下载之后使用下面的方法解压。
 

deploy/cpp_infer/readme_en.md

@@ -78,7 +78,7 @@ opencv3/
 
 
 #### 1.2.1 Compile from the source code
-* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle github repository and compile the inference library from the source code. It is recommended to download the inference library with paddle version greater than or equal to 2.0.1.
+* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle github repository and compile the inference library from the source code.
 * You can refer to [Paddle inference library] (https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html) to get the Paddle source code from github, and then compile To generate the latest inference library. The method of using git to access the code is as follows.
 
 

deploy/cpp_infer/tools/config.txt

@@ -3,7 +3,7 @@ use_gpu 0
 gpu_id  0
 gpu_mem  4000
 cpu_math_library_num_threads  10
-use_mkldnn 1
+use_mkldnn 0
 
 # det config
 max_side_len  960

doc/doc_ch/detection.md

@@ -108,9 +108,9 @@ PaddleOCR计算三个OCR检测相关的指标，分别是：Precision、Recall
 运行如下代码，根据配置文件`det_db_mv3.yml`中`save_res_path`指定的测试集检测结果文件，计算评估指标。
 
 评估时设置后处理参数`box_thresh=0.5`，`unclip_ratio=1.5`，使用不同数据集、不同模型训练，可调整这两个参数进行优化
-训练中模型参数默认保存在`Global.save_model_dir`目录下。在评估指标时，需要设置`Global.checkpoints`指向保存的参数文件。
+训练中模型参数默认保存在`Global.save_model_dir`目录下。在评估指标时，需要设置`Global.pretrained_model`指向保存的参数文件。
 ```shell
-python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{path/to/weights}/best_accuracy" PostProcess.box_thresh=0.5 PostProcess.unclip_ratio=1.5
+python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.pretrained_model="{path/to/weights}/best_accuracy" PostProcess.box_thresh=0.5 PostProcess.unclip_ratio=1.5
 ```
 
 

doc/doc_ch/recognition.md

@@ -420,8 +420,8 @@ Eval:
 评估数据集可以通过 `configs/rec/rec_icdar15_train.yml`  修改Eval中的 `label_file_path` 设置。
 
 ```
-# GPU 评估， Global.checkpoints 为待测权重
-python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
+# GPU 评估， Global.pretrained_model 为待测权重
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
 ```
 
 <a name="预测"></a>
@@ -432,7 +432,7 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec
 
 使用 PaddleOCR 训练好的模型，可以通过以下脚本进行快速预测。
 
-默认预测图片存储在 `infer_img` 里，通过 `-o Global.checkpoints` 指定权重：
+默认预测图片存储在 `infer_img` 里，通过 `-o Global.pretrained_model` 指定权重：
 
 ```
 # 预测英文结果

doc/doc_en/detection_en.md

@@ -101,9 +101,9 @@ Run the following code to calculate the evaluation indicators. The result will b
 
 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.
+The model parameters during training are saved in the `Global.save_model_dir` directory by default. When evaluating indicators, you need to set `Global.pretrained_model` to point to the saved parameter file.
 ```shell
-python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{path/to/weights}/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
+python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.pretrained_model="{path/to/weights}/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
 ```
 
 

doc/doc_en/recognition_en.md

@@ -425,8 +425,8 @@ Eval:
 The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/rec_icdar15_train.yml` file.
 
 ```
-# GPU evaluation, Global.checkpoints is the weight to be tested
-python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
+# GPU evaluation, Global.pretrained_model is the weight to be tested
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
 ```
 
 <a name="PREDICTION"></a>
@@ -437,7 +437,7 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec
 
 Using the model trained by paddleocr, you can quickly get prediction through the following script.
 
-The default prediction picture is stored in `infer_img`, and the weight is specified via `-o Global.checkpoints`:
+The default prediction picture is stored in `infer_img`, and the weight is specified via `-o Global.pretrained_model`:
 
 ```
 # Predict English results

ppocr/postprocess/rec_postprocess.py

@@ -216,6 +216,7 @@ class SRNLabelDecode(BaseRecLabelDecode):
                  character_type='en',
                  use_space_char=False,
                  **kwargs):
+        self.max_text_length = kwargs['max_text_length']
         super(SRNLabelDecode, self).__init__(character_dict_path,
                                              character_type, use_space_char)
 
@@ -229,9 +230,9 @@ class SRNLabelDecode(BaseRecLabelDecode):
         preds_idx = np.argmax(pred, axis=1)
         preds_prob = np.max(pred, axis=1)
 
-        preds_idx = np.reshape(preds_idx, [-1, 25])
+        preds_idx = np.reshape(preds_idx, [-1, self.max_text_length])
 
-        preds_prob = np.reshape(preds_prob, [-1, 25])
+        preds_prob = np.reshape(preds_prob, [-1, self.max_text_length])
 
         text = self.decode(preds_idx, preds_prob)