Merge branch 'dygraph' into sdmgr

PPOCRLabel/README_ch.md

@@ -71,6 +71,8 @@ pip3 install opencv-contrib-python-headless==4.2.0.32 # 如果下载过慢请添
 PPOCRLabel --lang ch # 启动
 ```
 
+> 如果上述安装出现问题，可以参考3.6节 错误提示
+
 #### 1.2.2 本地构建whl包并安装
 
 ```bash

PPOCRLabel/libs/canvas.py

@@ -704,8 +704,9 @@ def wheelEvent(self, ev):
 
     def keyPressEvent(self, ev):
         key = ev.key()
-        shapesBackup = []
         shapesBackup = copy.deepcopy(self.shapes)
+        if len(shapesBackup) == 0:
+            return
         self.shapesBackups.pop()
         self.shapesBackups.append(shapesBackup)
         if key == Qt.Key_Escape and self.current:

benchmark/run_benchmark_det.sh

@@ -17,7 +17,7 @@ function _set_params(){
     skip_steps=2                 # 解析日志，有些模型前几个step耗时长，需要跳过                                    (必填)
     keyword="ips:"               # 解析日志，筛选出数据所在行的关键字                                             (必填)
     index="1"
-    model_name=${model_item}_${run_mode}_bs${batch_size}_${fp_item}        # model_item 用于yml文件名匹配，model_name 用于数据入库前端展示
+    model_name=${model_item}_bs${batch_size}_${fp_item}        # model_item 用于yml文件名匹配，model_name 用于数据入库前端展示
 #   以下不用修改   
     device=${CUDA_VISIBLE_DEVICES//,/ }
     arr=(${device})

benchmark/run_det.sh

@@ -2,6 +2,7 @@
 # 提供可稳定复现性能的脚本，默认在标准docker环境内py37执行： paddlepaddle/paddle:latest-gpu-cuda10.1-cudnn7  paddle=2.1.2  py=37
 # 执行目录: ./PaddleOCR
 # 1 安装该模型需要的依赖 (如需开启优化策略请注明)
+log_path=${LOG_PATH_INDEX_DIR:-$(pwd)}
 python -m pip install -r requirements.txt
 # 2 拷贝该模型需要数据、预训练模型
 wget -P ./train_data/  https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar && cd train_data  && tar xf icdar2015.tar && cd ../
@@ -12,18 +13,22 @@ wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dyg
 
 model_mode_list=(det_res18_db_v2.0 det_r50_vd_east det_r50_vd_pse)
 fp_item_list=(fp32)
-bs_list=(8 16)
 for model_mode in ${model_mode_list[@]}; do
       for fp_item in ${fp_item_list[@]}; do
+          if [ ${model_mode} == "det_r50_vd_east" ]; then
+              bs_list=(16)
+          else
+              bs_list=(8 16)
+          fi
           for bs_item in ${bs_list[@]}; do
             echo "index is speed, 1gpus, begin, ${model_name}"
             run_mode=sp
-            log_name=ocr_${model_mode}_${run_mode}_bs${bs_item}_${fp_item}
+            log_name=ocr_${model_mode}_bs${bs_item}_${fp_item}_${run_mode}
             CUDA_VISIBLE_DEVICES=0 bash benchmark/run_benchmark_det.sh ${run_mode} ${bs_item} ${fp_item} 1 ${model_mode} | tee ${log_path}/${log_name}_speed_1gpus 2>&1    #  (5min)
             sleep 60
             echo "index is speed, 8gpus, run_mode is multi_process, begin, ${model_name}"
             run_mode=mp
-            log_name=ocr_${model_mode}_${run_mode}_bs${bs_item}_${fp_item}
+            log_name=ocr_${model_mode}_bs${bs_item}_${fp_item}_${run_mode}
             CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash benchmark/run_benchmark_det.sh ${run_mode} ${bs_item} ${fp_item} 2 ${model_mode} | tee ${log_path}/${log_name}_speed_8gpus8p 2>&1
             sleep 60
             done

configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml

@@ -18,6 +18,7 @@ Global:
 Architecture:
   name: DistillationModel
   algorithm: Distillation
+  model_type: det
   Models:
     Teacher:
       freeze_params: true

deploy/pdserving/README.md

@@ -45,63 +45,67 @@ PaddleOCR operating environment and Paddle Serving operating environment are nee
     ```
 
 3. Install the client to send requests to the service
-    In [download link](https://github.com/PaddlePaddle/Serving/blob/develop/doc/LATEST_PACKAGES.md) find the client installation package corresponding to the python version.
-    The python3.7 version is recommended here:
 
-    ```
-    wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp37-none-any.whl
-    pip3 install paddle_serving_client-0.0.0-cp37-none-any.whl
-    ```
-
-4. Install serving-app
-    ```
-    pip3 install paddle-serving-app==0.6.1
-    ```
+```bash
+# 安装serving，用于启动服务
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
+pip3 install paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
+# 如果是cuda10.1环境，可以使用下面的命令安装paddle-serving-server
+# wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
+# pip3 install paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
+
+# 安装client，用于向服务发送请求
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.7.0-cp37-none-any.whl
+pip3 install paddle_serving_client-0.7.0-cp37-none-any.whl
+
+# 安装serving-app
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.7.0-py3-none-any.whl
+pip3 install paddle_serving_app-0.7.0-py3-none-any.whl
+```
 
-   **note:** If you want to install the latest version of PaddleServing, refer to [link](https://github.com/PaddlePaddle/Serving/blob/develop/doc/LATEST_PACKAGES.md).
+   **note:** If you want to install the latest version of PaddleServing, refer to [link](https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Latest_Packages_CN.md).
 
 
 <a name="model-conversion"></a>
 ## Model conversion
 When using PaddleServing for service deployment, you need to convert the saved inference model into a serving model that is easy to deploy.
 
-Firstly, download the [inference model](https://github.com/PaddlePaddle/PaddleOCR#pp-ocr-20-series-model-listupdate-on-dec-15) of PPOCR
+Firstly, download the [inference model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/README_ch.md#pp-ocr%E7%B3%BB%E5%88%97%E6%A8%A1%E5%9E%8B%E5%88%97%E8%A1%A8%E6%9B%B4%E6%96%B0%E4%B8%AD) of PPOCR
 ```
 # Download and unzip the OCR text detection model
-wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar -O ch_PP-OCRv2_det_infer.tar && tar -xf ch_PP-OCRv2_det_infer.tar
 # Download and unzip the OCR text recognition model
-wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
-
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar -O ch_PP-OCRv2_rec_infer.tar &&  tar -xf ch_PP-OCRv2_rec_infer.tar
 ```
 Then, you can use installed paddle_serving_client tool to convert inference model to mobile model.
 ```
 #  Detection model conversion
-python3 -m paddle_serving_client.convert --dirname ./ch_ppocr_mobile_v2.0_det_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_det_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_det_mobile_2.0_serving/ \
-                                         --serving_client ./ppocr_det_mobile_2.0_client/
+                                         --serving_server ./ppocrv2_det_serving/ \
+                                         --serving_client ./ppocrv2_det_client/
 
 #  Recognition model conversion
-python3 -m paddle_serving_client.convert --dirname ./ch_ppocr_mobile_v2.0_rec_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_rec_mobile_2.0_serving/  \
-                                         --serving_client ./ppocr_rec_mobile_2.0_client/
+                                         --serving_server ./ppocrv2_rec_serving/  \
+                                         --serving_client ./ppocrv2_rec_client/
 
 ```
 
 After the detection model is converted, there will be additional folders of `ppocr_det_mobile_2.0_serving` and `ppocr_det_mobile_2.0_client` in the current folder, with the following format:
 ```
-|- ppocr_det_mobile_2.0_serving/
-   |- __model__
-   |- __params__
-   |- serving_server_conf.prototxt
-   |- serving_server_conf.stream.prototxt
-
-|- ppocr_det_mobile_2.0_client
-   |- serving_client_conf.prototxt
-   |- serving_client_conf.stream.prototxt
+|- ppocrv2_det_serving/
+  |- __model__  
+  |- __params__
+  |- serving_server_conf.prototxt  
+  |- serving_server_conf.stream.prototxt
+
+|- ppocrv2_det_client
+  |- serving_client_conf.prototxt  
+  |- serving_client_conf.stream.prototxt
 
 ```
 The recognition model is the same.

deploy/pdserving/README_CN.md

@@ -34,70 +34,66 @@ PaddleOCR提供2种服务部署方式：
 
 - 准备PaddleServing的运行环境，步骤如下
 
-1. 安装serving，用于启动服务
-    ```
-    pip3 install paddle-serving-server==0.6.1 # for CPU
-    pip3 install paddle-serving-server-gpu==0.6.1 # for GPU
-    # 其他GPU环境需要确认环境再选择执行如下命令
-    pip3 install paddle-serving-server-gpu==0.6.1.post101 # GPU with CUDA10.1 + TensorRT6
-    pip3 install paddle-serving-server-gpu==0.6.1.post11 # GPU with CUDA11 + TensorRT7
-    ```
-
-2. 安装client，用于向服务发送请求
-    在[下载链接](https://github.com/PaddlePaddle/Serving/blob/develop/doc/LATEST_PACKAGES.md)中找到对应python版本的client安装包，这里推荐python3.7版本：
-
-    ```
-    wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.0.0-cp37-none-any.whl
-    pip3 install paddle_serving_client-0.0.0-cp37-none-any.whl
-    ```
-
-3. 安装serving-app
-    ```
-    pip3 install paddle-serving-app==0.6.1
-    ```
+```bash
+# 安装serving，用于启动服务
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
+pip3 install paddle_serving_server_gpu-0.7.0.post102-py3-none-any.whl
+# 如果是cuda10.1环境，可以使用下面的命令安装paddle-serving-server
+# wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
+# pip3 install paddle_serving_server_gpu-0.7.0.post101-py3-none-any.whl
+
+# 安装client，用于向服务发送请求
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_client-0.7.0-cp37-none-any.whl
+pip3 install paddle_serving_client-0.7.0-cp37-none-any.whl
+
+# 安装serving-app
+wget https://paddle-serving.bj.bcebos.com/test-dev/whl/paddle_serving_app-0.7.0-py3-none-any.whl
+pip3 install paddle_serving_app-0.7.0-py3-none-any.whl
+```
 
-    **Note:** 如果要安装最新版本的PaddleServing参考[链接](https://github.com/PaddlePaddle/Serving/blob/develop/doc/LATEST_PACKAGES.md)。
+**Note:** 如果要安装最新版本的PaddleServing参考[链接](https://github.com/PaddlePaddle/Serving/blob/v0.7.0/doc/Latest_Packages_CN.md)。
 
 <a name="模型转换"></a>
 ## 模型转换
 
 使用PaddleServing做服务化部署时，需要将保存的inference模型转换为serving易于部署的模型。
 
-首先，下载PPOCR的[inference模型](https://github.com/PaddlePaddle/PaddleOCR#pp-ocr-20-series-model-listupdate-on-dec-15)
-```
+首先，下载PPOCR的[inference模型](https://github.com/PaddlePaddle/PaddleOCR#pp-ocr-series-model-listupdate-on-september-8th)
+
+```bash
 # 下载并解压 OCR 文本检测模型
-wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_det_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar -O ch_PP-OCRv2_det_infer.tar && tar -xf ch_PP-OCRv2_det_infer.tar
 # 下载并解压 OCR 文本识别模型
-wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar -O ch_PP-OCRv2_rec_infer.tar &&  tar -xf ch_PP-OCRv2_rec_infer.tar
 ```
 
 接下来，用安装的paddle_serving_client把下载的inference模型转换成易于server部署的模型格式。
 
-```
+```bash
 # 转换检测模型
-python3 -m paddle_serving_client.convert --dirname ./ch_ppocr_mobile_v2.0_det_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_det_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_det_mobile_2.0_serving/ \
-                                         --serving_client ./ppocr_det_mobile_2.0_client/
+                                         --serving_server ./ppocrv2_det_serving/ \
+                                         --serving_client ./ppocrv2_det_client/
 
 # 转换识别模型
-python3 -m paddle_serving_client.convert --dirname ./ch_ppocr_mobile_v2.0_rec_infer/ \
+python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \
                                          --model_filename inference.pdmodel          \
                                          --params_filename inference.pdiparams       \
-                                         --serving_server ./ppocr_rec_mobile_2.0_serving/  \
-                                         --serving_client ./ppocr_rec_mobile_2.0_client/
+                                         --serving_server ./ppocrv2_rec_serving/  \
+                                         --serving_client ./ppocrv2_rec_client/
 ```
 
-检测模型转换完成后，会在当前文件夹多出`ppocr_det_mobile_2.0_serving` 和`ppocr_det_mobile_2.0_client`的文件夹，具备如下格式：
+检测模型转换完成后，会在当前文件夹多出`ppocrv2_det_serving` 和`ppocrv2_det_client`的文件夹，具备如下格式：
 ```
-|- ppocr_det_mobile_2.0_serving/
+|- ppocrv2_det_serving/
   |- __model__  
   |- __params__
   |- serving_server_conf.prototxt  
   |- serving_server_conf.stream.prototxt
 
-|- ppocr_det_mobile_2.0_client
+|- ppocrv2_det_client
   |- serving_client_conf.prototxt  
   |- serving_client_conf.stream.prototxt
 

deploy/pdserving/config.yml

@@ -34,7 +34,7 @@ op:
             client_type: local_predictor
 
             #det模型路径
-            model_config: ./ppocr_det_mobile_2.0_serving
+            model_config: ./ppocrv2_det_serving
 
             #Fetch结果列表，以client_config中fetch_var的alias_name为准
             fetch_list: ["save_infer_model/scale_0.tmp_1"]
@@ -60,7 +60,7 @@ op:
             client_type: local_predictor
 
             #rec模型路径
-            model_config: ./ppocr_rec_mobile_2.0_serving
+            model_config: ./ppocrv2_rec_serving
 
             #Fetch结果列表，以client_config中fetch_var的alias_name为准
             fetch_list: ["save_infer_model/scale_0.tmp_1"]  

deploy/pdserving/web_service.py

@@ -54,7 +54,7 @@ def preprocess(self, input_dicts, data_id, log_id):
         _, self.new_h, self.new_w = det_img.shape
         return {"x": det_img[np.newaxis, :].copy()}, False, None, ""
 
-    def postprocess(self, input_dicts, fetch_dict, log_id):
+    def postprocess(self, input_dicts, fetch_dict, data_id, log_id):
         det_out = fetch_dict["save_infer_model/scale_0.tmp_1"]
         ratio_list = [
             float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w
@@ -129,7 +129,7 @@ def preprocess(self, input_dicts, data_id, log_id):
 
         return feed_list, False, None, ""
 
-    def postprocess(self, input_dicts, fetch_data, log_id):
+    def postprocess(self, input_dicts, fetch_data, data_id, log_id):
         res_list = []
         if isinstance(fetch_data, dict):
             if len(fetch_data) > 0:

deploy/pdserving/web_service_det.py

@@ -54,7 +54,7 @@ def preprocess(self, input_dicts, data_id, log_id):
         _, self.new_h, self.new_w = det_img.shape
         return {"x": det_img[np.newaxis, :].copy()}, False, None, ""
 
-    def postprocess(self, input_dicts, fetch_dict, log_id):
+    def postprocess(self, input_dicts, fetch_dict, data_id, log_id):
         det_out = fetch_dict["save_infer_model/scale_0.tmp_1"]
         ratio_list = [
             float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w

deploy/pdserving/web_service_rec.py

@@ -56,7 +56,7 @@ def preprocess(self, input_dicts, data_id, log_id):
         feed_list.append(feed)
         return feed_list, False, None, ""
 
-    def postprocess(self, input_dicts, fetch_data, log_id):
+    def postprocess(self, input_dicts, fetch_data, data_id, log_id):
         res_list = []
         if isinstance(fetch_data, dict):
             if len(fetch_data) > 0:

deploy/slim/prune/export_prune_model.py

@@ -52,21 +52,31 @@ def main(config, device, logger, vdl_writer):
         config['Architecture']["Head"]['out_channels'] = char_num
     model = build_model(config['Architecture'])
 
-    flops = paddle.flops(model, [1, 3, 640, 640])
-    logger.info(f"FLOPs before pruning: {flops}")
+    if config['Architecture']['model_type'] == 'det':
+        input_shape = [1, 3, 640, 640]
+    elif config['Architecture']['model_type'] == 'rec':
+        input_shape = [1, 3, 32, 320]
+
+    flops = paddle.flops(model, input_shape)
+    logger.info("FLOPs before pruning: {}".format(flops))
 
     from paddleslim.dygraph import FPGMFilterPruner
     model.train()
-    pruner = FPGMFilterPruner(model, [1, 3, 640, 640])
+    pruner = FPGMFilterPruner(model, input_shape)
 
     # build metric
     eval_class = build_metric(config['Metric'])
 
     def eval_fn():
         metric = program.eval(model, valid_dataloader, post_process_class,
                               eval_class)
-        logger.info(f"metric['hmean']: {metric['hmean']}")
-        return metric['hmean']
+        if config['Architecture']['model_type'] == 'det':
+            main_indicator = 'hmean'
+        else:
+            main_indicator = 'acc'
+        logger.info("metric[{}]: {}".format(main_indicator, metric[
+            main_indicator]))
+        return metric[main_indicator]
 
     params_sensitive = pruner.sensitive(
         eval_func=eval_fn,
@@ -81,18 +91,22 @@ def eval_fn():
     # calculate pruned params's ratio
     params_sensitive = pruner._get_ratios_by_loss(params_sensitive, loss=0.02)
     for key in params_sensitive.keys():
-        logger.info(f"{key}, {params_sensitive[key]}")
+        logger.info("{}, {}".format(key, params_sensitive[key]))
 
     plan = pruner.prune_vars(params_sensitive, [0])
 
-    flops = paddle.flops(model, [1, 3, 640, 640])
-    logger.info(f"FLOPs after pruning: {flops}")
+    flops = paddle.flops(model, input_shape)
+    logger.info("FLOPs after pruning: {}".format(flops))
 
     # load pretrain model
     load_model(config, model)
     metric = program.eval(model, valid_dataloader, post_process_class,
                           eval_class)
-    logger.info(f"metric['hmean']: {metric['hmean']}")
+    if config['Architecture']['model_type'] == 'det':
+        main_indicator = 'hmean'
+    else:
+        main_indicator = 'acc'
+    logger.info("metric['']: {}".format(main_indicator, metric[main_indicator]))
 
     # start export model
     from paddle.jit import to_static