Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into test_v10

PPOCRLabel/README.md

@@ -207,6 +207,24 @@ For some data that are difficult to recognize, the recognition results will not
     pip install opencv-contrib-python-headless==4.2.0.32
     ```
 
+### Dataset division
+
+- Enter the following command in the terminal to execute the dataset division script:
+    ```
+    cd ./PPOCRLabel # Change the directory to the PPOCRLabel folder
+    python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --labelRootPath ../train_data/label --detRootPath ../train_data/det --recRootPath ../train_data/rec
+    ```
+
+- Parameter Description:
+
+    trainValTestRatio is the division ratio of the number of images in the training set, validation set, and test set, set according to your actual situation, the default is 6:2:2
+    
+    labelRootPath is the storage path of the dataset labeled by PPOCRLabel, the default is ../train_data/label
+    
+    detRootPath is the path where the text detection dataset is divided according to the dataset marked by PPOCRLabel. The default is ../train_data/det
+    
+    recRootPath is the path where the character recognition dataset is divided according to the dataset marked by PPOCRLabel. The default is ../train_data/rec
+
 ### Related
 
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)
\ No newline at end of file

PPOCRLabel/README_ch.md

@@ -193,7 +193,23 @@ PPOCRLabel支持三种导出方式：
     ```
     pip install opencv-contrib-python-headless==4.2.0.32
     ```
+### 数据集划分
+- 在终端中输入以下命令执行数据集划分脚本：
+    ```
+    cd ./PPOCRLabel # 将目录切换到PPOCRLabel文件夹下
+    python gen_ocr_train_val_test.py --trainValTestRatio 6:2:2 --labelRootPath ../train_data/label --detRootPath ../train_data/det --recRootPath ../train_data/rec
+    ```
+- 参数说明：
+
+    trainValTestRatio是训练集、验证集、测试集的图像数量划分比例，根据你的实际情况设定，默认是6:2:2
+
+    labelRootPath是PPOCRLabel标注的数据集存放路径，默认是../train_data/label
+
+    detRootPath是根据PPOCRLabel标注的数据集划分后的文本检测数据集存放的路径，默认是../train_data/det 
 
+    recRootPath是根据PPOCRLabel标注的数据集划分后的字符识别数据集存放的路径，默认是../train_data/rec
+    
+    
 ### 4. 参考资料
 
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)

PPOCRLabel/gen_ocr_train_val_test.py

+# coding:utf8
+import os
+import shutil
+import random
+import argparse
+
+
+# 删除划分的训练集、验证集、测试集文件夹，重新创建一个空的文件夹
+def isCreateOrDeleteFolder(path, flag):
+    flagPath = os.path.join(path, flag)
+
+    if os.path.exists(flagPath):
+        shutil.rmtree(flagPath)
+
+    os.makedirs(flagPath)
+    flagAbsPath = os.path.abspath(flagPath)
+    return flagAbsPath
+
+
+def splitTrainVal(root, dir, absTrainRootPath, absValRootPath, absTestRootPath, trainTxt, valTxt, testTxt, flag):
+    # 按照指定的比例划分训练集、验证集、测试集
+    labelPath = os.path.join(root, dir)
+    labelAbsPath = os.path.abspath(labelPath)
+
+    if flag == "det":
+        labelFilePath = os.path.join(labelAbsPath, args.detLabelFileName)
+    elif flag == "rec":
+        labelFilePath = os.path.join(labelAbsPath, args.recLabelFileName)
+
+    labelFileRead = open(labelFilePath, "r", encoding="UTF-8")
+    labelFileContent = labelFileRead.readlines()
+    random.shuffle(labelFileContent)
+    labelRecordLen = len(labelFileContent)
+
+    for index, labelRecordInfo in enumerate(labelFileContent):
+        imageRelativePath = labelRecordInfo.split('\t')[0]
+        imageLabel = labelRecordInfo.split('\t')[1]
+        imageName = os.path.basename(imageRelativePath)
+
+        if flag == "det":
+            imagePath = os.path.join(labelAbsPath, imageName)
+        elif flag == "rec":
+            imagePath = os.path.join(labelAbsPath, "{}\\{}".format(args.recImageDirName, imageName))
+
+        # 按预设的比例划分训练集、验证集、测试集
+        trainValTestRatio = args.trainValTestRatio.split(":")
+        trainRatio = eval(trainValTestRatio[0]) / 10
+        valRatio = trainRatio + eval(trainValTestRatio[1]) / 10
+        curRatio = index / labelRecordLen
+
+        if curRatio < trainRatio:
+            imageCopyPath = os.path.join(absTrainRootPath, imageName)
+            shutil.copy(imagePath, imageCopyPath)
+            trainTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
+        elif curRatio >= trainRatio and curRatio < valRatio:
+            imageCopyPath = os.path.join(absValRootPath, imageName)
+            shutil.copy(imagePath, imageCopyPath)
+            valTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
+        else:
+            imageCopyPath = os.path.join(absTestRootPath, imageName)
+            shutil.copy(imagePath, imageCopyPath)
+            testTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
+
+
+# 删掉存在的文件
+def removeFile(path):
+    if os.path.exists(path):
+        os.remove(path)
+
+
+def genDetRecTrainVal(args):
+    detAbsTrainRootPath = isCreateOrDeleteFolder(args.detRootPath, "train")
+    detAbsValRootPath = isCreateOrDeleteFolder(args.detRootPath, "val")
+    detAbsTestRootPath = isCreateOrDeleteFolder(args.detRootPath, "test")
+    recAbsTrainRootPath = isCreateOrDeleteFolder(args.recRootPath, "train")
+    recAbsValRootPath = isCreateOrDeleteFolder(args.recRootPath, "val")
+    recAbsTestRootPath = isCreateOrDeleteFolder(args.recRootPath, "test")
+
+    removeFile(os.path.join(args.detRootPath, "train.txt"))
+    removeFile(os.path.join(args.detRootPath, "val.txt"))
+    removeFile(os.path.join(args.detRootPath, "test.txt"))
+    removeFile(os.path.join(args.recRootPath, "train.txt"))
+    removeFile(os.path.join(args.recRootPath, "val.txt"))
+    removeFile(os.path.join(args.recRootPath, "test.txt"))
+
+    detTrainTxt = open(os.path.join(args.detRootPath, "train.txt"), "a", encoding="UTF-8")
+    detValTxt = open(os.path.join(args.detRootPath, "val.txt"), "a", encoding="UTF-8")
+    detTestTxt = open(os.path.join(args.detRootPath, "test.txt"), "a", encoding="UTF-8")
+    recTrainTxt = open(os.path.join(args.recRootPath, "train.txt"), "a", encoding="UTF-8")
+    recValTxt = open(os.path.join(args.recRootPath, "val.txt"), "a", encoding="UTF-8")
+    recTestTxt = open(os.path.join(args.recRootPath, "test.txt"), "a", encoding="UTF-8")
+
+    for root, dirs, files in os.walk(args.labelRootPath):
+        for dir in dirs:
+            splitTrainVal(root, dir, detAbsTrainRootPath, detAbsValRootPath, detAbsTestRootPath, detTrainTxt, detValTxt,
+                          detTestTxt, "det")
+            splitTrainVal(root, dir, recAbsTrainRootPath, recAbsValRootPath, recAbsTestRootPath, recTrainTxt, recValTxt,
+                          recTestTxt, "rec")
+        break
+
+
+if __name__ == "__main__":
+    # 功能描述：分别划分检测和识别的训练集、验证集、测试集
+    # 说明：可以根据自己的路径和需求调整参数，图像数据往往多人合作分批标注，每一批图像数据放在一个文件夹内用PPOCRLabel进行标注，
+    # 如此会有多个标注好的图像文件夹汇总并划分训练集、验证集、测试集的需求
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--trainValTestRatio",
+        type=str,
+        default="6:2:2",
+        help="ratio of trainset:valset:testset")
+    parser.add_argument(
+        "--labelRootPath",
+        type=str,
+        default="../train_data/label",
+        help="path to the dataset marked by ppocrlabel, E.g, dataset folder named 1,2,3..."
+    )
+    parser.add_argument(
+        "--detRootPath",
+        type=str,
+        default="../train_data/det",
+        help="the path where the divided detection dataset is placed")
+    parser.add_argument(
+        "--recRootPath",
+        type=str,
+        default="../train_data/rec",
+        help="the path where the divided recognition dataset is placed"
+    )
+    parser.add_argument(
+        "--detLabelFileName",
+        type=str,
+        default="Label.txt",
+        help="the name of the detection annotation file")
+    parser.add_argument(
+        "--recLabelFileName",
+        type=str,
+        default="rec_gt.txt",
+        help="the name of the recognition annotation file"
+    )
+    parser.add_argument(
+        "--recImageDirName",
+        type=str,
+        default="crop_img",
+        help="the name of the folder where the cropped recognition dataset is located"
+    )
+    args = parser.parse_args()
+    genDetRecTrainVal(args)

deploy/pdserving/ocr_cpp_client.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# pylint: disable=doc-string-missing
+
+from paddle_serving_client import Client
+import sys
+import numpy as np
+import base64
+import os
+import cv2
+from paddle_serving_app.reader import Sequential, URL2Image, ResizeByFactor
+from paddle_serving_app.reader import Div, Normalize, Transpose
+from ocr_reader import OCRReader
+
+client = Client()
+# TODO:load_client need to load more than one client model.
+# this need to figure out some details.
+client.load_client_config(sys.argv[1:])
+client.connect(["127.0.0.1:9293"])
+
+import paddle
+test_img_dir = "test_img/"
+
+ocr_reader = OCRReader(char_dict_path="../../ppocr/utils/ppocr_keys_v1.txt")
+
+
+def cv2_to_base64(image):
+    return base64.b64encode(image).decode(
+        'utf8')  #data.tostring()).decode('utf8')
+
+
+for img_file in os.listdir(test_img_dir):
+    with open(os.path.join(test_img_dir, img_file), 'rb') as file:
+        image_data = file.read()
+    image = cv2_to_base64(image_data)
+    res_list = []
+    #print(image)
+    fetch_map = client.predict(
+        feed={"x": image}, fetch=["save_infer_model/scale_0.tmp_1"], batch=True)
+    print("fetrch map:", fetch_map)
+    one_batch_res = ocr_reader.postprocess(fetch_map, with_score=True)
+    for res in one_batch_res:
+        res_list.append(res[0])
+    res = {"res": str(res_list)}
+    print(res)

deploy/pdserving/pipeline_http_client.py

@@ -18,13 +18,19 @@ import json
 import base64
 import os
 
+import argparse
+parser = argparse.ArgumentParser(description="args for paddleserving")
+parser.add_argument("--image_dir", type=str, default="../../doc/imgs/")
+args = parser.parse_args()
+
 
 def cv2_to_base64(image):
     return base64.b64encode(image).decode('utf8')
 
 
 url = "http://127.0.0.1:9998/ocr/prediction"
-test_img_dir = "../../doc/imgs/"
+test_img_dir = args.image_dir
+
 for idx, img_file in enumerate(os.listdir(test_img_dir)):
     with open(os.path.join(test_img_dir, img_file), 'rb') as file:
         image_data1 = file.read()
@@ -36,5 +42,4 @@ for idx, img_file in enumerate(os.listdir(test_img_dir)):
         r = requests.post(url=url, data=json.dumps(data))
         print(r.json())
 
-test_img_dir = "../../doc/imgs/"
 print("==> total number of test imgs: ", len(os.listdir(test_img_dir)))

deploy/pdserving/pipeline_rpc_client.py

@@ -30,7 +30,12 @@ def cv2_to_base64(image):
     return base64.b64encode(image).decode('utf8')
 
 
-test_img_dir = "imgs/"
+import argparse
+parser = argparse.ArgumentParser(description="args for paddleserving")
+parser.add_argument("--image_dir", type=str, default="../../doc/imgs/")
+args = parser.parse_args()
+test_img_dir = args.image_dir
+
 for img_file in os.listdir(test_img_dir):
     with open(os.path.join(test_img_dir, img_file), 'rb') as file:
         image_data = file.read()

test_tipc/configs/mac_ppocr_det_mobile_params.txt

@@ -80,7 +80,8 @@ op.det.local_service_conf.use_mkldnn:True|False
 op.det.local_service_conf.thread_num:1|6
 op.det.local_service_conf.use_trt:False|True
 op.det.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_http_client.py --image_dir=../../doc/imgs
+pipline:pipeline_http_client.py|pipeline_rpc_client.py
+--image_dir=../../doc/imgs
 ===========================kl_quant_params===========================
 infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer/
 infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o

test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+2onnx: paddle2onnx
+--model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./inference/det_mobile_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
\ No newline at end of file

test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt

+===========================serving_params===========================
+model_name:ocr_det_mobile
+python:python3.7|cpp
+trans_model:-m paddle_serving_client.convert
+--dirname:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--serving_server:./deploy/pdserving/ppocr_det_mobile_2.0_serving/
+--serving_client:./deploy/pdserving/ppocr_det_mobile_2.0_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency=1
+op.det.local_service_conf.devices:null|0
+op.det.local_service_conf.use_mkldnn:True|False
+op.det.local_service_conf.thread_num:1|6
+op.det.local_service_conf.use_trt:False|True
+op.det.local_service_conf.precision:fp32|fp16|int8
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs
\ No newline at end of file

test_tipc/configs/ppocr_det_mobile_params.txt

@@ -80,7 +80,8 @@ op.det.local_service_conf.use_mkldnn:True|False
 op.det.local_service_conf.thread_num:1|6
 op.det.local_service_conf.use_trt:False|True
 op.det.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_http_client.py --image_dir=../../doc/imgs
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs
 ===========================kl_quant_params===========================
 infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer/
 infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o

test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+2onnx: paddle2onnx
+--model_dir:./inference/ch_ppocr_server_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./inference/det_server_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--det_model_dir:
+--image_dir:./inference/det_inference
\ No newline at end of file

test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt

+===========================serving_params===========================
+model_name:ocr_det_server
+python:python3.7|cpp
+trans_model:-m paddle_serving_client.convert
+--dirname:./inference/ch_ppocr_server_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--serving_server:./deploy/pdserving/ppocr_det_server_2.0_serving/
+--serving_client:./deploy/pdserving/ppocr_det_server_2.0_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency=1
+op.det.local_service_conf.devices:null|0
+op.det.local_service_conf.use_mkldnn:True|False
+op.det.local_service_conf.thread_num:1|6
+op.det.local_service_conf.use_trt:False|True
+op.det.local_service_conf.precision:fp32|fp16|int8
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs_words_en
\ No newline at end of file