diff --git a/PPOCRLabel/README.md b/PPOCRLabel/README.md index 7a936543277e2e1d5687681ac78eca96f5f3f400..9375559f3b10baaa52d034badaee40214b7c31ff 100644 --- a/PPOCRLabel/README.md +++ b/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 diff --git a/PPOCRLabel/README_ch.md b/PPOCRLabel/README_ch.md index 17bb95c08267bfac5e2cecde2e1d88c4a7cb1b60..7abf2f5d8b193b895e1993a8e1628d29c371df0a 100644 --- a/PPOCRLabel/README_ch.md +++ b/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) diff --git a/PPOCRLabel/gen_ocr_train_val_test.py b/PPOCRLabel/gen_ocr_train_val_test.py new file mode 100644 index 0000000000000000000000000000000000000000..64cba612ae267835dd47aedc2b0356c9df462038 --- /dev/null +++ b/PPOCRLabel/gen_ocr_train_val_test.py @@ -0,0 +1,147 @@ +# 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) diff --git a/deploy/pdserving/ocr_cpp_client.py b/deploy/pdserving/ocr_cpp_client.py new file mode 100755 index 0000000000000000000000000000000000000000..2baa7565ac78b9551c788c7b36457bce38828eb5 --- /dev/null +++ b/deploy/pdserving/ocr_cpp_client.py @@ -0,0 +1,56 @@ +# 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) diff --git a/deploy/pdserving/pipeline_http_client.py b/deploy/pdserving/pipeline_http_client.py index 0befe2f6144d18e24fb3f72ed1d919fd8cd7d5a4..61d13178220118eaf53c51723a9ef65201373ffb 100644 --- a/deploy/pdserving/pipeline_http_client.py +++ b/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))) diff --git a/deploy/pdserving/pipeline_rpc_client.py b/deploy/pdserving/pipeline_rpc_client.py index 79f898faf37f946cdbf4a87d4d62c8b1f9d5c93b..4dcb1ad5f533729e344809e99951b59fb2908537 100644 --- a/deploy/pdserving/pipeline_rpc_client.py +++ b/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() diff --git a/test_tipc/configs/mac_ppocr_det_mobile_params.txt b/test_tipc/configs/mac_ppocr_det_mobile_params.txt index b0415c9a1f79837866812d1e545ad8fd09fb681d..0200e2954948e5aeb719aa43e8a88d70c2af506d 100644 --- a/test_tipc/configs/mac_ppocr_det_mobile_params.txt +++ b/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 diff --git a/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_jetson.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_mac.txt b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_infer_python_mac.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_lite_java_metal_arm_gpu.txt b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_lite_java_metal_arm_gpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_lite_java_opencl_arm_gpu.txt b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_lite_java_opencl_arm_gpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..2d1a59920af20472b2006e6fd70f60e3ba1844d7 --- /dev/null +++ b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt @@ -0,0 +1,12 @@ +===========================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 diff --git a/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..a19c8ee3355b010b55d1dbf16aa0e21940ba546c --- /dev/null +++ b/test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt @@ -0,0 +1,18 @@ +===========================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 diff --git a/test_tipc/configs/ppocr_det_mobile/train_infer_python.txt b/test_tipc/configs/ppocr_det_mobile/train_infer_python.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile/train_linux_dcu_normal_normal_infer_python_dcu.txt b/test_tipc/configs/ppocr_det_mobile/train_linux_dcu_normal_normal_infer_python_dcu.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile/train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ppocr_det_mobile/train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/test_tipc/configs/ppocr_det_mobile_params.txt b/test_tipc/configs/ppocr_det_mobile_params.txt index d7e9cf95c2e9b4b2e18265e5f8b4a65cd6bdf518..0ccf77d1f91bde4e0ef191d11debb5818dcd49e0 100644 --- a/test_tipc/configs/ppocr_det_mobile_params.txt +++ b/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 diff --git a/test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..919736085bc9032debbae6cd432729995f224fe8 --- /dev/null +++ b/test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt @@ -0,0 +1,12 @@ +===========================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 diff --git a/test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..09b7ab750408a54fa292f1168d8de01bd962ca43 --- /dev/null +++ b/test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt @@ -0,0 +1,18 @@ +===========================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 diff --git a/test_tipc/configs/ppocr_det_server_params.txt b/test_tipc/configs/ppocr_det_server_params.txt index bba4ef44f769ed16671ead55a0eba6ee986aaaaa..f688fffac8824b0608ea6b6cec0683c70feb659e 100644 --- a/test_tipc/configs/ppocr_det_server_params.txt +++ b/test_tipc/configs/ppocr_det_server_params.txt @@ -80,4 +80,5 @@ 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 diff --git a/test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..69bd018623ec323ac979729447e0b2f96643c4c0 --- /dev/null +++ b/test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt @@ -0,0 +1,12 @@ +===========================paddle2onnx_params=========================== +2onnx: paddle2onnx +--model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/ +--model_filename:inference.pdmodel +--params_filename:inference.pdiparams +--save_file:./inference/rec_mobile_onnx/model.onnx +--opset_version:10 +--enable_onnx_checker:True +inference:tools/infer/predict_rec.py +--use_gpu:True|False +--rec_model_dir: +--image_dir:./inference/rec_inference \ No newline at end of file diff --git a/test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..7351e5bd6d5d8ffc5d49b313ad662b1e2fd55bd2 --- /dev/null +++ b/test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt @@ -0,0 +1,18 @@ +===========================serving_params=========================== +model_name:ocr_rec_mobile +python:python3.7|cpp +trans_model:-m paddle_serving_client.convert +--dirname:./inference/ch_ppocr_mobile_v2.0_rec_infer/ +--model_filename:inference.pdmodel +--params_filename:inference.pdiparams +--serving_server:./deploy/pdserving/ppocr_rec_mobile_2.0_serving/ +--serving_client:./deploy/pdserving/ppocr_rec_mobile_2.0_client/ +serving_dir:./deploy/pdserving +web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1 +op.rec.local_service_conf.devices:null|0 +op.rec.local_service_conf.use_mkldnn:True|False +op.rec.local_service_conf.thread_num:1|6 +op.rec.local_service_conf.use_trt:False|True +op.rec.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 diff --git a/test_tipc/configs/ppocr_rec_mobile_params.txt b/test_tipc/configs/ppocr_rec_mobile_params.txt index f3f3a54e14e042693d28559e487852a079f77bdd..3177d19cf6cf7759e13e5597492f3bd7fcea78ff 100644 --- a/test_tipc/configs/ppocr_rec_mobile_params.txt +++ b/test_tipc/configs/ppocr_rec_mobile_params.txt @@ -80,4 +80,5 @@ op.rec.local_service_conf.use_mkldnn:True|False op.rec.local_service_conf.thread_num:1|6 op.rec.local_service_conf.use_trt:False|True op.rec.local_service_conf.precision:fp32|fp16|int8 -pipline:pipeline_http_client.py --image_dir=../../doc/imgs_words_en +pipline:pipeline_http_client.py|pipeline_rpc_client.py +--image_dir=../../doc/imgs_words_en diff --git a/test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..16411aca520bf2e62775871da19eaa6b91602770 --- /dev/null +++ b/test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt @@ -0,0 +1,12 @@ +===========================paddle2onnx_params=========================== +2onnx: paddle2onnx +--model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/ +--model_filename:inference.pdmodel +--params_filename:inference.pdiparams +--save_file:./inference/rec_server_onnx/model.onnx +--opset_version:10 +--enable_onnx_checker:True +inference:tools/infer/predict_rec.py +--use_gpu:True|False +--rec_model_dir: +--image_dir:./inference/rec_inference \ No newline at end of file diff --git a/test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt new file mode 100644 index 0000000000000000000000000000000000000000..24e7a8f3e0364f2a0a14c74a27da7372508cd414 --- /dev/null +++ b/test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt @@ -0,0 +1,18 @@ +===========================serving_params=========================== +model_name:ocr_rec_server +python:python3.7 +trans_model:-m paddle_serving_client.convert +--dirname:./inference/ch_ppocr_server_v2.0_rec_infer/ +--model_filename:inference.pdmodel +--params_filename:inference.pdiparams +--serving_server:./deploy/pdserving/ppocr_rec_server_2.0_serving/ +--serving_client:./deploy/pdserving/ppocr_rec_server_2.0_client/ +serving_dir:./deploy/pdserving +web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1 +op.rec.local_service_conf.devices:null|0 +op.rec.local_service_conf.use_mkldnn:True|False +op.rec.local_service_conf.thread_num:1|6 +op.rec.local_service_conf.use_trt:False|True +op.rec.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 diff --git a/test_tipc/configs/ppocr_rec_server_params.txt b/test_tipc/configs/ppocr_rec_server_params.txt index 77961e8e651e0d770dae64860cc129aa2d50dcf2..3bc1dcce2c7103f2180c19551e8f5379e5524476 100644 --- a/test_tipc/configs/ppocr_rec_server_params.txt +++ b/test_tipc/configs/ppocr_rec_server_params.txt @@ -80,4 +80,5 @@ op.rec.local_service_conf.use_mkldnn:True|False op.rec.local_service_conf.thread_num:1|6 op.rec.local_service_conf.use_trt:False|True op.rec.local_service_conf.precision:fp32|fp16|int8 -pipline:pipeline_http_client.py --image_dir=../../doc/imgs_words_en +pipline:pipeline_http_client.py|pipeline_rpc_client.py +--image_dir=../../doc/imgs_words_en diff --git a/test_tipc/configs/win_ppocr_det_mobile_params.txt b/test_tipc/configs/win_ppocr_det_mobile_params.txt index 5a532ceb307fe87174dc6b46fbde236405f59ff5..0f4faee4b32925b4d0780ece6838c176238c7000 100644 --- a/test_tipc/configs/win_ppocr_det_mobile_params.txt +++ b/test_tipc/configs/win_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 diff --git a/test_tipc/docs/test_paddle2onnx.md b/test_tipc/docs/test_paddle2onnx.md index 5d784c5e93c3a93d00c256004de582dcbf357c45..df2734771e9252a40811c42ead03abbff1b7a1a3 100644 --- a/test_tipc/docs/test_paddle2onnx.md +++ b/test_tipc/docs/test_paddle2onnx.md @@ -18,10 +18,10 @@ PaddleServing预测功能测试的主程序为`test_paddle2onnx.sh`，可以测 先运行`prepare.sh`准备数据和模型，然后运行`test_paddle2onnx.sh`进行测试，最终在```test_tipc/output```目录下生成`paddle2onnx_infer_*.log`后缀的日志文件。 ```shell -bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile_params.txt "paddle2onnx_infer" +bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt "paddle2onnx_infer" # 用法: -bash test_tipc/test_paddle2onnx.sh ./test_tipc/configs/ppocr_det_mobile_params.txt +bash test_tipc/test_paddle2onnx.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt ``` #### 运行结果 diff --git a/test_tipc/docs/test_serving.md b/test_tipc/docs/test_serving.md index f63d6c7107ce92807c53d81a22a582b09178a712..1eded6f5821a5ebd9180cc4d89a1fecac61ad63d 100644 --- a/test_tipc/docs/test_serving.md +++ b/test_tipc/docs/test_serving.md @@ -20,10 +20,10 @@ PaddleServing预测功能测试的主程序为`test_serving.sh`，可以测试 先运行`prepare.sh`准备数据和模型，然后运行`test_serving.sh`进行测试，最终在```test_tipc/output```目录下生成`serving_infer_*.log`后缀的日志文件。 ```shell -bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile_params.txt "serving_infer" +bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt "serving_infer" # 用法: -bash test_tipc/test_serving.sh ./test_tipc/configs/ppocr_det_mobile_params.txt +bash test_tipc/test_serving.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt ``` #### 运行结果 diff --git a/test_tipc/test_lite.sh b/test_tipc/test_lite.sh index 832003ba302fe86995e20029cdb019e72d9ce162..1fd9d3c7186207922c436e7981622c707a56596f 100644 --- a/test_tipc/test_lite.sh +++ b/test_tipc/test_lite.sh @@ -3,7 +3,7 @@ source ./common_func.sh export LD_LIBRARY_PATH=${PWD}:$LD_LIBRARY_PATH FILENAME=$1 -dataline=$(awk 'NR==101, NR==110{print}' $FILENAME) +dataline=$(awk 'NR==102, NR==111{print}' $FILENAME) echo $dataline # parser params IFS=$'\n' diff --git a/test_tipc/test_paddle2onnx.sh b/test_tipc/test_paddle2onnx.sh index 5dc6e65ec81e6b8674877fc686c8b3650ce93a59..cd3cfc6120be631a21944a49ba8ffa6f92b5fc38 100644 --- a/test_tipc/test_paddle2onnx.sh +++ b/test_tipc/test_paddle2onnx.sh @@ -11,7 +11,7 @@ python=$(func_parser_value "${lines[2]}") # parser params -dataline=$(awk 'NR==111, NR==123{print}' $FILENAME) +dataline=$(awk 'NR==1, NR==12{print}' $FILENAME) IFS=$'\n' lines=(${dataline}) diff --git a/test_tipc/test_serving.sh b/test_tipc/test_serving.sh index be7b594c3848c423937c59336ce3bf686f8f228d..c36935a60fecacea672fd932773a8fb0bdcd619b 100644 --- a/test_tipc/test_serving.sh +++ b/test_tipc/test_serving.sh @@ -2,7 +2,7 @@ source test_tipc/common_func.sh FILENAME=$1 -dataline=$(awk 'NR==67, NR==83{print}' $FILENAME) +dataline=$(awk 'NR==1, NR==18{print}' $FILENAME) # parser params IFS=$'\n' @@ -35,6 +35,8 @@ web_use_trt_list=$(func_parser_value "${lines[14]}") web_precision_key=$(func_parser_key "${lines[15]}") web_precision_list=$(func_parser_value "${lines[15]}") pipeline_py=$(func_parser_value "${lines[16]}") +image_dir_key=$(func_parser_key "${lines[17]}") +image_dir_value=$(func_parser_value "${lines[17]}") LOG_PATH="../../test_tipc/output" mkdir -p ./test_tipc/output @@ -51,67 +53,98 @@ function func_serving(){ set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}") set_serving_server=$(func_set_params "${serving_server_key}" "${serving_server_value}") set_serving_client=$(func_set_params "${serving_client_key}" "${serving_client_value}") + set_image_dir=$(func_set_params "${image_dir_key}" "${image_dir_value}") trans_model_cmd="${python} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}" eval $trans_model_cmd cd ${serving_dir_value} echo $PWD unset https_proxy unset http_proxy - for use_gpu in ${web_use_gpu_list[*]}; do - echo ${ues_gpu} - if [ ${use_gpu} = "null" ]; then - for use_mkldnn in ${web_use_mkldnn_list[*]}; do - if [ ${use_mkldnn} = "False" ]; then - continue - fi - for threads in ${web_cpu_threads_list[*]}; do - _save_log_path="${LOG_PATH}/server_infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_1.log" - set_cpu_threads=$(func_set_params "${web_cpu_threads_key}" "${threads}") - web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}=${use_gpu} ${web_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} &" - eval $web_service_cmd - sleep 2s - pipeline_cmd="${python} ${pipeline_py} > ${_save_log_path} 2>&1 " - eval $pipeline_cmd - last_status=${PIPESTATUS[0]} - eval "cat ${_save_log_path}" - status_check $last_status "${pipeline_cmd}" "${status_log}" - PID=$! - kill $PID - sleep 2s - ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 - done - done - elif [ ${use_gpu} = "0" ]; then - for use_trt in ${web_use_trt_list[*]}; do - for precision in ${web_precision_list[*]}; do - if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then - continue - fi - if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then - continue - fi - if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [[ ${_flag_quant} = "True" ]]; then - continue - fi - _save_log_path="${LOG_PATH}/server_infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_1.log" - set_tensorrt=$(func_set_params "${web_use_trt_key}" "${use_trt}") - set_precision=$(func_set_params "${web_precision_key}" "${precision}") - web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} & " + for python in ${python[*]}; do + if [ ${python} = "cpp"]; then + for use_gpu in ${web_use_gpu_list[*]}; do + if [ ${use_gpu} = "null" ]; then + web_service_cpp_cmd="${python} -m paddle_serving_server.serve --model ppocr_det_mobile_2.0_serving/ ppocr_rec_mobile_2.0_serving/ --port 9293" eval $web_service_cmd sleep 2s - pipeline_cmd="${python} ${pipeline_py} > ${_save_log_path} 2>&1" + _save_log_path="${LOG_PATH}/server_infer_cpp_cpu_pipeline_usemkldnn_False_threads_4_batchsize_1.log" + pipeline_cmd="${python} ocr_cpp_client.py ppocr_det_mobile_2.0_client/ ppocr_rec_mobile_2.0_client/" eval $pipeline_cmd - last_status=${PIPESTATUS[0]} - eval "cat ${_save_log_path}" status_check $last_status "${pipeline_cmd}" "${status_log}" - PID=$! - kill $PID sleep 2s ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 - done + else + web_service_cpp_cmd="${python} -m paddle_serving_server.serve --model ppocr_det_mobile_2.0_serving/ ppocr_rec_mobile_2.0_serving/ --port 9293 --gpu_id=0" + eval $web_service_cmd + sleep 2s + _save_log_path="${LOG_PATH}/server_infer_cpp_cpu_pipeline_usemkldnn_False_threads_4_batchsize_1.log" + pipeline_cmd="${python} ocr_cpp_client.py ppocr_det_mobile_2.0_client/ ppocr_rec_mobile_2.0_client/" + eval $pipeline_cmd + status_check $last_status "${pipeline_cmd}" "${status_log}" + sleep 2s + ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 + fi done else - echo "Does not support hardware other than CPU and GPU Currently!" + # python serving + for use_gpu in ${web_use_gpu_list[*]}; do + echo ${ues_gpu} + if [ ${use_gpu} = "null" ]; then + for use_mkldnn in ${web_use_mkldnn_list[*]}; do + if [ ${use_mkldnn} = "False" ]; then + continue + fi + for threads in ${web_cpu_threads_list[*]}; do + set_cpu_threads=$(func_set_params "${web_cpu_threads_key}" "${threads}") + web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}=${use_gpu} ${web_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} &" + eval $web_service_cmd + sleep 2s + for pipeline in ${pipeline_py[*]}; do + _save_log_path="${LOG_PATH}/server_infer_cpu_${pipeline%_client*}_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_1.log" + pipeline_cmd="${python} ${pipeline} ${set_image_dir} > ${_save_log_path} 2>&1 " + eval $pipeline_cmd + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${pipeline_cmd}" "${status_log}" + sleep 2s + done + ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 + done + done + elif [ ${use_gpu} = "0" ]; then + for use_trt in ${web_use_trt_list[*]}; do + for precision in ${web_precision_list[*]}; do + if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then + continue + fi + if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then + continue + fi + if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [[ ${_flag_quant} = "True" ]]; then + continue + fi + set_tensorrt=$(func_set_params "${web_use_trt_key}" "${use_trt}") + set_precision=$(func_set_params "${web_precision_key}" "${precision}") + web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} & " + eval $web_service_cmd + + sleep 2s + for pipeline in ${pipeline_py[*]}; do + _save_log_path="${LOG_PATH}/server_infer_gpu_${pipeline%_client*}_usetrt_${use_trt}_precision_${precision}_batchsize_1.log" + pipeline_cmd="${python} ${pipeline} ${set_image_dir}> ${_save_log_path} 2>&1" + eval $pipeline_cmd + last_status=${PIPESTATUS[0]} + eval "cat ${_save_log_path}" + status_check $last_status "${pipeline_cmd}" "${status_log}" + sleep 2s + done + ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9 + done + done + else + echo "Does not support hardware other than CPU and GPU Currently!" + fi + done fi done } diff --git a/test_tipc/test_train_inference_python.sh b/test_tipc/test_train_inference_python.sh index eaeaf9684b1fed6738149d61d3697232e105a72f..c62b6274f8dcbc84d08900c5d228d78fd3c0de1a 100644 --- a/test_tipc/test_train_inference_python.sh +++ b/test_tipc/test_train_inference_python.sh @@ -90,7 +90,7 @@ infer_value1=$(func_parser_value "${lines[50]}") # parser klquant_infer if [ ${MODE} = "klquant_whole_infer" ]; then - dataline=$(awk 'NR==82, NR==98{print}' $FILENAME) + dataline=$(awk 'NR==85 NR==101{print}' $FILENAME) lines=(${dataline}) # parser inference model infer_model_dir_list=$(func_parser_value "${lines[1]}") @@ -244,7 +244,7 @@ else export Count=0 USE_GPU_KEY=(${train_use_gpu_value}) for gpu in ${gpu_list[*]}; do - use_gpu=${USE_GPU_KEY[Count]} + train_use_gpu=${USE_GPU_KEY[Count]} Count=$(($Count + 1)) ips="" if [ ${gpu} = "-1" ];then @@ -302,11 +302,20 @@ else set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}") set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}") set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}") - set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${use_gpu}") - save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}" - + set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${train_use_gpu}") + if [ ${#ips} -le 26 ];then + save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}" + nodes=1 + else + IFS="," + ips_array=(${ips}) + IFS="|" + nodes=${#ips_array[@]} + save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}_nodes_${nodes}" + fi + # load pretrain from norm training if current trainer is pact or fpgm trainer - if [ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]; then + if ([ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]) && [ ${nodes} -le 1 ]; then set_pretrain="${load_norm_train_model}" fi @@ -325,7 +334,7 @@ else set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${train_model_name}") # save norm trained models to set pretrain for pact training and fpgm training - if [ ${trainer} = ${trainer_norm} ]; then + if [ ${trainer} = ${trainer_norm} ] && [ ${nodes} -le 1]; then load_norm_train_model=${set_eval_pretrain} fi # run eval