init
This commit is contained in:
@@ -0,0 +1,54 @@
|
||||
[English](README.md) | 简体中文
|
||||
# PP-OCRv3 昆仑芯XPU Python部署示例
|
||||
|
||||
本目录下提供`infer.py`, 供用户完成PP-OCRv3在昆仑芯XPU上的部署.
|
||||
|
||||
## 1. 部署环境准备
|
||||
在部署前，需自行编译基于昆仑XPU的FastDeploy python wheel包并安装，参考文档[昆仑芯XPU部署环境](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install#自行编译安装)
|
||||
|
||||
## 2.部署模型准备
|
||||
在部署前, 请准备好您所需要运行的推理模型, 您可以在[FastDeploy支持的PaddleOCR模型列表](../README.md)中下载所需模型.
|
||||
|
||||
## 3.运行部署示例
|
||||
```
|
||||
# 下载部署示例代码
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd FastDeploy/examples/vision/ocr/PP-OCR/kunlunxin/python
|
||||
|
||||
# 如果您希望从PaddleOCR下载示例代码，请运行
|
||||
git clone https://github.com/PaddlePaddle/PaddleOCR.git
|
||||
# 注意：如果当前分支找不到下面的fastdeploy测试代码，请切换到dygraph分支
|
||||
git checkout dygraph
|
||||
cd PaddleOCR/deploy/fastdeploy/kunlunxin/python
|
||||
|
||||
# 下载PP-OCRv3文字检测模型
|
||||
wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
|
||||
tar -xvf ch_PP-OCRv3_det_infer.tar
|
||||
# 下载文字方向分类器模型
|
||||
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
|
||||
tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
|
||||
# 下载PP-OCRv3文字识别模型
|
||||
wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
|
||||
tar -xvf ch_PP-OCRv3_rec_infer.tar
|
||||
|
||||
# 下载预测图片与字典文件
|
||||
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
|
||||
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
|
||||
|
||||
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg
|
||||
```
|
||||
|
||||
运行完成可视化结果如下图所示
|
||||
|
||||
<div align="center">
|
||||
<img width="640" src="https://user-images.githubusercontent.com/109218879/185826024-f7593a0c-1bd2-4a60-b76c-15588484fa08.jpg">
|
||||
</div>
|
||||
|
||||
## 4. 更多指南
|
||||
- [PP-OCR系列 Python API查阅](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/python/html/ocr.html)
|
||||
- [FastDeploy部署PaddleOCR模型概览](../../)
|
||||
- [PP-OCRv3 C++部署](../cpp)
|
||||
- 如果用户想要调整前后处理超参数、单独使用文字检测识别模型、使用其他模型等，更多详细文档与说明请参考[PP-OCR系列在CPU/GPU上的部署](../../cpu-gpu/python/README.md)
|
||||
|
||||
## 5. 常见问题
|
||||
- [如何将视觉模型预测结果转为numpy格式](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/vision_result_related_problems.md)
|
||||
@@ -0,0 +1,111 @@
|
||||
# Copyright (c) 2022 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.
|
||||
|
||||
import fastdeploy as fd
|
||||
import cv2
|
||||
import os
|
||||
|
||||
|
||||
def parse_arguments():
|
||||
import argparse
|
||||
import ast
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"--det_model", required=True, help="Path of Detection model of PPOCR.")
|
||||
parser.add_argument(
|
||||
"--cls_model",
|
||||
required=True,
|
||||
help="Path of Classification model of PPOCR.")
|
||||
parser.add_argument(
|
||||
"--rec_model",
|
||||
required=True,
|
||||
help="Path of Recognization model of PPOCR.")
|
||||
parser.add_argument(
|
||||
"--rec_label_file",
|
||||
required=True,
|
||||
help="Path of Recognization model of PPOCR.")
|
||||
parser.add_argument(
|
||||
"--image", type=str, required=True, help="Path of test image file.")
|
||||
parser.add_argument(
|
||||
"--cls_bs",
|
||||
type=int,
|
||||
default=1,
|
||||
help="Classification model inference batch size.")
|
||||
parser.add_argument(
|
||||
"--rec_bs",
|
||||
type=int,
|
||||
default=6,
|
||||
help="Recognition model inference batch size")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def build_option(args):
|
||||
|
||||
det_option = fd.RuntimeOption()
|
||||
cls_option = fd.RuntimeOption()
|
||||
rec_option = fd.RuntimeOption()
|
||||
|
||||
det_option.use_kunlunxin()
|
||||
cls_option.use_kunlunxin()
|
||||
rec_option.use_kunlunxin()
|
||||
|
||||
return det_option, cls_option, rec_option
|
||||
|
||||
|
||||
args = parse_arguments()
|
||||
|
||||
det_model_file = os.path.join(args.det_model, "inference.pdmodel")
|
||||
det_params_file = os.path.join(args.det_model, "inference.pdiparams")
|
||||
|
||||
cls_model_file = os.path.join(args.cls_model, "inference.pdmodel")
|
||||
cls_params_file = os.path.join(args.cls_model, "inference.pdiparams")
|
||||
|
||||
rec_model_file = os.path.join(args.rec_model, "inference.pdmodel")
|
||||
rec_params_file = os.path.join(args.rec_model, "inference.pdiparams")
|
||||
rec_label_file = args.rec_label_file
|
||||
|
||||
det_option, cls_option, rec_option = build_option(args)
|
||||
|
||||
det_model = fd.vision.ocr.DBDetector(
|
||||
det_model_file, det_params_file, runtime_option=det_option)
|
||||
|
||||
cls_model = fd.vision.ocr.Classifier(
|
||||
cls_model_file, cls_params_file, runtime_option=cls_option)
|
||||
|
||||
rec_model = fd.vision.ocr.Recognizer(
|
||||
rec_model_file, rec_params_file, rec_label_file, runtime_option=rec_option)
|
||||
|
||||
# Create PP-OCRv3, if cls_model is not needed,
|
||||
# just set cls_model=None .
|
||||
ppocr_v3 = fd.vision.ocr.PPOCRv3(
|
||||
det_model=det_model, cls_model=cls_model, rec_model=rec_model)
|
||||
|
||||
# Set inference batch size for cls model and rec model, the value could be -1 and 1 to positive infinity.
|
||||
# When inference batch size is set to -1, it means that the inference batch size
|
||||
# of the cls and rec models will be the same as the number of boxes detected by the det model.
|
||||
ppocr_v3.cls_batch_size = args.cls_bs
|
||||
ppocr_v3.rec_batch_size = args.rec_bs
|
||||
|
||||
# Prepare image.
|
||||
im = cv2.imread(args.image)
|
||||
|
||||
# Print the results.
|
||||
result = ppocr_v3.predict(im)
|
||||
|
||||
print(result)
|
||||
|
||||
# Visuliaze the output.
|
||||
vis_im = fd.vision.vis_ppocr(im, result)
|
||||
cv2.imwrite("visualized_result.jpg", vis_im)
|
||||
print("Visualized result save in ./visualized_result.jpg")
|
||||
Reference in New Issue
Block a user