mirror of
https://github.com/RapidAI/RapidOCR.git
synced 2026-11-13 22:40:53 +08:00
Add openvino support
This commit is contained in:
SWHL committed
1 parent
a65416fced
commit
932c4d1869
59 files changed
+2026
-142
No files matched your search
+47
-135
@@ -1,148 +1,60 @@
|
||||
### 使用步骤
|
||||
1. 下载相应模型和用于显示的字体文件
|
||||
- [百度网盘 提取码：30jv](https://pan.baidu.com/s/1qkqWK4wRdMjqGGbzR-FyWg) | [Google Drive](https://drive.google.com/drive/folders/1x_a9KpCo_1blxH1xFOfgKVkw1HYRVywY?usp=sharing)
|
||||
### 目录说明
|
||||
- `onnxruntime_infer`: 基于ONNXRuntime推理引擎推理
|
||||
- `openvino_infer`: 基于OpenVINO推理引擎推理
|
||||
|
||||
- 下载之后模型和相应字体文件放在`fonts`和`models`下，最终目录结构如下：
|
||||
```text
|
||||
models
|
||||
|-- ch_PP-OCRv2_det_infer.onnx
|
||||
|-- ch_ppocr_mobile_v2.0_cls_infer.onnx
|
||||
|-- ch_ppocr_mobile_v2.0_det_infer.onnx
|
||||
|-- ch_ppocr_server_v2.0_det_infer.onnx
|
||||
|-- ch_ppocr_server_v2.0_rec_infer.onnx
|
||||
|-- en_number_mobile_v2.0_rec_infer.onnx
|
||||
|-- korean_mobile_v2.0_rec_infer.onnx
|
||||
`-- japan_rec_crnn.onnx
|
||||
### TODO
|
||||
- [ ] 模型转INT8，尚未找到转换代码
|
||||
- [ ] 其他推理模型代码整理
|
||||
- [ ] 模型转换代码整理
|
||||
|
||||
fonts
|
||||
|-- msyh.ttc
|
||||
`-- korean.ttf
|
||||
```
|
||||
### 关于OpenVINO
|
||||
- OpenVINO可以直接推理ONNX模型，可以不用转换直接使用之前ONNX模型
|
||||
- OpenVINO推理速度更快，但是从对比来看，占用内存更多，目前正在排查原因
|
||||
|
||||
2. 运行
|
||||
- 接口调用方式运行
|
||||
- 如果想要使用其他语言的识别模型，可以只对`rec_model_path`和`keys_path`作对应更改即可
|
||||
- **!!!各个不同语言的推理代码区别只在于模型和字典文件!!!**
|
||||
```python
|
||||
from rapid_ocr_api import TextSystem, visualize
|
||||
### OpenVINO与ONNXRuntime性能对比
|
||||
- 推理设备：`Windows 64位 Intel(R) Core(TM) i5-4210M CPU @ 2.60GHz 2.59 GHz`
|
||||
- 测试图像宽高: `12119x810`
|
||||
|
||||
det_model_path = 'models/ch_ppocr_mobile_v2.0_det_infer.onnx'
|
||||
cls_model_path = 'models/ch_ppocr_mobile_v2.0_cls_infer.onnx'
|
||||
|
||||
# 中英文识别
|
||||
rec_model_path = 'models/ch_ppocr_mobile_v2.0_rec_infer.onnx'
|
||||
keys_path = 'rec_dict/ppocr_keys_v1.txt'
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
|
||||
image_path = r'test_images/det_images/ch_en_num.jpg'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res)
|
||||
| 测试模型 | 推理框架 | 占用内存(3次平均) | 推理时间(3次平均) |
|
||||
| ------------------------------------ | -------------------- | ----------------- | ----------------- |
|
||||
| `ch_PP-OCRv2_det_infer.onnx` | `ONNXRuntime=1.10.0` | 0.8G | 5.354s |
|
||||
| `ch_PP-OCRv2_det_infer.onnx` | `openvino=2022.1.0` | 3.225G | 2.53s |
|
||||
| `ch_PP-OCRv2_det_infer.xml` FP32 | `openvino=2022.1.0` | 3.175G | 2.0455s |
|
||||
|
||||
|
||||
# 只有中英文和数字识别
|
||||
rec_model_path = 'models/en_number_mobile_v2.0_rec_infer.onnx'
|
||||
keys_path = 'rec_dict/en_dict.txt'
|
||||
### OpenVINO与ONNXRuntime推理代码写法对比
|
||||
NOTE: 以`ch_ppocr_mobile_v2_det`中推理代码为例子
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
- ONNXRuntime
|
||||
```python
|
||||
import onnxruntime
|
||||
|
||||
image_path = r'test_images/det_images/en_num.png'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res)
|
||||
# 声明
|
||||
sess_opt = onnxruntime.SessionOptions()
|
||||
sess_opt.log_severity_level = 4
|
||||
sess_opt.enable_cpu_mem_arena = False
|
||||
self.session = onnxruntime.InferenceSession(det_model_path, sess_opt)
|
||||
self.input_name = self.session.get_inputs()[0].name
|
||||
self.output_name = self.session.get_outputs()[0].name
|
||||
|
||||
# 推理
|
||||
preds = self.session.run([self.output_name],
|
||||
{self.input_name: img})
|
||||
```
|
||||
|
||||
# 日语识别
|
||||
rec_model_path = 'models/japan_rec_crnn.onnx'
|
||||
keys_path = 'rec_dict/japan_dict.txt'
|
||||
- OpenVINO
|
||||
```python
|
||||
from openvino.runtime import Core
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
# 初始化
|
||||
ie = Core()
|
||||
model_onnx = ie.read_model(det_model_path)
|
||||
compile_model = ie.compile_model(model=model_onnx,
|
||||
device_name='CPU')
|
||||
self.vino_session = compile_model.create_infer_request()
|
||||
|
||||
image_path = r'test_images/det_images/japan.png'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res)
|
||||
# 推理
|
||||
self.vino_session.infer(inputs=[img])
|
||||
vino_preds = self.vino_session.get_output_tensor().data
|
||||
```
|
||||
|
||||
|
||||
# 韩语识别
|
||||
rec_model_path = 'models/korean_mobile_v2.0_rec_infer.onnx'
|
||||
keys_path = 'rec_dict/korean_dict.txt'
|
||||
font_path = 'fonts/korean.ttf'
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
|
||||
image_path = r'test_images/det_images/korean_1.jpg'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res, font_path)
|
||||
```
|
||||
|
||||
- 命令行运行
|
||||
```shell
|
||||
$ bash test_demo.sh
|
||||
```
|
||||
|
||||
### 相关调节参数
|
||||
|参数名称|作用|建议取值范围|默认值|代码位置|
|
||||
|:---:|:---:|:---:|:---:|:---:|
|
||||
|box_thresh|文本检测所得框是否保留的阈值，值越大，召回率越低|[0, 1]|0.5|[text_detect.py](https://github.com/RapidAI/RapidOCR/blob/6aa79aa390c9c9e8f41df0f0c35f3dca97e6dc93/python/ch_ppocr_mobile_v2_det/text_detect.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L55)|
|
||||
|unclip_ratio|控制文本检测框的大小，值越大，检测框整体越大|[1.6, 2.0]|1.6|[text_detect.py](https://github.com/RapidAI/RapidOCR/blob/6aa79aa390c9c9e8f41df0f0c35f3dca97e6dc93/python/ch_ppocr_mobile_v2_det/text_detect.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L57)|
|
||||
|text_score|文本识别结果置信度，值越大，把握越大|[0, 1]|0.5|[rapidOCR.py](https://github.com/RapidAI/RapidOCR/blob/6aa79aa390c9c9e8f41df0f0c35f3dca97e6dc93/python/rapidOCR.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L270)|
|
||||
|
||||
|
||||
### onnxruntime-gpu版推理配置
|
||||
|
||||
1. ONNXRuntime-gpu需要严格按照与cuda、cudnn版本对应来安装，具体参考[文档](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), **这一步关乎后面是否可以成功调用GPU**
|
||||
2. 推理代码中，加载onnx模型部分，用以下对应语言代码替换即可,详细参见：[官方教程](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html)
|
||||
- python版本
|
||||
```python
|
||||
import onnxruntime as ort
|
||||
|
||||
model_path = '<path to model>'
|
||||
|
||||
providers = [
|
||||
('CUDAExecutionProvider', {
|
||||
'device_id': 0,
|
||||
'arena_extend_strategy': 'kNextPowerOfTwo',
|
||||
'gpu_mem_limit': 2 * 1024 * 1024 * 1024,
|
||||
'cudnn_conv_algo_search': 'EXHAUSTIVE',
|
||||
'do_copy_in_default_stream': True,
|
||||
}),
|
||||
'CPUExecutionProvider',
|
||||
]
|
||||
|
||||
session = ort.InferenceSession(model_path, providers=providers)
|
||||
```
|
||||
- C/C++版本
|
||||
```c++
|
||||
OrtSessionOptions* session_options = /* ... */;
|
||||
|
||||
OrtCUDAProviderOptions options;
|
||||
options.device_id = 0;
|
||||
options.arena_extend_strategy = 0;
|
||||
options.gpu_mem_limit = 2 * 1024 * 1024 * 1024;
|
||||
options.cudnn_conv_algo_search = OrtCudnnConvAlgoSearch::EXHAUSTIVE;
|
||||
options.do_copy_in_default_stream = 1;
|
||||
|
||||
SessionOptionsAppendExecutionProvider_CUDA(session_options, &options);
|
||||
```
|
||||
3. 推理时间粗略对比(跑完RapidOCR整个项目)
|
||||
|
||||
|推理方式|推理图像数目|耗费时间|
|
||||
|:---:|:---:|:---:|
|
||||
|CPU|46张图像|191 s|
|
||||
|GPU|46张图像|52.38 s|
|
||||
||||
|
||||
@@ -0,0 +1,148 @@
|
||||
### 使用步骤
|
||||
1. 下载相应模型和用于显示的字体文件
|
||||
- [百度网盘 提取码：30jv](https://pan.baidu.com/s/1qkqWK4wRdMjqGGbzR-FyWg) | [Google Drive](https://drive.google.com/drive/folders/1x_a9KpCo_1blxH1xFOfgKVkw1HYRVywY?usp=sharing)
|
||||
|
||||
- 下载之后模型和相应字体文件放在`fonts`和`models`下，最终目录结构如下：
|
||||
```text
|
||||
models
|
||||
|-- ch_PP-OCRv2_det_infer.onnx
|
||||
|-- ch_ppocr_mobile_v2.0_cls_infer.onnx
|
||||
|-- ch_ppocr_mobile_v2.0_det_infer.onnx
|
||||
|-- ch_ppocr_server_v2.0_det_infer.onnx
|
||||
|-- ch_ppocr_server_v2.0_rec_infer.onnx
|
||||
|-- en_number_mobile_v2.0_rec_infer.onnx
|
||||
|-- korean_mobile_v2.0_rec_infer.onnx
|
||||
`-- japan_rec_crnn.onnx
|
||||
|
||||
fonts
|
||||
|-- msyh.ttc
|
||||
`-- korean.ttf
|
||||
```
|
||||
|
||||
2. 运行
|
||||
- 接口调用方式运行
|
||||
- 如果想要使用其他语言的识别模型，可以只对`rec_model_path`和`keys_path`作对应更改即可
|
||||
- **!!!各个不同语言的推理代码区别只在于模型和字典文件!!!**
|
||||
```python
|
||||
from rapid_ocr_api import TextSystem, visualize
|
||||
|
||||
det_model_path = 'models/ch_ppocr_mobile_v2.0_det_infer.onnx'
|
||||
cls_model_path = 'models/ch_ppocr_mobile_v2.0_cls_infer.onnx'
|
||||
|
||||
# 中英文识别
|
||||
rec_model_path = 'models/ch_ppocr_mobile_v2.0_rec_infer.onnx'
|
||||
keys_path = 'rec_dict/ppocr_keys_v1.txt'
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
|
||||
image_path = r'test_images/det_images/ch_en_num.jpg'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res)
|
||||
|
||||
|
||||
# 只有中英文和数字识别
|
||||
rec_model_path = 'models/en_number_mobile_v2.0_rec_infer.onnx'
|
||||
keys_path = 'rec_dict/en_dict.txt'
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
|
||||
image_path = r'test_images/det_images/en_num.png'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res)
|
||||
|
||||
|
||||
# 日语识别
|
||||
rec_model_path = 'models/japan_rec_crnn.onnx'
|
||||
keys_path = 'rec_dict/japan_dict.txt'
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
|
||||
image_path = r'test_images/det_images/japan.png'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res)
|
||||
|
||||
|
||||
# 韩语识别
|
||||
rec_model_path = 'models/korean_mobile_v2.0_rec_infer.onnx'
|
||||
keys_path = 'rec_dict/korean_dict.txt'
|
||||
font_path = 'fonts/korean.ttf'
|
||||
|
||||
text_sys = TextSystem(det_model_path,
|
||||
rec_model_path,
|
||||
use_angle_cls=True,
|
||||
cls_model_path=cls_model_path,
|
||||
keys_path=keys_path)
|
||||
|
||||
image_path = r'test_images/det_images/korean_1.jpg'
|
||||
dt_boxes, rec_res = text_sys(image_path)
|
||||
visualize(image_path, dt_boxes, rec_res, font_path)
|
||||
```
|
||||
|
||||
- 命令行运行
|
||||
```shell
|
||||
$ bash test_demo.sh
|
||||
```
|
||||
|
||||
### 相关调节参数
|
||||
|参数名称|作用|建议取值范围|默认值|代码位置|
|
||||
|:---:|:---:|:---:|:---:|:---:|
|
||||
|box_thresh|文本检测所得框是否保留的阈值，值越大，召回率越低|[0, 1]|0.5|[text_detect.py](https://github.com/RapidAI/RapidOCR/blob/6aa79aa390c9c9e8f41df0f0c35f3dca97e6dc93/python/ch_ppocr_mobile_v2_det/text_detect.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L55)|
|
||||
|unclip_ratio|控制文本检测框的大小，值越大，检测框整体越大|[1.6, 2.0]|1.6|[text_detect.py](https://github.com/RapidAI/RapidOCR/blob/6aa79aa390c9c9e8f41df0f0c35f3dca97e6dc93/python/ch_ppocr_mobile_v2_det/text_detect.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L57)|
|
||||
|text_score|文本识别结果置信度，值越大，把握越大|[0, 1]|0.5|[rapidOCR.py](https://github.com/RapidAI/RapidOCR/blob/6aa79aa390c9c9e8f41df0f0c35f3dca97e6dc93/python/rapidOCR.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L270)|
|
||||
|
||||
|
||||
### onnxruntime-gpu版推理配置
|
||||
|
||||
1. ONNXRuntime-gpu需要严格按照与cuda、cudnn版本对应来安装，具体参考[文档](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), **这一步关乎后面是否可以成功调用GPU**
|
||||
2. 推理代码中，加载onnx模型部分，用以下对应语言代码替换即可,详细参见：[官方教程](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html)
|
||||
- python版本
|
||||
```python
|
||||
import onnxruntime as ort
|
||||
|
||||
model_path = '<path to model>'
|
||||
|
||||
providers = [
|
||||
('CUDAExecutionProvider', {
|
||||
'device_id': 0,
|
||||
'arena_extend_strategy': 'kNextPowerOfTwo',
|
||||
'gpu_mem_limit': 2 * 1024 * 1024 * 1024,
|
||||
'cudnn_conv_algo_search': 'EXHAUSTIVE',
|
||||
'do_copy_in_default_stream': True,
|
||||
}),
|
||||
'CPUExecutionProvider',
|
||||
]
|
||||
|
||||
session = ort.InferenceSession(model_path, providers=providers)
|
||||
```
|
||||
- C/C++版本
|
||||
```c++
|
||||
OrtSessionOptions* session_options = /* ... */;
|
||||
|
||||
OrtCUDAProviderOptions options;
|
||||
options.device_id = 0;
|
||||
options.arena_extend_strategy = 0;
|
||||
options.gpu_mem_limit = 2 * 1024 * 1024 * 1024;
|
||||
options.cudnn_conv_algo_search = OrtCudnnConvAlgoSearch::EXHAUSTIVE;
|
||||
options.do_copy_in_default_stream = 1;
|
||||
|
||||
SessionOptionsAppendExecutionProvider_CUDA(session_options, &options);
|
||||
```
|
||||
3. 推理时间粗略对比(跑完RapidOCR整个项目)
|
||||
|
||||
|推理方式|推理图像数目|耗费时间|
|
||||
|:---:|:---:|:---:|
|
||||
|CPU|46张图像|191 s|
|
||||
|GPU|46张图像|52.38 s|
|
||||
||||
|
||||
Executable → Regular
File renamed without changes.
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
File renamed without changes.
Executable → Regular
File renamed without changes.
Executable → Regular
File renamed without changes.
File renamed without changes.
Executable → Regular
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
Executable → Regular
+2
-1
@@ -4,4 +4,5 @@ onnxruntime==1.7.0
|
||||
opencv_python==4.5.1.48
|
||||
six==1.15.0
|
||||
numpy==1.19.2
|
||||
Pillow==8.3.0
|
||||
Pillow==8.3.0
|
||||
openvino==2022.1.0
|
||||
File renamed without changes.
File renamed without changes.
File renamed without changes.
|
Before Width: | Height: | Size: 69 KiB After Width: | Height: | Size: 69 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 291 KiB After Width: | Height: | Size: 291 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 453 KiB After Width: | Height: | Size: 453 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 39 KiB After Width: | Height: | Size: 39 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 159 KiB After Width: | Height: | Size: 159 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 201 KiB After Width: | Height: | Size: 201 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 5.6 KiB After Width: | Height: | Size: 5.6 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 8.7 KiB After Width: | Height: | Size: 8.7 KiB |
File renamed without changes.
|
Before Width: | Height: | Size: 3.6 KiB After Width: | Height: | Size: 3.6 KiB |
@@ -0,0 +1,6 @@
|
||||
#### 安装
|
||||
```bash
|
||||
# Windows端
|
||||
pip install openvino==2022.1.0
|
||||
pip install openvino-dev==2022.1.0
|
||||
```
|
||||
@@ -0,0 +1,6 @@
|
||||
# !/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
# @File: __init__.py
|
||||
# @Time: 2021/01/23 15:24:27
|
||||
# @Author: Max
|
||||
from .text_detect import TextDetector
|
||||
@@ -0,0 +1,9 @@
|
||||
#! /bin/bash
|
||||
set -e errexit
|
||||
|
||||
root_path=$(cd $(dirname $0); pwd)
|
||||
image_path=${root_path}"/test_images/det_images/1.jpg"
|
||||
model_path=${root_path}"/models/ch_ppocr_mobile_v2.0_det_infer.onnx"
|
||||
|
||||
python text_detect.py --image_path ${image_path} \
|
||||
--model_path ${model_path}
|
||||
@@ -0,0 +1,153 @@
|
||||
# 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.
|
||||
# !/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
import argparse
|
||||
import time
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from openvino.runtime import Core
|
||||
|
||||
try:
|
||||
from .utils import (DBPostProcess, check_and_read_gif, create_operators,
|
||||
draw_text_det_res, transform)
|
||||
except:
|
||||
from utils import (DBPostProcess, check_and_read_gif, create_operators,
|
||||
draw_text_det_res, transform)
|
||||
|
||||
|
||||
class TextDetector(object):
|
||||
def __init__(self, det_model_path):
|
||||
pre_process_list = [{
|
||||
'DetResizeForTest': {
|
||||
'limit_side_len': 736,
|
||||
'limit_type': 'min'
|
||||
}
|
||||
}, {
|
||||
'NormalizeImage': {
|
||||
'std': [0.229, 0.224, 0.225],
|
||||
'mean': [0.485, 0.456, 0.406],
|
||||
'scale': '1./255.',
|
||||
'order': 'hwc'
|
||||
}
|
||||
}, {
|
||||
'ToCHWImage': None
|
||||
}, {
|
||||
'KeepKeys': {
|
||||
'keep_keys': ['image', 'shape']
|
||||
}
|
||||
}]
|
||||
|
||||
self.preprocess_op = create_operators(pre_process_list)
|
||||
self.postprocess_op = DBPostProcess(thresh=0.3,
|
||||
box_thresh=0.5,
|
||||
max_candidates=1000,
|
||||
unclip_ratio=1.6,
|
||||
use_dilation=True)
|
||||
ie = Core()
|
||||
model_onnx = ie.read_model(det_model_path)
|
||||
compile_model = ie.compile_model(model=model_onnx,
|
||||
device_name='CPU')
|
||||
self.vino_session = compile_model.create_infer_request()
|
||||
|
||||
def order_points_clockwise(self, pts):
|
||||
"""
|
||||
reference from: https://github.com/jrosebr1/imutils/blob/master/imutils/perspective.py
|
||||
# sort the points based on their x-coordinates
|
||||
"""
|
||||
xSorted = pts[np.argsort(pts[:, 0]), :]
|
||||
|
||||
# grab the left-most and right-most points from the sorted
|
||||
# x-roodinate points
|
||||
leftMost = xSorted[:2, :]
|
||||
rightMost = xSorted[2:, :]
|
||||
|
||||
# now, sort the left-most coordinates according to their
|
||||
# y-coordinates so we can grab the top-left and bottom-left
|
||||
# points, respectively
|
||||
leftMost = leftMost[np.argsort(leftMost[:, 1]), :]
|
||||
(tl, bl) = leftMost
|
||||
|
||||
rightMost = rightMost[np.argsort(rightMost[:, 1]), :]
|
||||
(tr, br) = rightMost
|
||||
|
||||
rect = np.array([tl, tr, br, bl], dtype="float32")
|
||||
return rect
|
||||
|
||||
def clip_det_res(self, points, img_height, img_width):
|
||||
for pno in range(points.shape[0]):
|
||||
points[pno, 0] = int(min(max(points[pno, 0], 0), img_width - 1))
|
||||
points[pno, 1] = int(min(max(points[pno, 1], 0), img_height - 1))
|
||||
return points
|
||||
|
||||
def filter_tag_det_res(self, dt_boxes, image_shape):
|
||||
img_height, img_width = image_shape[0:2]
|
||||
dt_boxes_new = []
|
||||
for box in dt_boxes:
|
||||
box = self.order_points_clockwise(box)
|
||||
box = self.clip_det_res(box, img_height, img_width)
|
||||
rect_width = int(np.linalg.norm(box[0] - box[1]))
|
||||
rect_height = int(np.linalg.norm(box[0] - box[3]))
|
||||
if rect_width <= 3 or rect_height <= 3:
|
||||
continue
|
||||
dt_boxes_new.append(box)
|
||||
dt_boxes = np.array(dt_boxes_new)
|
||||
return dt_boxes
|
||||
|
||||
def __call__(self, img):
|
||||
ori_im = img.copy()
|
||||
data = {'image': img}
|
||||
data = transform(data, self.preprocess_op)
|
||||
img, shape_list = data
|
||||
if img is None:
|
||||
return None, 0
|
||||
img = np.expand_dims(img, axis=0)
|
||||
img = img.astype(np.float32)
|
||||
shape_list = np.expand_dims(shape_list, axis=0)
|
||||
|
||||
start_time = time.time()
|
||||
self.vino_session.infer(inputs=[img])
|
||||
vino_preds = self.vino_session.get_output_tensor().data
|
||||
|
||||
post_result = self.postprocess_op(vino_preds, shape_list)
|
||||
dt_boxes = post_result[0]['points']
|
||||
dt_boxes = self.filter_tag_det_res(dt_boxes, ori_im.shape)
|
||||
elapse = time.time() - start_time
|
||||
|
||||
src_im = draw_text_det_res(dt_boxes, r'E:\PythonProjects\RapidOCR\python\test_images\long1.jpg')
|
||||
cv2.imwrite('det_results.jpg', src_im)
|
||||
return dt_boxes, elapse
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--image_path', type=str, help='image_path|image_dir')
|
||||
parser.add_argument('--model_path', type=str, help='model_path')
|
||||
args = parser.parse_args()
|
||||
|
||||
text_detector = TextDetector(args.model_path)
|
||||
|
||||
img, flag = check_and_read_gif(args.image_path)
|
||||
if not flag:
|
||||
img = cv2.imread(args.image_path)
|
||||
if img is None:
|
||||
raise ValueError(f"error in loading image:{args.image_path}")
|
||||
|
||||
dt_boxes, elapse = text_detector(img)
|
||||
|
||||
src_im = draw_text_det_res(dt_boxes, args.image_path)
|
||||
cv2.imwrite('det_results.jpg', src_im)
|
||||
print(f'图像已经保存为det_results.jpg了\t{elapse:.6f}s')
|
||||
|
||||
@@ -0,0 +1,414 @@
|
||||
"""
|
||||
# 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.
|
||||
"""
|
||||
# coding:utf-8
|
||||
from __future__ import (absolute_import, division, print_function,
|
||||
unicode_literals)
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import pyclipper
|
||||
import six
|
||||
from shapely.geometry import Polygon
|
||||
|
||||
|
||||
class DecodeImage(object):
|
||||
""" decode image """
|
||||
|
||||
def __init__(self, img_mode='RGB', channel_first=False, **kwargs):
|
||||
self.img_mode = img_mode
|
||||
self.channel_first = channel_first
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
if six.PY2:
|
||||
assert type(img) is str and len(
|
||||
img) > 0, "invalid input 'img' in DecodeImage"
|
||||
else:
|
||||
assert type(img) is bytes and len(
|
||||
img) > 0, "invalid input 'img' in DecodeImage"
|
||||
img = np.frombuffer(img, dtype='uint8')
|
||||
img = cv2.imdecode(img, 1)
|
||||
if img is None:
|
||||
return None
|
||||
if self.img_mode == 'GRAY':
|
||||
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
|
||||
elif self.img_mode == 'RGB':
|
||||
assert img.shape[2] == 3, 'invalid shape of image[%s]' % (
|
||||
img.shape)
|
||||
img = img[:, :, ::-1]
|
||||
|
||||
if self.channel_first:
|
||||
img = img.transpose((2, 0, 1))
|
||||
|
||||
data['image'] = img
|
||||
return data
|
||||
|
||||
|
||||
class NormalizeImage(object):
|
||||
""" normalize image such as substract mean, divide std
|
||||
"""
|
||||
|
||||
def __init__(self, scale=None, mean=None, std=None, order='chw', **kwargs):
|
||||
if isinstance(scale, str):
|
||||
scale = eval(scale)
|
||||
self.scale = np.float32(scale if scale is not None else 1.0 / 255.0)
|
||||
mean = mean if mean is not None else [0.485, 0.456, 0.406]
|
||||
std = std if std is not None else [0.229, 0.224, 0.225]
|
||||
|
||||
shape = (3, 1, 1) if order == 'chw' else (1, 1, 3)
|
||||
self.mean = np.array(mean).reshape(shape).astype('float32')
|
||||
self.std = np.array(std).reshape(shape).astype('float32')
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
from PIL import Image
|
||||
if isinstance(img, Image.Image):
|
||||
img = np.array(img)
|
||||
|
||||
assert isinstance(img,
|
||||
np.ndarray), "invalid input 'img' in NormalizeImage"
|
||||
data['image'] = (
|
||||
img.astype('float32') * self.scale - self.mean) / self.std
|
||||
return data
|
||||
|
||||
|
||||
class ToCHWImage(object):
|
||||
""" convert hwc image to chw image
|
||||
"""
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
pass
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
from PIL import Image
|
||||
if isinstance(img, Image.Image):
|
||||
img = np.array(img)
|
||||
data['image'] = img.transpose((2, 0, 1))
|
||||
return data
|
||||
|
||||
|
||||
class KeepKeys(object):
|
||||
def __init__(self, keep_keys, **kwargs):
|
||||
self.keep_keys = keep_keys
|
||||
|
||||
def __call__(self, data):
|
||||
data_list = []
|
||||
for key in self.keep_keys:
|
||||
data_list.append(data[key])
|
||||
return data_list
|
||||
|
||||
|
||||
class DetResizeForTest(object):
|
||||
def __init__(self, **kwargs):
|
||||
super(DetResizeForTest, self).__init__()
|
||||
self.resize_type = 0
|
||||
if 'image_shape' in kwargs:
|
||||
self.image_shape = kwargs['image_shape']
|
||||
self.resize_type = 1
|
||||
elif 'limit_side_len' in kwargs:
|
||||
self.limit_side_len = kwargs['limit_side_len']
|
||||
self.limit_type = kwargs.get('limit_type', 'min')
|
||||
|
||||
if 'resize_long' in kwargs:
|
||||
self.resize_type = 2
|
||||
self.resize_long = kwargs.get('resize_long', 960)
|
||||
else:
|
||||
self.limit_side_len = 736
|
||||
self.limit_type = 'min'
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
src_h, src_w, _ = img.shape
|
||||
|
||||
if self.resize_type == 0:
|
||||
# img, shape = self.resize_image_type0(img)
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type0(img)
|
||||
elif self.resize_type == 2:
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type2(img)
|
||||
else:
|
||||
# img, shape = self.resize_image_type1(img)
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type1(img)
|
||||
data['image'] = img
|
||||
data['shape'] = np.array([src_h, src_w, ratio_h, ratio_w])
|
||||
return data
|
||||
|
||||
def resize_image_type1(self, img):
|
||||
resize_h, resize_w = self.image_shape
|
||||
ori_h, ori_w = img.shape[:2] # (h, w, c)
|
||||
ratio_h = float(resize_h) / ori_h
|
||||
ratio_w = float(resize_w) / ori_w
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
# return img, np.array([ori_h, ori_w])
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
def resize_image_type0(self, img):
|
||||
"""
|
||||
resize image to a size multiple of 32 which is required by the network
|
||||
args:
|
||||
img(array): array with shape [h, w, c]
|
||||
return(tuple):
|
||||
img, (ratio_h, ratio_w)
|
||||
"""
|
||||
limit_side_len = self.limit_side_len
|
||||
h, w, _ = img.shape
|
||||
|
||||
# limit the max side
|
||||
if self.limit_type == 'max':
|
||||
if max(h, w) > limit_side_len:
|
||||
if h > w:
|
||||
ratio = float(limit_side_len) / h
|
||||
else:
|
||||
ratio = float(limit_side_len) / w
|
||||
else:
|
||||
ratio = 1.
|
||||
else:
|
||||
if min(h, w) < limit_side_len:
|
||||
if h < w:
|
||||
ratio = float(limit_side_len) / h
|
||||
else:
|
||||
ratio = float(limit_side_len) / w
|
||||
else:
|
||||
ratio = 1.
|
||||
resize_h = int(h * ratio)
|
||||
resize_w = int(w * ratio)
|
||||
|
||||
resize_h = int(round(resize_h / 32) * 32)
|
||||
resize_w = int(round(resize_w / 32) * 32)
|
||||
|
||||
try:
|
||||
if int(resize_w) <= 0 or int(resize_h) <= 0:
|
||||
return None, (None, None)
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
except:
|
||||
print(img.shape, resize_w, resize_h)
|
||||
sys.exit(0)
|
||||
ratio_h = resize_h / float(h)
|
||||
ratio_w = resize_w / float(w)
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
def resize_image_type2(self, img):
|
||||
h, w, _ = img.shape
|
||||
|
||||
resize_w = w
|
||||
resize_h = h
|
||||
|
||||
# Fix the longer side
|
||||
if resize_h > resize_w:
|
||||
ratio = float(self.resize_long) / resize_h
|
||||
else:
|
||||
ratio = float(self.resize_long) / resize_w
|
||||
|
||||
resize_h = int(resize_h * ratio)
|
||||
resize_w = int(resize_w * ratio)
|
||||
|
||||
max_stride = 128
|
||||
resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
|
||||
resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
ratio_h = resize_h / float(h)
|
||||
ratio_w = resize_w / float(w)
|
||||
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
|
||||
def transform(data, ops=None):
|
||||
""" transform """
|
||||
if ops is None:
|
||||
ops = []
|
||||
for op in ops:
|
||||
data = op(data)
|
||||
if data is None:
|
||||
return None
|
||||
return data
|
||||
|
||||
|
||||
def check_and_read_gif(img_path):
|
||||
if os.path.basename(img_path)[-3:] in ['gif', 'GIF']:
|
||||
gif = cv2.VideoCapture(img_path)
|
||||
ret, frame = gif.read()
|
||||
if not ret:
|
||||
print("Cannot read {}. This gif image maybe corrupted.")
|
||||
return None, False
|
||||
if len(frame.shape) == 2 or frame.shape[-1] == 1:
|
||||
frame = cv2.cvtColor(frame, cv2.COLOR_GRAY2RGB)
|
||||
imgvalue = frame[:, :, ::-1]
|
||||
return imgvalue, True
|
||||
return None, False
|
||||
|
||||
|
||||
def create_operators(op_param_list, global_config=None):
|
||||
"""
|
||||
create operators based on the config
|
||||
|
||||
Args:
|
||||
params(list): a dict list, used to create some operators
|
||||
"""
|
||||
assert isinstance(
|
||||
op_param_list, list), ('operator config should be a list')
|
||||
ops = []
|
||||
for operator in op_param_list:
|
||||
assert isinstance(operator,
|
||||
dict) and len(operator) == 1, "yaml format error"
|
||||
op_name = list(operator)[0]
|
||||
param = {} if operator[op_name] is None else operator[op_name]
|
||||
if global_config is not None:
|
||||
param.update(global_config)
|
||||
op = eval(op_name)(**param)
|
||||
ops.append(op)
|
||||
return ops
|
||||
|
||||
|
||||
def draw_text_det_res(dt_boxes, img_path):
|
||||
src_im = cv2.imread(img_path)
|
||||
for box in dt_boxes:
|
||||
box = np.array(box).astype(np.int32).reshape(-1, 2)
|
||||
cv2.polylines(src_im, [box], True,
|
||||
color=(255, 255, 0), thickness=2)
|
||||
return src_im
|
||||
|
||||
|
||||
class DBPostProcess(object):
|
||||
"""
|
||||
The post process for Differentiable Binarization (DB).
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
thresh=0.3,
|
||||
box_thresh=0.7,
|
||||
max_candidates=1000,
|
||||
unclip_ratio=2.0,
|
||||
use_dilation=False,
|
||||
**kwargs):
|
||||
self.thresh = thresh
|
||||
self.box_thresh = box_thresh
|
||||
self.max_candidates = max_candidates
|
||||
self.unclip_ratio = unclip_ratio
|
||||
self.min_size = 3
|
||||
self.dilation_kernel = None if not use_dilation else np.array(
|
||||
[[1, 1], [1, 1]])
|
||||
|
||||
def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
|
||||
'''
|
||||
_bitmap: single map with shape (1, H, W),
|
||||
whose values are binarized as {0, 1}
|
||||
'''
|
||||
|
||||
bitmap = _bitmap
|
||||
height, width = bitmap.shape
|
||||
|
||||
outs = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST,
|
||||
cv2.CHAIN_APPROX_SIMPLE)
|
||||
if len(outs) == 3:
|
||||
img, contours, _ = outs[0], outs[1], outs[2]
|
||||
elif len(outs) == 2:
|
||||
contours, _ = outs[0], outs[1]
|
||||
|
||||
num_contours = min(len(contours), self.max_candidates)
|
||||
|
||||
boxes = []
|
||||
scores = []
|
||||
for index in range(num_contours):
|
||||
contour = contours[index]
|
||||
points, sside = self.get_mini_boxes(contour)
|
||||
if sside < self.min_size:
|
||||
continue
|
||||
points = np.array(points)
|
||||
score = self.box_score_fast(pred, points.reshape(-1, 2))
|
||||
if self.box_thresh > score:
|
||||
continue
|
||||
|
||||
box = self.unclip(points).reshape(-1, 1, 2)
|
||||
box, sside = self.get_mini_boxes(box)
|
||||
if sside < self.min_size + 2:
|
||||
continue
|
||||
box = np.array(box)
|
||||
|
||||
box[:, 0] = np.clip(
|
||||
np.round(box[:, 0] / width * dest_width), 0, dest_width)
|
||||
box[:, 1] = np.clip(
|
||||
np.round(box[:, 1] / height * dest_height), 0, dest_height)
|
||||
boxes.append(box.astype(np.int16))
|
||||
scores.append(score)
|
||||
return np.array(boxes, dtype=np.int16), scores
|
||||
|
||||
def unclip(self, box):
|
||||
unclip_ratio = self.unclip_ratio
|
||||
poly = Polygon(box)
|
||||
distance = poly.area * unclip_ratio / poly.length
|
||||
offset = pyclipper.PyclipperOffset()
|
||||
offset.AddPath(box, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
|
||||
expanded = np.array(offset.Execute(distance))
|
||||
return expanded
|
||||
|
||||
def get_mini_boxes(self, contour):
|
||||
bounding_box = cv2.minAreaRect(contour)
|
||||
points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
|
||||
|
||||
index_1, index_2, index_3, index_4 = 0, 1, 2, 3
|
||||
if points[1][1] > points[0][1]:
|
||||
index_1 = 0
|
||||
index_4 = 1
|
||||
else:
|
||||
index_1 = 1
|
||||
index_4 = 0
|
||||
if points[3][1] > points[2][1]:
|
||||
index_2 = 2
|
||||
index_3 = 3
|
||||
else:
|
||||
index_2 = 3
|
||||
index_3 = 2
|
||||
|
||||
box = [
|
||||
points[index_1], points[index_2], points[index_3], points[index_4]
|
||||
]
|
||||
return box, min(bounding_box[1])
|
||||
|
||||
def box_score_fast(self, bitmap, _box):
|
||||
h, w = bitmap.shape[:2]
|
||||
box = _box.copy()
|
||||
xmin = np.clip(np.floor(box[:, 0].min()).astype(np.int), 0, w - 1)
|
||||
xmax = np.clip(np.ceil(box[:, 0].max()).astype(np.int), 0, w - 1)
|
||||
ymin = np.clip(np.floor(box[:, 1].min()).astype(np.int), 0, h - 1)
|
||||
ymax = np.clip(np.ceil(box[:, 1].max()).astype(np.int), 0, h - 1)
|
||||
|
||||
mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)
|
||||
box[:, 0] = box[:, 0] - xmin
|
||||
box[:, 1] = box[:, 1] - ymin
|
||||
cv2.fillPoly(mask, box.reshape(1, -1, 2).astype(np.int32), 1)
|
||||
return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]
|
||||
|
||||
def __call__(self, pred, shape_list):
|
||||
pred = pred[:, 0, :, :]
|
||||
segmentation = pred > self.thresh
|
||||
|
||||
boxes_batch = []
|
||||
for batch_index in range(pred.shape[0]):
|
||||
src_h, src_w, ratio_h, ratio_w = shape_list[batch_index]
|
||||
if self.dilation_kernel is not None:
|
||||
mask = cv2.dilate(
|
||||
np.array(segmentation[batch_index]).astype(np.uint8),
|
||||
self.dilation_kernel)
|
||||
else:
|
||||
mask = segmentation[batch_index]
|
||||
boxes, scores = self.boxes_from_bitmap(pred[batch_index], mask,
|
||||
src_w, src_h)
|
||||
|
||||
boxes_batch.append({'points': boxes})
|
||||
return boxes_batch
|
||||
@@ -0,0 +1,6 @@
|
||||
# !/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
# @File: __init__.py
|
||||
# @Time: 2021/01/23 15:24:27
|
||||
# @Author: Max
|
||||
from .text_detect import TextDetector
|
||||
@@ -0,0 +1,9 @@
|
||||
#! /bin/bash
|
||||
set -e errexit
|
||||
|
||||
root_path=$(cd $(dirname $0); pwd)
|
||||
image_path=${root_path}"/test_images/det_images/1.jpg"
|
||||
model_path=${root_path}"/models/ch_ppocr_mobile_v2.0_det_infer.onnx"
|
||||
|
||||
python text_detect.py --image_path ${image_path} \
|
||||
--model_path ${model_path}
|
||||
@@ -0,0 +1,150 @@
|
||||
# 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.
|
||||
# !/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
import argparse
|
||||
import time
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from openvino.runtime import Core
|
||||
|
||||
try:
|
||||
from .utils import (DBPostProcess, check_and_read_gif, create_operators,
|
||||
draw_text_det_res, transform)
|
||||
except:
|
||||
from utils import (DBPostProcess, check_and_read_gif, create_operators,
|
||||
draw_text_det_res, transform)
|
||||
|
||||
|
||||
class TextDetector(object):
|
||||
def __init__(self, det_model_path):
|
||||
pre_process_list = [{
|
||||
'DetResizeForTest': {
|
||||
'limit_side_len': 736,
|
||||
'limit_type': 'min'
|
||||
}
|
||||
}, {
|
||||
'NormalizeImage': {
|
||||
'std': [0.229, 0.224, 0.225],
|
||||
'mean': [0.485, 0.456, 0.406],
|
||||
'scale': '1./255.',
|
||||
'order': 'hwc'
|
||||
}
|
||||
}, {
|
||||
'ToCHWImage': None
|
||||
}, {
|
||||
'KeepKeys': {
|
||||
'keep_keys': ['image', 'shape']
|
||||
}
|
||||
}]
|
||||
|
||||
self.preprocess_op = create_operators(pre_process_list)
|
||||
self.postprocess_op = DBPostProcess(thresh=0.3,
|
||||
box_thresh=0.5,
|
||||
max_candidates=1000,
|
||||
unclip_ratio=1.6,
|
||||
use_dilation=True)
|
||||
ie = Core()
|
||||
model_onnx = ie.read_model(det_model_path)
|
||||
compile_model = ie.compile_model(model=model_onnx,
|
||||
device_name='CPU')
|
||||
self.vino_session = compile_model.create_infer_request()
|
||||
|
||||
def order_points_clockwise(self, pts):
|
||||
"""
|
||||
reference from: https://github.com/jrosebr1/imutils/blob/master/imutils/perspective.py
|
||||
# sort the points based on their x-coordinates
|
||||
"""
|
||||
xSorted = pts[np.argsort(pts[:, 0]), :]
|
||||
|
||||
# grab the left-most and right-most points from the sorted
|
||||
# x-roodinate points
|
||||
leftMost = xSorted[:2, :]
|
||||
rightMost = xSorted[2:, :]
|
||||
|
||||
# now, sort the left-most coordinates according to their
|
||||
# y-coordinates so we can grab the top-left and bottom-left
|
||||
# points, respectively
|
||||
leftMost = leftMost[np.argsort(leftMost[:, 1]), :]
|
||||
(tl, bl) = leftMost
|
||||
|
||||
rightMost = rightMost[np.argsort(rightMost[:, 1]), :]
|
||||
(tr, br) = rightMost
|
||||
|
||||
rect = np.array([tl, tr, br, bl], dtype="float32")
|
||||
return rect
|
||||
|
||||
def clip_det_res(self, points, img_height, img_width):
|
||||
for pno in range(points.shape[0]):
|
||||
points[pno, 0] = int(min(max(points[pno, 0], 0), img_width - 1))
|
||||
points[pno, 1] = int(min(max(points[pno, 1], 0), img_height - 1))
|
||||
return points
|
||||
|
||||
def filter_tag_det_res(self, dt_boxes, image_shape):
|
||||
img_height, img_width = image_shape[0:2]
|
||||
dt_boxes_new = []
|
||||
for box in dt_boxes:
|
||||
box = self.order_points_clockwise(box)
|
||||
box = self.clip_det_res(box, img_height, img_width)
|
||||
rect_width = int(np.linalg.norm(box[0] - box[1]))
|
||||
rect_height = int(np.linalg.norm(box[0] - box[3]))
|
||||
if rect_width <= 3 or rect_height <= 3:
|
||||
continue
|
||||
dt_boxes_new.append(box)
|
||||
dt_boxes = np.array(dt_boxes_new)
|
||||
return dt_boxes
|
||||
|
||||
def __call__(self, img):
|
||||
ori_im = img.copy()
|
||||
data = {'image': img}
|
||||
data = transform(data, self.preprocess_op)
|
||||
img, shape_list = data
|
||||
if img is None:
|
||||
return None, 0
|
||||
img = np.expand_dims(img, axis=0)
|
||||
img = img.astype(np.float32)
|
||||
shape_list = np.expand_dims(shape_list, axis=0)
|
||||
|
||||
start_time = time.time()
|
||||
self.vino_session.infer(inputs=[img])
|
||||
vino_preds = self.vino_session.get_output_tensor().data
|
||||
|
||||
post_result = self.postprocess_op(vino_preds, shape_list)
|
||||
dt_boxes = post_result[0]['points']
|
||||
dt_boxes = self.filter_tag_det_res(dt_boxes, ori_im.shape)
|
||||
elapse = time.time() - start_time
|
||||
return dt_boxes, elapse
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--image_path', type=str, help='image_path|image_dir')
|
||||
parser.add_argument('--model_path', type=str, help='model_path')
|
||||
args = parser.parse_args()
|
||||
|
||||
text_detector = TextDetector(args.model_path)
|
||||
|
||||
img, flag = check_and_read_gif(args.image_path)
|
||||
if not flag:
|
||||
img = cv2.imread(args.image_path)
|
||||
if img is None:
|
||||
raise ValueError(f"error in loading image:{args.image_path}")
|
||||
|
||||
dt_boxes, elapse = text_detector(img)
|
||||
|
||||
src_im = draw_text_det_res(dt_boxes, args.image_path)
|
||||
cv2.imwrite('det_results.jpg', src_im)
|
||||
print(f'图像已经保存为det_results.jpg了\t{elapse:.6f}s')
|
||||
|
||||
@@ -0,0 +1,414 @@
|
||||
"""
|
||||
# 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.
|
||||
"""
|
||||
# coding:utf-8
|
||||
from __future__ import (absolute_import, division, print_function,
|
||||
unicode_literals)
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import pyclipper
|
||||
import six
|
||||
from shapely.geometry import Polygon
|
||||
|
||||
|
||||
class DecodeImage(object):
|
||||
""" decode image """
|
||||
|
||||
def __init__(self, img_mode='RGB', channel_first=False, **kwargs):
|
||||
self.img_mode = img_mode
|
||||
self.channel_first = channel_first
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
if six.PY2:
|
||||
assert type(img) is str and len(
|
||||
img) > 0, "invalid input 'img' in DecodeImage"
|
||||
else:
|
||||
assert type(img) is bytes and len(
|
||||
img) > 0, "invalid input 'img' in DecodeImage"
|
||||
img = np.frombuffer(img, dtype='uint8')
|
||||
img = cv2.imdecode(img, 1)
|
||||
if img is None:
|
||||
return None
|
||||
if self.img_mode == 'GRAY':
|
||||
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
|
||||
elif self.img_mode == 'RGB':
|
||||
assert img.shape[2] == 3, 'invalid shape of image[%s]' % (
|
||||
img.shape)
|
||||
img = img[:, :, ::-1]
|
||||
|
||||
if self.channel_first:
|
||||
img = img.transpose((2, 0, 1))
|
||||
|
||||
data['image'] = img
|
||||
return data
|
||||
|
||||
|
||||
class NormalizeImage(object):
|
||||
""" normalize image such as substract mean, divide std
|
||||
"""
|
||||
|
||||
def __init__(self, scale=None, mean=None, std=None, order='chw', **kwargs):
|
||||
if isinstance(scale, str):
|
||||
scale = eval(scale)
|
||||
self.scale = np.float32(scale if scale is not None else 1.0 / 255.0)
|
||||
mean = mean if mean is not None else [0.485, 0.456, 0.406]
|
||||
std = std if std is not None else [0.229, 0.224, 0.225]
|
||||
|
||||
shape = (3, 1, 1) if order == 'chw' else (1, 1, 3)
|
||||
self.mean = np.array(mean).reshape(shape).astype('float32')
|
||||
self.std = np.array(std).reshape(shape).astype('float32')
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
from PIL import Image
|
||||
if isinstance(img, Image.Image):
|
||||
img = np.array(img)
|
||||
|
||||
assert isinstance(img,
|
||||
np.ndarray), "invalid input 'img' in NormalizeImage"
|
||||
data['image'] = (
|
||||
img.astype('float32') * self.scale - self.mean) / self.std
|
||||
return data
|
||||
|
||||
|
||||
class ToCHWImage(object):
|
||||
""" convert hwc image to chw image
|
||||
"""
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
pass
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
from PIL import Image
|
||||
if isinstance(img, Image.Image):
|
||||
img = np.array(img)
|
||||
data['image'] = img.transpose((2, 0, 1))
|
||||
return data
|
||||
|
||||
|
||||
class KeepKeys(object):
|
||||
def __init__(self, keep_keys, **kwargs):
|
||||
self.keep_keys = keep_keys
|
||||
|
||||
def __call__(self, data):
|
||||
data_list = []
|
||||
for key in self.keep_keys:
|
||||
data_list.append(data[key])
|
||||
return data_list
|
||||
|
||||
|
||||
class DetResizeForTest(object):
|
||||
def __init__(self, **kwargs):
|
||||
super(DetResizeForTest, self).__init__()
|
||||
self.resize_type = 0
|
||||
if 'image_shape' in kwargs:
|
||||
self.image_shape = kwargs['image_shape']
|
||||
self.resize_type = 1
|
||||
elif 'limit_side_len' in kwargs:
|
||||
self.limit_side_len = kwargs['limit_side_len']
|
||||
self.limit_type = kwargs.get('limit_type', 'min')
|
||||
|
||||
if 'resize_long' in kwargs:
|
||||
self.resize_type = 2
|
||||
self.resize_long = kwargs.get('resize_long', 960)
|
||||
else:
|
||||
self.limit_side_len = 736
|
||||
self.limit_type = 'min'
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
src_h, src_w, _ = img.shape
|
||||
|
||||
if self.resize_type == 0:
|
||||
# img, shape = self.resize_image_type0(img)
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type0(img)
|
||||
elif self.resize_type == 2:
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type2(img)
|
||||
else:
|
||||
# img, shape = self.resize_image_type1(img)
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type1(img)
|
||||
data['image'] = img
|
||||
data['shape'] = np.array([src_h, src_w, ratio_h, ratio_w])
|
||||
return data
|
||||
|
||||
def resize_image_type1(self, img):
|
||||
resize_h, resize_w = self.image_shape
|
||||
ori_h, ori_w = img.shape[:2] # (h, w, c)
|
||||
ratio_h = float(resize_h) / ori_h
|
||||
ratio_w = float(resize_w) / ori_w
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
# return img, np.array([ori_h, ori_w])
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
def resize_image_type0(self, img):
|
||||
"""
|
||||
resize image to a size multiple of 32 which is required by the network
|
||||
args:
|
||||
img(array): array with shape [h, w, c]
|
||||
return(tuple):
|
||||
img, (ratio_h, ratio_w)
|
||||
"""
|
||||
limit_side_len = self.limit_side_len
|
||||
h, w, _ = img.shape
|
||||
|
||||
# limit the max side
|
||||
if self.limit_type == 'max':
|
||||
if max(h, w) > limit_side_len:
|
||||
if h > w:
|
||||
ratio = float(limit_side_len) / h
|
||||
else:
|
||||
ratio = float(limit_side_len) / w
|
||||
else:
|
||||
ratio = 1.
|
||||
else:
|
||||
if min(h, w) < limit_side_len:
|
||||
if h < w:
|
||||
ratio = float(limit_side_len) / h
|
||||
else:
|
||||
ratio = float(limit_side_len) / w
|
||||
else:
|
||||
ratio = 1.
|
||||
resize_h = int(h * ratio)
|
||||
resize_w = int(w * ratio)
|
||||
|
||||
resize_h = int(round(resize_h / 32) * 32)
|
||||
resize_w = int(round(resize_w / 32) * 32)
|
||||
|
||||
try:
|
||||
if int(resize_w) <= 0 or int(resize_h) <= 0:
|
||||
return None, (None, None)
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
except:
|
||||
print(img.shape, resize_w, resize_h)
|
||||
sys.exit(0)
|
||||
ratio_h = resize_h / float(h)
|
||||
ratio_w = resize_w / float(w)
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
def resize_image_type2(self, img):
|
||||
h, w, _ = img.shape
|
||||
|
||||
resize_w = w
|
||||
resize_h = h
|
||||
|
||||
# Fix the longer side
|
||||
if resize_h > resize_w:
|
||||
ratio = float(self.resize_long) / resize_h
|
||||
else:
|
||||
ratio = float(self.resize_long) / resize_w
|
||||
|
||||
resize_h = int(resize_h * ratio)
|
||||
resize_w = int(resize_w * ratio)
|
||||
|
||||
max_stride = 128
|
||||
resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
|
||||
resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
ratio_h = resize_h / float(h)
|
||||
ratio_w = resize_w / float(w)
|
||||
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
|
||||
def transform(data, ops=None):
|
||||
""" transform """
|
||||
if ops is None:
|
||||
ops = []
|
||||
for op in ops:
|
||||
data = op(data)
|
||||
if data is None:
|
||||
return None
|
||||
return data
|
||||
|
||||
|
||||
def check_and_read_gif(img_path):
|
||||
if os.path.basename(img_path)[-3:] in ['gif', 'GIF']:
|
||||
gif = cv2.VideoCapture(img_path)
|
||||
ret, frame = gif.read()
|
||||
if not ret:
|
||||
print("Cannot read {}. This gif image maybe corrupted.")
|
||||
return None, False
|
||||
if len(frame.shape) == 2 or frame.shape[-1] == 1:
|
||||
frame = cv2.cvtColor(frame, cv2.COLOR_GRAY2RGB)
|
||||
imgvalue = frame[:, :, ::-1]
|
||||
return imgvalue, True
|
||||
return None, False
|
||||
|
||||
|
||||
def create_operators(op_param_list, global_config=None):
|
||||
"""
|
||||
create operators based on the config
|
||||
|
||||
Args:
|
||||
params(list): a dict list, used to create some operators
|
||||
"""
|
||||
assert isinstance(
|
||||
op_param_list, list), ('operator config should be a list')
|
||||
ops = []
|
||||
for operator in op_param_list:
|
||||
assert isinstance(operator,
|
||||
dict) and len(operator) == 1, "yaml format error"
|
||||
op_name = list(operator)[0]
|
||||
param = {} if operator[op_name] is None else operator[op_name]
|
||||
if global_config is not None:
|
||||
param.update(global_config)
|
||||
op = eval(op_name)(**param)
|
||||
ops.append(op)
|
||||
return ops
|
||||
|
||||
|
||||
def draw_text_det_res(dt_boxes, img_path):
|
||||
src_im = cv2.imread(img_path)
|
||||
for box in dt_boxes:
|
||||
box = np.array(box).astype(np.int32).reshape(-1, 2)
|
||||
cv2.polylines(src_im, [box], True,
|
||||
color=(255, 255, 0), thickness=2)
|
||||
return src_im
|
||||
|
||||
|
||||
class DBPostProcess(object):
|
||||
"""
|
||||
The post process for Differentiable Binarization (DB).
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
thresh=0.3,
|
||||
box_thresh=0.7,
|
||||
max_candidates=1000,
|
||||
unclip_ratio=2.0,
|
||||
use_dilation=False,
|
||||
**kwargs):
|
||||
self.thresh = thresh
|
||||
self.box_thresh = box_thresh
|
||||
self.max_candidates = max_candidates
|
||||
self.unclip_ratio = unclip_ratio
|
||||
self.min_size = 3
|
||||
self.dilation_kernel = None if not use_dilation else np.array(
|
||||
[[1, 1], [1, 1]])
|
||||
|
||||
def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
|
||||
'''
|
||||
_bitmap: single map with shape (1, H, W),
|
||||
whose values are binarized as {0, 1}
|
||||
'''
|
||||
|
||||
bitmap = _bitmap
|
||||
height, width = bitmap.shape
|
||||
|
||||
outs = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST,
|
||||
cv2.CHAIN_APPROX_SIMPLE)
|
||||
if len(outs) == 3:
|
||||
img, contours, _ = outs[0], outs[1], outs[2]
|
||||
elif len(outs) == 2:
|
||||
contours, _ = outs[0], outs[1]
|
||||
|
||||
num_contours = min(len(contours), self.max_candidates)
|
||||
|
||||
boxes = []
|
||||
scores = []
|
||||
for index in range(num_contours):
|
||||
contour = contours[index]
|
||||
points, sside = self.get_mini_boxes(contour)
|
||||
if sside < self.min_size:
|
||||
continue
|
||||
points = np.array(points)
|
||||
score = self.box_score_fast(pred, points.reshape(-1, 2))
|
||||
if self.box_thresh > score:
|
||||
continue
|
||||
|
||||
box = self.unclip(points).reshape(-1, 1, 2)
|
||||
box, sside = self.get_mini_boxes(box)
|
||||
if sside < self.min_size + 2:
|
||||
continue
|
||||
box = np.array(box)
|
||||
|
||||
box[:, 0] = np.clip(
|
||||
np.round(box[:, 0] / width * dest_width), 0, dest_width)
|
||||
box[:, 1] = np.clip(
|
||||
np.round(box[:, 1] / height * dest_height), 0, dest_height)
|
||||
boxes.append(box.astype(np.int16))
|
||||
scores.append(score)
|
||||
return np.array(boxes, dtype=np.int16), scores
|
||||
|
||||
def unclip(self, box):
|
||||
unclip_ratio = self.unclip_ratio
|
||||
poly = Polygon(box)
|
||||
distance = poly.area * unclip_ratio / poly.length
|
||||
offset = pyclipper.PyclipperOffset()
|
||||
offset.AddPath(box, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
|
||||
expanded = np.array(offset.Execute(distance))
|
||||
return expanded
|
||||
|
||||
def get_mini_boxes(self, contour):
|
||||
bounding_box = cv2.minAreaRect(contour)
|
||||
points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
|
||||
|
||||
index_1, index_2, index_3, index_4 = 0, 1, 2, 3
|
||||
if points[1][1] > points[0][1]:
|
||||
index_1 = 0
|
||||
index_4 = 1
|
||||
else:
|
||||
index_1 = 1
|
||||
index_4 = 0
|
||||
if points[3][1] > points[2][1]:
|
||||
index_2 = 2
|
||||
index_3 = 3
|
||||
else:
|
||||
index_2 = 3
|
||||
index_3 = 2
|
||||
|
||||
box = [
|
||||
points[index_1], points[index_2], points[index_3], points[index_4]
|
||||
]
|
||||
return box, min(bounding_box[1])
|
||||
|
||||
def box_score_fast(self, bitmap, _box):
|
||||
h, w = bitmap.shape[:2]
|
||||
box = _box.copy()
|
||||
xmin = np.clip(np.floor(box[:, 0].min()).astype(np.int), 0, w - 1)
|
||||
xmax = np.clip(np.ceil(box[:, 0].max()).astype(np.int), 0, w - 1)
|
||||
ymin = np.clip(np.floor(box[:, 1].min()).astype(np.int), 0, h - 1)
|
||||
ymax = np.clip(np.ceil(box[:, 1].max()).astype(np.int), 0, h - 1)
|
||||
|
||||
mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)
|
||||
box[:, 0] = box[:, 0] - xmin
|
||||
box[:, 1] = box[:, 1] - ymin
|
||||
cv2.fillPoly(mask, box.reshape(1, -1, 2).astype(np.int32), 1)
|
||||
return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]
|
||||
|
||||
def __call__(self, pred, shape_list):
|
||||
pred = pred[:, 0, :, :]
|
||||
segmentation = pred > self.thresh
|
||||
|
||||
boxes_batch = []
|
||||
for batch_index in range(pred.shape[0]):
|
||||
src_h, src_w, ratio_h, ratio_w = shape_list[batch_index]
|
||||
if self.dilation_kernel is not None:
|
||||
mask = cv2.dilate(
|
||||
np.array(segmentation[batch_index]).astype(np.uint8),
|
||||
self.dilation_kernel)
|
||||
else:
|
||||
mask = segmentation[batch_index]
|
||||
boxes, scores = self.boxes_from_bitmap(pred[batch_index], mask,
|
||||
src_w, src_h)
|
||||
|
||||
boxes_batch.append({'points': boxes})
|
||||
return boxes_batch
|
||||
@@ -0,0 +1,6 @@
|
||||
# !/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
# @File: __init__.py
|
||||
# @Time: 2021/01/23 15:24:27
|
||||
# @Author: Max
|
||||
from .text_detect import TextDetector
|
||||
@@ -0,0 +1,9 @@
|
||||
#! /bin/bash
|
||||
set -e errexit
|
||||
|
||||
root_path=$(cd $(dirname $0); pwd)
|
||||
image_path=${root_path}"/test_images/det_images/1.jpg"
|
||||
model_path=${root_path}"/models/ch_ppocr_mobile_v2.0_det_infer.onnx"
|
||||
|
||||
python text_detect.py --image_path ${image_path} \
|
||||
--model_path ${model_path}
|
||||
@@ -0,0 +1,150 @@
|
||||
# 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.
|
||||
# !/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
import argparse
|
||||
import time
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from openvino.runtime import Core
|
||||
|
||||
try:
|
||||
from .utils import (DBPostProcess, check_and_read_gif, create_operators,
|
||||
draw_text_det_res, transform)
|
||||
except:
|
||||
from utils import (DBPostProcess, check_and_read_gif, create_operators,
|
||||
draw_text_det_res, transform)
|
||||
|
||||
|
||||
class TextDetector(object):
|
||||
def __init__(self, det_model_path):
|
||||
pre_process_list = [{
|
||||
'DetResizeForTest': {
|
||||
'limit_side_len': 736,
|
||||
'limit_type': 'min'
|
||||
}
|
||||
}, {
|
||||
'NormalizeImage': {
|
||||
'std': [0.229, 0.224, 0.225],
|
||||
'mean': [0.485, 0.456, 0.406],
|
||||
'scale': '1./255.',
|
||||
'order': 'hwc'
|
||||
}
|
||||
}, {
|
||||
'ToCHWImage': None
|
||||
}, {
|
||||
'KeepKeys': {
|
||||
'keep_keys': ['image', 'shape']
|
||||
}
|
||||
}]
|
||||
|
||||
self.preprocess_op = create_operators(pre_process_list)
|
||||
self.postprocess_op = DBPostProcess(thresh=0.3,
|
||||
box_thresh=0.5,
|
||||
max_candidates=1000,
|
||||
unclip_ratio=1.6,
|
||||
use_dilation=True)
|
||||
ie = Core()
|
||||
model_onnx = ie.read_model(det_model_path)
|
||||
compile_model = ie.compile_model(model=model_onnx,
|
||||
device_name='CPU')
|
||||
self.vino_session = compile_model.create_infer_request()
|
||||
|
||||
def order_points_clockwise(self, pts):
|
||||
"""
|
||||
reference from: https://github.com/jrosebr1/imutils/blob/master/imutils/perspective.py
|
||||
# sort the points based on their x-coordinates
|
||||
"""
|
||||
xSorted = pts[np.argsort(pts[:, 0]), :]
|
||||
|
||||
# grab the left-most and right-most points from the sorted
|
||||
# x-roodinate points
|
||||
leftMost = xSorted[:2, :]
|
||||
rightMost = xSorted[2:, :]
|
||||
|
||||
# now, sort the left-most coordinates according to their
|
||||
# y-coordinates so we can grab the top-left and bottom-left
|
||||
# points, respectively
|
||||
leftMost = leftMost[np.argsort(leftMost[:, 1]), :]
|
||||
(tl, bl) = leftMost
|
||||
|
||||
rightMost = rightMost[np.argsort(rightMost[:, 1]), :]
|
||||
(tr, br) = rightMost
|
||||
|
||||
rect = np.array([tl, tr, br, bl], dtype="float32")
|
||||
return rect
|
||||
|
||||
def clip_det_res(self, points, img_height, img_width):
|
||||
for pno in range(points.shape[0]):
|
||||
points[pno, 0] = int(min(max(points[pno, 0], 0), img_width - 1))
|
||||
points[pno, 1] = int(min(max(points[pno, 1], 0), img_height - 1))
|
||||
return points
|
||||
|
||||
def filter_tag_det_res(self, dt_boxes, image_shape):
|
||||
img_height, img_width = image_shape[0:2]
|
||||
dt_boxes_new = []
|
||||
for box in dt_boxes:
|
||||
box = self.order_points_clockwise(box)
|
||||
box = self.clip_det_res(box, img_height, img_width)
|
||||
rect_width = int(np.linalg.norm(box[0] - box[1]))
|
||||
rect_height = int(np.linalg.norm(box[0] - box[3]))
|
||||
if rect_width <= 3 or rect_height <= 3:
|
||||
continue
|
||||
dt_boxes_new.append(box)
|
||||
dt_boxes = np.array(dt_boxes_new)
|
||||
return dt_boxes
|
||||
|
||||
def __call__(self, img):
|
||||
ori_im = img.copy()
|
||||
data = {'image': img}
|
||||
data = transform(data, self.preprocess_op)
|
||||
img, shape_list = data
|
||||
if img is None:
|
||||
return None, 0
|
||||
img = np.expand_dims(img, axis=0)
|
||||
img = img.astype(np.float32)
|
||||
shape_list = np.expand_dims(shape_list, axis=0)
|
||||
|
||||
start_time = time.time()
|
||||
self.vino_session.infer(inputs=[img])
|
||||
vino_preds = self.vino_session.get_output_tensor().data
|
||||
|
||||
post_result = self.postprocess_op(vino_preds, shape_list)
|
||||
dt_boxes = post_result[0]['points']
|
||||
dt_boxes = self.filter_tag_det_res(dt_boxes, ori_im.shape)
|
||||
elapse = time.time() - start_time
|
||||
return dt_boxes, elapse
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--image_path', type=str, help='image_path|image_dir')
|
||||
parser.add_argument('--model_path', type=str, help='model_path')
|
||||
args = parser.parse_args()
|
||||
|
||||
text_detector = TextDetector(args.model_path)
|
||||
|
||||
img, flag = check_and_read_gif(args.image_path)
|
||||
if not flag:
|
||||
img = cv2.imread(args.image_path)
|
||||
if img is None:
|
||||
raise ValueError(f"error in loading image:{args.image_path}")
|
||||
|
||||
dt_boxes, elapse = text_detector(img)
|
||||
|
||||
src_im = draw_text_det_res(dt_boxes, args.image_path)
|
||||
cv2.imwrite('det_results.jpg', src_im)
|
||||
print(f'图像已经保存为det_results.jpg了\t{elapse:.6f}s')
|
||||
|
||||
@@ -0,0 +1,414 @@
|
||||
"""
|
||||
# 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.
|
||||
"""
|
||||
# coding:utf-8
|
||||
from __future__ import (absolute_import, division, print_function,
|
||||
unicode_literals)
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import pyclipper
|
||||
import six
|
||||
from shapely.geometry import Polygon
|
||||
|
||||
|
||||
class DecodeImage(object):
|
||||
""" decode image """
|
||||
|
||||
def __init__(self, img_mode='RGB', channel_first=False, **kwargs):
|
||||
self.img_mode = img_mode
|
||||
self.channel_first = channel_first
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
if six.PY2:
|
||||
assert type(img) is str and len(
|
||||
img) > 0, "invalid input 'img' in DecodeImage"
|
||||
else:
|
||||
assert type(img) is bytes and len(
|
||||
img) > 0, "invalid input 'img' in DecodeImage"
|
||||
img = np.frombuffer(img, dtype='uint8')
|
||||
img = cv2.imdecode(img, 1)
|
||||
if img is None:
|
||||
return None
|
||||
if self.img_mode == 'GRAY':
|
||||
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
|
||||
elif self.img_mode == 'RGB':
|
||||
assert img.shape[2] == 3, 'invalid shape of image[%s]' % (
|
||||
img.shape)
|
||||
img = img[:, :, ::-1]
|
||||
|
||||
if self.channel_first:
|
||||
img = img.transpose((2, 0, 1))
|
||||
|
||||
data['image'] = img
|
||||
return data
|
||||
|
||||
|
||||
class NormalizeImage(object):
|
||||
""" normalize image such as substract mean, divide std
|
||||
"""
|
||||
|
||||
def __init__(self, scale=None, mean=None, std=None, order='chw', **kwargs):
|
||||
if isinstance(scale, str):
|
||||
scale = eval(scale)
|
||||
self.scale = np.float32(scale if scale is not None else 1.0 / 255.0)
|
||||
mean = mean if mean is not None else [0.485, 0.456, 0.406]
|
||||
std = std if std is not None else [0.229, 0.224, 0.225]
|
||||
|
||||
shape = (3, 1, 1) if order == 'chw' else (1, 1, 3)
|
||||
self.mean = np.array(mean).reshape(shape).astype('float32')
|
||||
self.std = np.array(std).reshape(shape).astype('float32')
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
from PIL import Image
|
||||
if isinstance(img, Image.Image):
|
||||
img = np.array(img)
|
||||
|
||||
assert isinstance(img,
|
||||
np.ndarray), "invalid input 'img' in NormalizeImage"
|
||||
data['image'] = (
|
||||
img.astype('float32') * self.scale - self.mean) / self.std
|
||||
return data
|
||||
|
||||
|
||||
class ToCHWImage(object):
|
||||
""" convert hwc image to chw image
|
||||
"""
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
pass
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
from PIL import Image
|
||||
if isinstance(img, Image.Image):
|
||||
img = np.array(img)
|
||||
data['image'] = img.transpose((2, 0, 1))
|
||||
return data
|
||||
|
||||
|
||||
class KeepKeys(object):
|
||||
def __init__(self, keep_keys, **kwargs):
|
||||
self.keep_keys = keep_keys
|
||||
|
||||
def __call__(self, data):
|
||||
data_list = []
|
||||
for key in self.keep_keys:
|
||||
data_list.append(data[key])
|
||||
return data_list
|
||||
|
||||
|
||||
class DetResizeForTest(object):
|
||||
def __init__(self, **kwargs):
|
||||
super(DetResizeForTest, self).__init__()
|
||||
self.resize_type = 0
|
||||
if 'image_shape' in kwargs:
|
||||
self.image_shape = kwargs['image_shape']
|
||||
self.resize_type = 1
|
||||
elif 'limit_side_len' in kwargs:
|
||||
self.limit_side_len = kwargs['limit_side_len']
|
||||
self.limit_type = kwargs.get('limit_type', 'min')
|
||||
|
||||
if 'resize_long' in kwargs:
|
||||
self.resize_type = 2
|
||||
self.resize_long = kwargs.get('resize_long', 960)
|
||||
else:
|
||||
self.limit_side_len = 736
|
||||
self.limit_type = 'min'
|
||||
|
||||
def __call__(self, data):
|
||||
img = data['image']
|
||||
src_h, src_w, _ = img.shape
|
||||
|
||||
if self.resize_type == 0:
|
||||
# img, shape = self.resize_image_type0(img)
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type0(img)
|
||||
elif self.resize_type == 2:
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type2(img)
|
||||
else:
|
||||
# img, shape = self.resize_image_type1(img)
|
||||
img, [ratio_h, ratio_w] = self.resize_image_type1(img)
|
||||
data['image'] = img
|
||||
data['shape'] = np.array([src_h, src_w, ratio_h, ratio_w])
|
||||
return data
|
||||
|
||||
def resize_image_type1(self, img):
|
||||
resize_h, resize_w = self.image_shape
|
||||
ori_h, ori_w = img.shape[:2] # (h, w, c)
|
||||
ratio_h = float(resize_h) / ori_h
|
||||
ratio_w = float(resize_w) / ori_w
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
# return img, np.array([ori_h, ori_w])
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
def resize_image_type0(self, img):
|
||||
"""
|
||||
resize image to a size multiple of 32 which is required by the network
|
||||
args:
|
||||
img(array): array with shape [h, w, c]
|
||||
return(tuple):
|
||||
img, (ratio_h, ratio_w)
|
||||
"""
|
||||
limit_side_len = self.limit_side_len
|
||||
h, w, _ = img.shape
|
||||
|
||||
# limit the max side
|
||||
if self.limit_type == 'max':
|
||||
if max(h, w) > limit_side_len:
|
||||
if h > w:
|
||||
ratio = float(limit_side_len) / h
|
||||
else:
|
||||
ratio = float(limit_side_len) / w
|
||||
else:
|
||||
ratio = 1.
|
||||
else:
|
||||
if min(h, w) < limit_side_len:
|
||||
if h < w:
|
||||
ratio = float(limit_side_len) / h
|
||||
else:
|
||||
ratio = float(limit_side_len) / w
|
||||
else:
|
||||
ratio = 1.
|
||||
resize_h = int(h * ratio)
|
||||
resize_w = int(w * ratio)
|
||||
|
||||
resize_h = int(round(resize_h / 32) * 32)
|
||||
resize_w = int(round(resize_w / 32) * 32)
|
||||
|
||||
try:
|
||||
if int(resize_w) <= 0 or int(resize_h) <= 0:
|
||||
return None, (None, None)
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
except:
|
||||
print(img.shape, resize_w, resize_h)
|
||||
sys.exit(0)
|
||||
ratio_h = resize_h / float(h)
|
||||
ratio_w = resize_w / float(w)
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
def resize_image_type2(self, img):
|
||||
h, w, _ = img.shape
|
||||
|
||||
resize_w = w
|
||||
resize_h = h
|
||||
|
||||
# Fix the longer side
|
||||
if resize_h > resize_w:
|
||||
ratio = float(self.resize_long) / resize_h
|
||||
else:
|
||||
ratio = float(self.resize_long) / resize_w
|
||||
|
||||
resize_h = int(resize_h * ratio)
|
||||
resize_w = int(resize_w * ratio)
|
||||
|
||||
max_stride = 128
|
||||
resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
|
||||
resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
|
||||
img = cv2.resize(img, (int(resize_w), int(resize_h)))
|
||||
ratio_h = resize_h / float(h)
|
||||
ratio_w = resize_w / float(w)
|
||||
|
||||
return img, [ratio_h, ratio_w]
|
||||
|
||||
|
||||
def transform(data, ops=None):
|
||||
""" transform """
|
||||
if ops is None:
|
||||
ops = []
|
||||
for op in ops:
|
||||
data = op(data)
|
||||
if data is None:
|
||||
return None
|
||||
return data
|
||||
|
||||
|
||||
def check_and_read_gif(img_path):
|
||||
if os.path.basename(img_path)[-3:] in ['gif', 'GIF']:
|
||||
gif = cv2.VideoCapture(img_path)
|
||||
ret, frame = gif.read()
|
||||
if not ret:
|
||||
print("Cannot read {}. This gif image maybe corrupted.")
|
||||
return None, False
|
||||
if len(frame.shape) == 2 or frame.shape[-1] == 1:
|
||||
frame = cv2.cvtColor(frame, cv2.COLOR_GRAY2RGB)
|
||||
imgvalue = frame[:, :, ::-1]
|
||||
return imgvalue, True
|
||||
return None, False
|
||||
|
||||
|
||||
def create_operators(op_param_list, global_config=None):
|
||||
"""
|
||||
create operators based on the config
|
||||
|
||||
Args:
|
||||
params(list): a dict list, used to create some operators
|
||||
"""
|
||||
assert isinstance(
|
||||
op_param_list, list), ('operator config should be a list')
|
||||
ops = []
|
||||
for operator in op_param_list:
|
||||
assert isinstance(operator,
|
||||
dict) and len(operator) == 1, "yaml format error"
|
||||
op_name = list(operator)[0]
|
||||
param = {} if operator[op_name] is None else operator[op_name]
|
||||
if global_config is not None:
|
||||
param.update(global_config)
|
||||
op = eval(op_name)(**param)
|
||||
ops.append(op)
|
||||
return ops
|
||||
|
||||
|
||||
def draw_text_det_res(dt_boxes, img_path):
|
||||
src_im = cv2.imread(img_path)
|
||||
for box in dt_boxes:
|
||||
box = np.array(box).astype(np.int32).reshape(-1, 2)
|
||||
cv2.polylines(src_im, [box], True,
|
||||
color=(255, 255, 0), thickness=2)
|
||||
return src_im
|
||||
|
||||
|
||||
class DBPostProcess(object):
|
||||
"""
|
||||
The post process for Differentiable Binarization (DB).
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
thresh=0.3,
|
||||
box_thresh=0.7,
|
||||
max_candidates=1000,
|
||||
unclip_ratio=2.0,
|
||||
use_dilation=False,
|
||||
**kwargs):
|
||||
self.thresh = thresh
|
||||
self.box_thresh = box_thresh
|
||||
self.max_candidates = max_candidates
|
||||
self.unclip_ratio = unclip_ratio
|
||||
self.min_size = 3
|
||||
self.dilation_kernel = None if not use_dilation else np.array(
|
||||
[[1, 1], [1, 1]])
|
||||
|
||||
def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
|
||||
'''
|
||||
_bitmap: single map with shape (1, H, W),
|
||||
whose values are binarized as {0, 1}
|
||||
'''
|
||||
|
||||
bitmap = _bitmap
|
||||
height, width = bitmap.shape
|
||||
|
||||
outs = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST,
|
||||
cv2.CHAIN_APPROX_SIMPLE)
|
||||
if len(outs) == 3:
|
||||
img, contours, _ = outs[0], outs[1], outs[2]
|
||||
elif len(outs) == 2:
|
||||
contours, _ = outs[0], outs[1]
|
||||
|
||||
num_contours = min(len(contours), self.max_candidates)
|
||||
|
||||
boxes = []
|
||||
scores = []
|
||||
for index in range(num_contours):
|
||||
contour = contours[index]
|
||||
points, sside = self.get_mini_boxes(contour)
|
||||
if sside < self.min_size:
|
||||
continue
|
||||
points = np.array(points)
|
||||
score = self.box_score_fast(pred, points.reshape(-1, 2))
|
||||
if self.box_thresh > score:
|
||||
continue
|
||||
|
||||
box = self.unclip(points).reshape(-1, 1, 2)
|
||||
box, sside = self.get_mini_boxes(box)
|
||||
if sside < self.min_size + 2:
|
||||
continue
|
||||
box = np.array(box)
|
||||
|
||||
box[:, 0] = np.clip(
|
||||
np.round(box[:, 0] / width * dest_width), 0, dest_width)
|
||||
box[:, 1] = np.clip(
|
||||
np.round(box[:, 1] / height * dest_height), 0, dest_height)
|
||||
boxes.append(box.astype(np.int16))
|
||||
scores.append(score)
|
||||
return np.array(boxes, dtype=np.int16), scores
|
||||
|
||||
def unclip(self, box):
|
||||
unclip_ratio = self.unclip_ratio
|
||||
poly = Polygon(box)
|
||||
distance = poly.area * unclip_ratio / poly.length
|
||||
offset = pyclipper.PyclipperOffset()
|
||||
offset.AddPath(box, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
|
||||
expanded = np.array(offset.Execute(distance))
|
||||
return expanded
|
||||
|
||||
def get_mini_boxes(self, contour):
|
||||
bounding_box = cv2.minAreaRect(contour)
|
||||
points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
|
||||
|
||||
index_1, index_2, index_3, index_4 = 0, 1, 2, 3
|
||||
if points[1][1] > points[0][1]:
|
||||
index_1 = 0
|
||||
index_4 = 1
|
||||
else:
|
||||
index_1 = 1
|
||||
index_4 = 0
|
||||
if points[3][1] > points[2][1]:
|
||||
index_2 = 2
|
||||
index_3 = 3
|
||||
else:
|
||||
index_2 = 3
|
||||
index_3 = 2
|
||||
|
||||
box = [
|
||||
points[index_1], points[index_2], points[index_3], points[index_4]
|
||||
]
|
||||
return box, min(bounding_box[1])
|
||||
|
||||
def box_score_fast(self, bitmap, _box):
|
||||
h, w = bitmap.shape[:2]
|
||||
box = _box.copy()
|
||||
xmin = np.clip(np.floor(box[:, 0].min()).astype(np.int), 0, w - 1)
|
||||
xmax = np.clip(np.ceil(box[:, 0].max()).astype(np.int), 0, w - 1)
|
||||
ymin = np.clip(np.floor(box[:, 1].min()).astype(np.int), 0, h - 1)
|
||||
ymax = np.clip(np.ceil(box[:, 1].max()).astype(np.int), 0, h - 1)
|
||||
|
||||
mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)
|
||||
box[:, 0] = box[:, 0] - xmin
|
||||
box[:, 1] = box[:, 1] - ymin
|
||||
cv2.fillPoly(mask, box.reshape(1, -1, 2).astype(np.int32), 1)
|
||||
return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]
|
||||
|
||||
def __call__(self, pred, shape_list):
|
||||
pred = pred[:, 0, :, :]
|
||||
segmentation = pred > self.thresh
|
||||
|
||||
boxes_batch = []
|
||||
for batch_index in range(pred.shape[0]):
|
||||
src_h, src_w, ratio_h, ratio_w = shape_list[batch_index]
|
||||
if self.dilation_kernel is not None:
|
||||
mask = cv2.dilate(
|
||||
np.array(segmentation[batch_index]).astype(np.uint8),
|
||||
self.dilation_kernel)
|
||||
else:
|
||||
mask = segmentation[batch_index]
|
||||
boxes, scores = self.boxes_from_bitmap(pred[batch_index], mask,
|
||||
src_w, src_h)
|
||||
|
||||
boxes_batch.append({'points': boxes})
|
||||
return boxes_batch
|
||||
@@ -0,0 +1,59 @@
|
||||
# !/usr/bin/env python
|
||||
# -*- encoding: utf-8 -*-
|
||||
# @File: test_openvino.py
|
||||
# @Author: SWHL
|
||||
# @Contact: liekkaskono@163.com
|
||||
import numpy as np
|
||||
|
||||
# Infer ONNXRuntime
|
||||
# import cv2
|
||||
|
||||
# from ch_ppocr_mobile_v2_det import TextDetector
|
||||
|
||||
# det_model_path = 'models/ch_PP-OCRv2_det_infer.onnx'
|
||||
|
||||
# img_path = 'test_images/long1.jpg'
|
||||
# img = cv2.imread(img_path)
|
||||
|
||||
# text_detect_onnx = TextDetector(det_model_path)
|
||||
# dt_boxes, elapse = text_detect_onnx(img)
|
||||
# print(f'onnxruntime: {elapse}')
|
||||
|
||||
|
||||
# # Infer ONNX
|
||||
# import cv2
|
||||
# from ch_ppocr_mobile_v2_det_openvino_onnx import TextDetector as TextDetectorVino
|
||||
|
||||
# det_model_path = 'models/ch_PP-OCRv2_det_infer.onnx'
|
||||
# img_path = 'test_images/det_images/ch_en_num.jpg'
|
||||
# img = cv2.imread(img_path)
|
||||
|
||||
# text_detect_vino = TextDetectorVino(det_model_path)
|
||||
# dt_boxes, elapse = text_detect_vino(img)
|
||||
# print(f'openvino ONNX: {elapse}\tdt_boxes:{np.mean(dt_boxes)}')
|
||||
|
||||
# # Infer IR
|
||||
import cv2
|
||||
from ch_ppocr_mobile_v2_det_openvino_ir import TextDetector as TextDetectorIR
|
||||
|
||||
det_model_path = 'models/IR/FP16/ch_PP-OCRv2_det_infer.xml'
|
||||
img_path = 'test_images/long1.jpg'
|
||||
img = cv2.imread(img_path)
|
||||
|
||||
text_detect_ir = TextDetectorIR(det_model_path)
|
||||
dt_boxes, elapse = text_detect_ir(img)
|
||||
print(f'FP16 openvino IR: {elapse}\tdt_boxes:{np.mean(dt_boxes)}')
|
||||
|
||||
# Infer paddle 有误
|
||||
# RuntimeError: Can't SetBlob with name: x, because model input (shape={?,3,960,960}) and blob (shape=(1.3.12128.800)) are incompatible
|
||||
# import cv2
|
||||
# from ch_ppocr_mobile_v2_det_openvino_paddle import TextDetector as TextDetectorPaddle
|
||||
|
||||
# det_model_path = 'models/ch_PP-OCRv2_det_infer/ch_PP-OCRv2_det_infer/inference.pdmodel'
|
||||
# img_path = 'test_images/long1.jpg'
|
||||
# img = cv2.imread(img_path)
|
||||
|
||||
# text_detect_ir = TextDetectorPaddle(det_model_path)
|
||||
# dt_boxes, elapse = text_detect_ir(img)
|
||||
# print(f'openvino IR: {elapse}')
|
||||
|
||||
Reference in new issue
Block a user