# tf_meter_parse

**Repository Path**: hstarlive/tf_meter_parse

## Basic Information

- **Project Name**: tf_meter_parse
- **Description**: 基于神经网络的远程抄表终端
- **Primary Language**: C++
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 2
- **Forks**: 0
- **Created**: 2020-09-08
- **Last Updated**: 2024-03-03

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## 基于神经网络的远程抄表终端

### 平台参数
神经网络框架：TensorFlow 2.2  
处理器：i.MX 6ULL（Cortex®-A7 单核 792MHz）  
RAM: 512MB  
FLASH: 8GB eMMC 

### 识别测试
为了方便模块维护和及进程间相互调用，采用HTTP接口，Python示例：
```python
import requests
import base64

#板卡地址
url = 'http://x.x.x.x:x/img'

fd = open("00623.jpg", 'rb')
img = fd.read()
base64_encrypt = base64.b64encode(img)
post_data = {'img': str(base64_encrypt, 'utf-8')}

r = requests.post(url, json=post_data)
print(r.status_code)
print(r.text)

```

识别效果：  
![](./img/00639.png)  
![](./img/00623.png)


### 依赖项目


[opencv](https://github.com/opencv/opencv.git "opencv")  
[tensorflow](https://github.com/tensorflow/tensorflow.git "tensorflow")  
[cpp-httplib](https://github.com/yhirose/cpp-httplib.git "cpp-httplib")  
[spdlog](https://github.com/gabime/spdlog.git "spdlog")  
[yaml-cpp](https://github.com/jbeder/yaml-cpp.git "yaml-cpp")  
[json](https://github.com/nlohmann/json.git "json")