Made English README.MD to default

This commit is contained in:
Heiko J Schick
2020-10-26 16:28:11 +01:00
parent 7d08608009
commit 4e3f349792
3 changed files with 53 additions and 53 deletions
+15 -13
View File
@@ -1,38 +1,40 @@
中文|[英文](README_EN.md)
EN|[CH](README.md)
# tools
#### 介绍
#### introduce
Ascend tools,昇腾工具仓库。
Ascend tools
**Please go to the corresponding folder to get the tool according to your needs, or click the link below to select the tool you need to use.**
**请根据自己的需要进入对应文件夹获取工具,或者点击下面的说明链接选择需要的工具进行使用。**
#### 使用说明
#### explain
1. [msame](https://gitee.com/ascend/tools/tree/master/msame)
**模型推理工具**:输入.om模型和模型所需要的输入bin文件,输出模型的输出数据文件。
**Model reasoning tool**:Input. Om model and model required input bin file, output model output data file.
2. [img2bin](https://gitee.com/ascend/tools/tree/master/img2bin)
**bin文件生成工具**:生成模型推理所需的输入数据,以.bin格式保存。
**Bin file generation tool** : Generates input data required for model reasoning, saved in.bin format.
3. [makesd](https://gitee.com/ascend/tools/tree/master/makesd)
**制卡工具**:制卡工具包,提供ubuntu下制卡功能。
**makesd tool**makesd tools packageProvide card making function under ubuntu.
4. [faster_install](https://gitee.com/ascend/tools/tree/master/faster_install)
**快速安装脚本**:环境快速安装脚本。
**faster_install**environment fast install script.
5. [configure_usb_ethernet](https://gitee.com/ascend/tools/tree/master/configure_usb_ethernet)
**USB虚拟网卡连接脚本**:配置USB网卡对应的IP地址
**configure_usb_ethernet**configuring the IP address of the USB NIC
6. [pt2pb](https://gitee.com/ascend/tools/tree/master/pt2pb)
**pytorch模型转tensorflow pb模型工具**:输入pytorch权重参数模型,转为onnx,再转为pb模型
**pytorch model transform to tensorflow pb model tool**input pytorch weights parameters modeltransform to onnx filethen transform to pb model
7. [dnmetis](https://gitee.com/ascend/tools/tree/master/dnmetis)
**NPU推理精度和性能测试工具**:使用Python封装ACL的C++接口,输入om模型和原始数据集图片、标签,即可执行模型推理,输出精度数据和性能数据
**Test tool for NPU inference precision and performance**Using Python to encapsulate the C++ interface of ACL, inputting om model and original dataset images and tags, we can execute model inference and give out precision and performance of the om model