README.md 1.85 KB
Newer Older
liucong's avatar
liucong committed
1
2
3
4
5
6
7
8
9
10
# ResNet50

## 模型介绍
使用MIGraphX推理框架对ResNet50模型进行推理。

## 模型结构
ResNet50模型包含了49个卷积层、一个全连接层。

## Python版本推理

liucong's avatar
liucong committed
11
下面介绍如何运行Python代码示例,Python示例的详细说明见Doc目录下的Tutorial_Python.md。
liucong's avatar
liucong committed
12

liucong's avatar
liucong committed
13
### 下载镜像
liucong's avatar
liucong committed
14

liucong's avatar
liucong committed
15
在光源中下载MIGraphX镜像: 
liucong's avatar
liucong committed
16
17
18
19
20

```python
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
```

liucong's avatar
liucong committed
21
### 设置Python环境变量
liucong's avatar
liucong committed
22

liucong's avatar
liucong committed
23
24
25
```
export PYTHONPATH=/opt/dtk/lib:$PYTHONPATH
```
liucong's avatar
liucong committed
26

liucong's avatar
liucong committed
27
### 安装依赖
liucong's avatar
liucong committed
28
29

```python
liucong's avatar
liucong committed
30
# 进入resnet50 migraphx工程根目录
liucong's avatar
liucong committed
31
cd <path_to_resnet50_migraphx> 
liucong's avatar
liucong committed
32
33
34
35
36
37
38
39

# 进入示例程序目录
cd Python/

# 安装依赖
pip install -r requirements.txt
```

liucong's avatar
liucong committed
40
41
### 运行示例

liucong's avatar
liucong committed
42
执行如下示例,输出分类结果。
liucong's avatar
liucong committed
43
44
45
46
47
48
49

```python
python Classifier.py
```

## C++版本推理

liucong's avatar
liucong committed
50
51
52
53
54
下面介绍如何运行C++代码示例,C++示例的详细说明见Doc目录下的Tutorial_Cpp.md。

### 下载镜像

在光源中下载MIGraphX镜像: 
liucong's avatar
liucong committed
55

liucong's avatar
liucong committed
56
57
58
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:ort1.14.0_migraphx3.0.0-dtk22.10.1
```
liucong's avatar
liucong committed
59
60
61
62

### 安装Opencv依赖

```python
liucong's avatar
liucong committed
63
cd <path_to_resnet50_migraphx>
liucong's avatar
liucong committed
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
sh ./3rdParty/InstallOpenCVDependences.sh
```


### 安装OpenCV并构建工程

```
rbuild build -d depend
```

### 设置环境变量

将依赖库依赖加入环境变量LD_LIBRARY_PATH,在~/.bashrc中添加如下语句:

```
liucong's avatar
liucong committed
79
export LD_LIBRARY_PATH=<path_to_resnet50_migraphx>/depend/lib64/:$LD_LIBRARY_PATH
liucong's avatar
liucong committed
80
81
82
83
84
85
86
87
```

然后执行:

```
source ~/.bashrc
```

liucong's avatar
liucong committed
88
### 运行示例
liucong's avatar
liucong committed
89
90

```python
liucong's avatar
liucong committed
91
# 进入resnet50 migraphx工程根目录
liucong's avatar
liucong committed
92
cd <path_to_resnet50_migraphx> 
liucong's avatar
liucong committed
93
94

# 进入build目录
liucong's avatar
liucong committed
95
cd build/
liucong's avatar
liucong committed
96
97
98
99
100

# 执行示例程序
./ResNet50
```

liucong's avatar
liucong committed
101
## 源码仓库及问题反馈
liucong's avatar
liucong committed
102

liucong's avatar
liucong committed
103
https://developer.hpccube.com/codes/modelzoo/resnet50_migraphx
liucong's avatar
liucong committed
104

liucong's avatar
liucong committed
105
## 参考
liucong's avatar
liucong committed
106

liucong's avatar
liucong committed
107
https://github.com/onnx/models/tree/main/vision/classification/resnet
liucong's avatar
liucong committed
108