You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: demo/multi-model-exec/README.md
+34-1Lines changed: 34 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -74,6 +74,8 @@ This is the demo of showing multiple AI models running concurrently on Ryzen AI.
74
74
75
75
Make sure you have met all the requirements by following the [Installation Instructions](https://ryzenai.docs.amd.com/en/latest/inst.html#).
76
76
77
+
For step-by-step procedure for installing dependencies and building the demo from the source code following the [Multi Model instructions](../../example/multi-model/README.md)
78
+
77
79
Download the onnx models and test image/video package, and unzip it under **<path_to_RyzenAI-SW>/demo/multi-model-exec/npu_modelsx4_demo/**
78
80
79
81
@@ -129,23 +131,54 @@ Download the onnx models and test image/video package, and unzip it under **<pat
129
131
## 4 Run The Demo
130
132
131
133
Please note that all the steps mentioned here need to be performed in ***Windows CMD Prompt***. You can load and run the models one by one:
134
+
135
+
Run the MobileNet V2 based classification model:
136
+
137
+
```bash
138
+
cd npu_modelsx4_demo
132
139
run_mobile_net_v2.bat
140
+
```
133
141
134
142

135
143
144
+
Run the ResNet50 based classification model:
145
+
146
+
```bash
136
147
run_resnet50.bat
148
+
```
149
+
137
150

151
+
152
+
Run the RetinaFace model for face detection:
153
+
154
+
```bash
138
155
run_retinaface.bat
156
+
```
157
+
139
158

159
+
160
+
Run the segmentation model:
161
+
162
+
```bash
140
163
run_segmentation.bat
164
+
```
165
+
141
166

142
167
168
+
Run the YOLO based object detection model:
169
+
170
+
```bash
143
171
run_yolovx.bat
172
+
```
173
+
144
174

145
175
146
-
or you can load and run multiple models at the same time:
176
+
or you can load and run multiple models at the same time:
0 commit comments