Merge branch 'master' of https://github.com/mit-han-lab/proxylessnas

Author: han-cai

search/README.md

@@ -19,21 +19,21 @@
 
 Without any proxy, directly and efficiently search neural network architectures on your target **task** and **hardware**! 
 
-![](assets/proxyless_nas.png)
+![](../assets/proxyless_nas.png)
 
 <p align="center">
-    <img src="assets/proxyless_bar.png" width="80%" />
+    <img src="../assets/proxyless_bar.png" width="80%" />
 </p>
 
-![](assets/proxyless_compare.png)
+![](../assets/proxyless_compare.png)
 
 <table>
 <tr>
     <th> Mobile settings </th><th> GPU settings </th>
 </tr>
 <tr>
     <td>
-    <img src="assets/proxyless_vs_mobilenet.png" width="100%" />
+    <img src="../assets/proxyless_vs_mobilenet.png" width="100%" />
     </td>
 <td>
 
@@ -59,8 +59,8 @@ Without any proxy, directly and efficiently search neural network architectures
 
 People used to deploy one model to all platforms, but this is not good. To fully exploit the efficiency, we should specialize architectures for each platform.
 
-![](assets/specialization.jpg)
-[![Watch the video](assets/specialized_archs.png)](assets/visualization.mp4)
+![](../assets/specialization.jpg)
+[![Watch the video](../assets/specialized_archs.png)](../assets/visualization.mp4)
 
 ## Requirements
 - Pytorch 1.0
@@ -100,4 +100,4 @@ python imagenet_run_exp.py --path Exp/proxyless_mobile_14 --net proxyless_mobile
 ```bash
 # Architecture Search
 please refer to imagenet_arch_search.py
-```
+```