update decompress codes and figures

README.md

@@ -1,8 +1,11 @@
-# Searching for A Robust Neural Architecture in Four GPU Hours
+## Searching for A Robust Neural Architecture in Four GPU Hours
 
 We propose A Gradient-based neural architecture search approach using Differentiable Architecture Sampler (GDAS).
 
-## Requirements
+<img src="data/GDAS.png" width="520">
+Figure-1. We utilize a DAG to represent the search space of a neural cell. Different operations (colored arrows) transform one node (square) to its intermediate features (little circles). Meanwhile, each node is the sum of the intermediate features transformed from the previous nodes. As indicated by the solid connections, the neural cell in the proposed GDAS is a sampled sub-graph of this DAG. Specifically, among the intermediate features between every two nodes, GDAS samples one feature in a differentiable way.
+
+### Requirements
 - PyTorch 1.0.1
 - Python 3.6
 - opencv
@@ -10,7 +13,7 @@ We propose A Gradient-based neural architecture search approach using Differenti
 conda install pytorch torchvision cuda100 -c pytorch
 ```
 
-## Usages
+### Usages
 
 Train the searched CNN on CIFAR
 ```
@@ -41,10 +44,14 @@ CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-WT2.sh DARTS_V2
 CUDA_VISIBLE_DEVICES=0 bash ./scripts-rnn/train-WT2.sh GDAS
 ```
 
-## Training Logs
+### Training Logs
 Some training logs can be found in `./data/logs/`, and some pre-trained models can be found in [Google Driver](https://drive.google.com/open?id=1Ofhc49xC1PLIX4O708gJZ1ugzz4td_RJ).
 
-## Citation
+### Experimental Results
+<img src="data/imagenet-results.png" width="600">
+Figure 2. Top-1 and top-5 errors on ImageNet.
+
+### Citation
 ```
 @inproceedings{dong2019search,
   title={Searching for A Robust Neural Architecture in Four GPU Hours},