From 1d5e7c0995df26edf15efb5a9c2acea63a5d2c19 Mon Sep 17 00:00:00 2001
From: D-X-Y <280835372@qq.com>
Date: Sat, 5 Oct 2019 15:21:23 +1000
Subject: [PATCH] update README
---
README.md | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/README.md b/README.md
index 7c2f4af..a23067c 100644
--- a/README.md
+++ b/README.md
@@ -17,8 +17,12 @@ Some methods use knowledge distillation (KD), which require pre-trained models.
## [Network Pruning via Transformable Architecture Search](https://arxiv.org/abs/1905.09717)
In this paper, we proposed a differentiable searching strategy for transformable architectures, i.e., searching for the depth and width of a deep neural network.
+You could see the highlight of our Transformable Architecture Search (TAS) at our [project page](https://xuanyidong.com/assets/projects/NeurIPS-2019-TAS.html).
-
+
+
+
+
### Usage
@@ -46,9 +50,10 @@ args: `cifar10` indicates the dataset name, `ResNet56` indicates the basemodel n
## One-Shot Neural Architecture Search via Self-Evaluated Template Network
+
+
Highlight: we equip one-shot NAS with an architecture sampler and train network weights using uniformly sampling.
-
### Usage
@@ -64,9 +69,10 @@ Searching codes come soon!
## [Searching for A Robust Neural Architecture in Four GPU Hours](http://openaccess.thecvf.com/content_CVPR_2019/papers/Dong_Searching_for_a_Robust_Neural_Architecture_in_Four_GPU_Hours_CVPR_2019_paper.pdf)
-We proposed a gradient-based searching algorithm using differentiable architecture sampling (improving DARTS with Gumbel-softmax sampling).
-
+
+
+We proposed a gradient-based searching algorithm using differentiable architecture sampling (improving DARTS with Gumbel-softmax sampling).
The old version is located at [`others/GDAS`](https://github.com/D-X-Y/NAS-Projects/tree/master/others/GDAS) and a paddlepaddle implementation is locate at [`others/paddlepaddle`](https://github.com/D-X-Y/NAS-Projects/tree/master/others/paddlepaddle).