iicd/xautodl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update Warmup

Browse Source
This commit is contained in:
D-X-Y
2020-10-08 10:19:34 +11:00
parent ad5d6e28b9
commit ab801cbf14
7 changed files with 90 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
exps/NATS-algos/search-size.py
View File

@@ -2,7 +2,13 @@
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2020 #
######################################################################################
# In this file, we aims to evaluate three kinds of channel searching strategies:
# -
# - channel-wise interpaltion from "Network Pruning via Transformable Architecture Search, NeurIPS 2019"
# - masking + Gumbel-Softmax from "FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions, CVPR 2020"
# - masking + sampling from "Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS, CVPR 2020"
# For simplicity, we use tas, fbv2, and tunas to refer these three strategies. Their official implementations are at the following links:
# - TAS: https://github.com/D-X-Y/AutoDL-Projects/blob/master/docs/NeurIPS-2019-TAS.md
# - FBV2: https://github.com/facebookresearch/mobile-vision
# - TuNAS: https://github.com/google-research/google-research/tree/master/tunas
####
# python ./exps/NATS-algos/search-size.py --dataset cifar10 --data_path $TORCH_HOME/cifar.python --algo tunas --arch_weight_decay 0 --warmup_ratio 0.25
####