iicd/autodl-projects
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update typos

Browse Source
This commit is contained in:
D-X-Y 2020-10-07 17:50:59 -07:00
parent ab801cbf14
commit 45ce442058
2 changed files with 5 additions and 5 deletions
exps/NATS-algos
search-size.py
lib/models/shape_searchs
generic_size_tiny_cell_model.py

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

@ -1,13 +1,13 @@
################################################## ##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2020 # # Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2020 #
###################################################################################### ###########################################################################################################################################
# In this file, we aims to evaluate three kinds of channel searching strategies: # 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" # - channel-wise interpolation 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 + 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" # - 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: # 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 # - TAS: https://github.com/D-X-Y/AutoDL-Projects/blob/master/docs/NeurIPS-2019-TAS.md
# - FBV2: https://github.com/facebookresearch/mobile-vision # - FBNetV2: https://github.com/facebookresearch/mobile-vision
# - TuNAS: https://github.com/google-research/google-research/tree/master/tunas # - 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 # 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
@ -23,7 +23,7 @@
# python ./exps/NATS-algos/search-size.py --dataset cifar10 --data_path $TORCH_HOME/cifar.python --algo tunas --arch_weight_decay 0 --rand_seed 777 --use_api 0 # python ./exps/NATS-algos/search-size.py --dataset cifar10 --data_path $TORCH_HOME/cifar.python --algo tunas --arch_weight_decay 0 --rand_seed 777 --use_api 0
# python ./exps/NATS-algos/search-size.py --dataset cifar100 --data_path $TORCH_HOME/cifar.python --algo tunas --arch_weight_decay 0 --rand_seed 777 # python ./exps/NATS-algos/search-size.py --dataset cifar100 --data_path $TORCH_HOME/cifar.python --algo tunas --arch_weight_decay 0 --rand_seed 777
# python ./exps/NATS-algos/search-size.py --dataset ImageNet16-120 --data_path $TORCH_HOME/cifar.python/ImageNet16 --algo tunas --arch_weight_decay 0 --rand_seed 777 # python ./exps/NATS-algos/search-size.py --dataset ImageNet16-120 --data_path $TORCH_HOME/cifar.python/ImageNet16 --algo tunas --arch_weight_decay 0 --rand_seed 777
###################################################################################### ###########################################################################################################################################
import os, sys, time, random, argparse import os, sys, time, random, argparse
import numpy as np import numpy as np
from copy import deepcopy from copy import deepcopy

2
lib/models/shape_searchs/generic_size_tiny_cell_model.py
View File

@ -2,7 +2,7 @@
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.01 # # Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.01 #
##################################################### #####################################################
# Here, we utilized three techniques to search for the number of channels: # Here, we utilized three techniques to search for the number of channels:
# - channel-wise interpaltion from "Network Pruning via Transformable Architecture Search, NeurIPS 2019" # - channel-wise interpolation 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 + 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" # - masking + sampling from "Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNAS, CVPR 2020"
from typing import List, Text, Any from typing import List, Text, Any