AI Rank
EN
← 开源
JiahuiYu

slimmable_networks

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
927
Star
135
Fork
+0
本周
1
贡献者
创建于 2018-11-21 · 更新于 2026-09-19 · 今日第 12589 名
主要开发者
JiahuiYu

JiahuiYu/slimmable_networks 排名第 12,589，有 927 个星标。

同类别比较

JiahuiYu/slimmable_networks 排名第 12,589，此处有 8 个同类条目；microsoft/tf-gnn-samples 排名第 12,588。

同类别比较
名称排名指标
YyzHarry/imbalanced-regression12,578
语言:
Python
星标数:
929
分叉数:
149
简介:
[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
microsoft/maro12,581
语言:
Python
星标数:
929
分叉数:
160
简介:
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
awslabs/fortuna12,586
语言:
Python
星标数:
928
分叉数:
55
简介:
A Library for Uncertainty Quantification.
microsoft/tf-gnn-samples12,588
语言:
Python
星标数:
928
分叉数:
224
简介:
TensorFlow implementations of Graph Neural Networks
deepdrive/deepdrive12,593
语言:
Python
星标数:
926
分叉数:
147
简介:
Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
NorskRegnesentral/skweak12,595
语言:
Python
星标数:
925
分叉数:
76
简介:
skweak: A software toolkit for weak supervision applied to NLP tasks
hzy46/Char-RNN-TensorFlow12,599
语言:
Python
星标数:
925
分叉数:
421
简介:
Multi-language Char RNN for TensorFlow >= 1.2.
carpedm20/BEGAN-tensorflow12,605
语言:
Python
星标数:
924
分叉数:
229
简介:
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
星标数927
分叉数135
贡献者1
创建日期2018-11-21
更新日期2026-09-19
1 天星标数0
7 天星标数0
排名12,589
上次排名12,507
排名变化-82
7 天星标排名13,497
上次 7 天星标排名13,507
7 天星标排名变化10
总星标排名11,799
上次总星标排名11,782
总星标排名变化-17
国家China
README 摘录

Slimmable Networks An open source framework for slimmable training on tasks of ImageNet classification and COCO detection, which has enabled numerous projects. Slimmable Neural Networks ICLR 2019 Paper | OpenReview | Detection | Model Zoo Illustration of slimmable neural networks. The same model can run at different widths (number of active channels), permitting instant and adaptive accuracy-efficiency trade-offs. Universally Slimmable Networks and Improved Training Techniques ICCV 2019 Paper | Model Zoo Illustration of universally slimmable networks. The same model can run at

**arbitrary** widths. AutoSlim: Towards One-Shot Architecture Search for Channel Numbers NeurIPS 2019 Workshop Paper | Model Zoo AutoSlimming MobileNet v1, MobileNet v2, MNasNet and ResNet-50: the optimized number of channels under **each** computational budget (FLOPs). Slimmable Model Zoo **Slimmable Neural Networks** | Model | Switches (Widths) | Top-1 Err. 9 | 569M 325M 150M 41M | a6285db | | S-MobileNet v2 | 1. 3 | 301M 209M 97M 59M | 0593ffd | | S-ShuffleNet | 2. 8 | 524M 138M 38M | 1427f66 | | S-ResNet-50 | 1. 1G 278M | 3fca9cc | **Universally

Slimmable Networks and Improved Training Techniques** | Model | Model ID | Spectrum | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | :- | :-: | :- | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | US‑MobileNet v1 | 13d5af2 | Width MFLOPs Top-1 Err. 3 | | US‑MobileNet v2 | 3880cad | Width MFLOPs Top-1 Err. 7 | **AutoSlim: Towards One-Shot Architecture Search for Channel Numbers** | Model | Top-1 Err. 1 | 572M 325M 150M | 9b0b1ab | | AutoSlim-MobileNet v2 | 24. 0 | 505M 305M 207M | a24f1f2 | | AutoSlim-MNasNet | 24. 8 | 532M 315M 217M | 31477c9 | | AutoSlim-ResNet-50 | 24. 0G 570M | f95f419 | Technical Details Implementing

slimmable networks and slimmable training is straightforward: Switchable batchnorm and slimmable layers are implemented in . Slimmable training is implemented in these lines in . 0 Attribution-NonCommercial International The software is for educaitonal and academic research purpose only.

常见问题

记录了多少星标和分叉？

JiahuiYu/slimmable_networks 有 927 个星标和 135 个分叉。

仓库排名是多少？

JiahuiYu/slimmable_networks 排名第 12,589。

记录的语言和类别是什么？

JiahuiYu/slimmable_networks 有 927 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

JiahuiYu/slimmable_networks 与 microsoft/tf-gnn-samples 比较，后者排名第 12,588，有 928 个星标。

README

Slimmable Networks

An open source framework for slimmable training on tasks of ImageNet classification and COCO detection, which has enabled numerous projects. 1, 2, 3

  1. Slimmable Neural Networks ICLR 2019 Paper | OpenReview | Detection | Model Zoo

Illustration of slimmable neural networks. The same model can run at different widths (number of active channels), permitting instant and adaptive accuracy-efficiency trade-offs.

  1. Universally Slimmable Networks and Improved Training Techniques ICCV 2019 Paper | Model Zoo

Illustration of universally slimmable networks. The same model can run at arbitrary widths.

  1. AutoSlim: Towards One-Shot Architecture Search for Channel Numbers NeurIPS 2019 Workshop Paper | Model Zoo

AutoSlimming MobileNet v1, MobileNet v2, MNasNet and ResNet-50: the optimized number of channels under each computational budget (FLOPs).

Run

  1. Requirements:
    • python3, pytorch 1.0, torchvision 0.2.1, pyyaml 3.13.
    • Prepare ImageNet-1k data following pytorch example.
  2. Training and Testing:
    • The codebase is a general ImageNet training framework using yaml config under apps dir, based on PyTorch.
    • To test, download pretrained models to logs dir and directly run command.
    • To train, comment test_only and pretrained in config file. You will need to manage visible gpus by yourself.
    • Command: python train.py app:{apps/***.yml}. {apps/***.yml} is config file. Do not miss app: prefix.
    • Training and testing of MSCOCO benchmarks are released under branch detection.
  3. Still have questions?
    • If you still have questions, please search closed issues first. If the problem is not solved, please open a new.

Slimmable Model Zoo

Slimmable Neural Networks

Model Switches (Widths) Top-1 Err. FLOPs Model ID
S-MobileNet v1 1.00
0.75
0.50
0.25 28.5
30.5
35.2
46.9 569M
325M
150M
41M a6285db
S-MobileNet v2 1.00
0.75
0.50
0.35 29.5
31.1
35.6
40.3 301M
209M
97M
59M 0593ffd
S-ShuffleNet 2.00
1.00
0.50 28.6
34.5
42.8 524M
138M
38M 1427f66
S-ResNet-50 1.00
0.75
0.50
0.25 24.0
25.1
27.9
35.0 4.1G
2.3G
1.1G
278M 3fca9cc

Universally Slimmable Networks and Improved Training Techniques

Model Model ID Spectrum
US‑MobileNet v1 13d5af2 Width
MFLOPs
Top-1 Err. 1.0
568
28.2 0.975
543
28.3 0.95
517
28.4 0.925
490
28.7 0.9
466
28.7 0.875
443
29.1 0.85
421
29.4 0.825
389
29.7 0.8
366
30.2 0.775
345
30.3 0.75
325
30.5 0.725
306
30.9 0.7
287
31.2 0.675
267
31.7 0.65
249
32.2 0.625
232
32.5 0.6
217
33.2 0.575
201
33.7 0.55
177
34.4 0.525
162
35.0 0.5
149
35.8 0.475
136
36.5 0.45
124
37.3 0.425
114
38.1 0.4
100
39.0 0.375
89
40.0 0.35
80
41.0 0.325
71
41.9 0.3
64
42.7 0.275
48
44.2 0.25
41
44.3
US‑MobileNet v2 3880cad Width
MFLOPs
Top-1 Err. 1.0
300
28.5 0.975
299
28.5 0.95
284
28.8 0.925
274
28.9 0.9
269
29.1 0.875
268
29.1 0.85
254
29.4 0.825
235
29.9 0.8
222
30.0 0.775
213
30.2 0.75
209
30.4 0.725
185
30.7 0.7
173
31.1 0.675
165
31.4 0.65
161
31.7 0.625
161
31.7 0.6
151
32.4 0.575
150
32.4 0.55
106
34.4 0.525
100
34.6 0.5
97
34.9 0.475
96
35.1 0.45
88
35.8 0.425
88
35.8 0.4
80
36.6 0.375
80
36.7 0.35
59
37.7

AutoSlim: Towards One-Shot Architecture Search for Channel Numbers

Model Top-1 Err. FLOPs Model ID
AutoSlim-MobileNet v1 27.0
28.5
32.1 572M
325M
150M 9b0b1ab
AutoSlim-MobileNet v2 24.6
25.8
27.0 505M
305M
207M a24f1f2
AutoSlim-MNasNet 24.6
25.4
26.8 532M
315M
217M 31477c9
AutoSlim-ResNet-50 24.0
24.4
26.0
27.8 3.0G
2.0G
1.0G
570M f95f419

Technical Details

Implementing slimmable networks and slimmable training is straightforward:

License

CC 4.0 Attribution-NonCommercial International

The software is for educaitonal and academic research purpose only.

排名相邻
同类项目