Skip to content

Pytorch implementation of "Designing Network Design Spaces" (CVPR 2020)

License

Notifications You must be signed in to change notification settings

iVishalr/RegNetX

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RegNet

Designing Network Design Spaces

Pytorch Implementation of "Desigining Network Design Spaces", Radosavovic et al. CVPR 2020.

Paper | Official Implementation

RegNet offer a very nice design space for neural network architectures. RegNet design space consists of networks with simple structure which authors call "Regular" Networks (RegNet). Models in RegNet design space have higher concentration of models that perform well and generalise well. RegNet models are very efficient and run upto 5 times faster than EfficientNet models on GPUs.

Also RegNet models have been used as a backbone in Tesla FSD Stack.

Overview Of AnyNet

  • Main goal of the paper is to help in better understanding of network design and discover principles that generalize across settings.
  • Explore structure aspeck of network design and arrive at low dimensional design space consisting of simple regualar networks
  • Network width and depth can be explained by a quantized linear function.

AnyNet Design Space

The basic structure of models in AnyNet design space consists of a simple Stem which is then followed by the network body that does majority of the computation and a final network head that predicts the class scores. The stem and head networks are kept as simple as possible. The network body consists of 4 stages that operate at progressively lower resolutions.

AnyNet

Structure of network body is determined by block width w, network depth d_i, bottleneck ratio b_i and group widths g. Degrees of freedom at stage 'i' are number of blocks d in each stage, block width w and other block parameters such as stride, padding and so on.

Other models are obtained by refining the design space by adding more constraints on the above parameters. Design space is refined keeping the following things in mind :

  • Simplify structure of design space.
  • Improve the interpretability of design space.
  • Maintain Design space complexity.
  • Maintain model diversity in design space.

AnyNetX

XBlock

  • Uses XBlocks within each block of the network
  • Degrees of freedom in AnyNetX is 16
  • Each network has 4 stages
  • Each stage has 4 parameters (network depth di, block width wi, bottleneck ratio bi, group width gi)
  • bi ∈ {1,2,4}
  • gi ∈ {1,2,3,...,32}
  • wi <= 1024
  • di <= 16

AnyNetX(A)

AnyNetX(A) is same as the above AnyNetX

AnyNetX(B)

In this design space,

  • bottleneck ratio bi is fixed for all stages.
  • performance of models in AnyNetX(B) space is almost equal to AnyNetX(A) in average and best case senarios
  • bi <= 2 seemes to work best.

AnyNetX(C)

In this design space,

  • Shared group width gi for all stages.
  • AnyNetX(C) has 6 fewer degrees of freedom compared to AnyNetX(A)
  • gi > 1 seems to work best

AnyNetX(D)

In AnyNetX(D) design space, authors observed that good networks have increasing stage widths w(i+1) > wi

AnyNetX(E)

In AnyNetX(E) design space, it was observed that as stage widths wi increases, depth di likewise tend to increase except for the last stage.

RegNet

Please refer to Section 3.3 in paper.

Training

Import any of the following variants of RegNet using

from regnet import regnetx_002 as RegNet002
from regnet import Xblock, Yblock # required if you want to use YBlock instead of Xblock. Refer to paper for more details on YBlock

RegNet variants available are:

  • regnetx_002
  • regnetx_004
  • regnetx_006
  • regnetx_008
  • regnetx_016
  • regnetx_032
  • regnetx_040
  • regnetx_064
  • regnetx_080
  • regnetx_120
  • regnetx_160
  • regnetx_320

Import TrainingConfig and Trainer Classes from regnet and use them to train the model as follows

from regnet import TrainingConfig, Trainer

model = RegNet002(block=Xblock, num_classes=10)

training_config = TrainingConfig(max_epochs=10, batch_size=128, learning_rate=3e-4, weight_decay=5e-4, ckpt_path="./regnet.pt")
trainer = Trainer(model = model, train_dataset=train_dataset, test_dataset=test_dataset, configs=training_config)
trainer.train()

Note : you need not use TrainingConfig and Trainer classes if you want to write your own training loops. Just importing the respective models would suffice.

TODO

  • Implement model checkpointing for every 'x' epochs

References

[1] https://github.com/signatrix/regnet

[2] https://github.com/d-li14/regnet.pytorch

@InProceedings{Radosavovic2020,
  title = {Designing Network Design Spaces},
  author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{\'a}r},
  booktitle = {CVPR},
  year = {2020}
}

LICENSE

MIT

About

Pytorch implementation of "Designing Network Design Spaces" (CVPR 2020)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published