CondenseNet: Light weighted CNN for mobile devices

Overview

CondenseNets

This repository contains the code (in PyTorch) for "CondenseNet: An Efficient DenseNet using Learned Group Convolutions" paper by Gao Huang*, Shichen Liu*, Laurens van der Maaten and Kilian Weinberger (* Authors contributed equally).

Citation

If you find our project useful in your research, please consider citing:

@inproceedings{huang2018condensenet,
  title={Condensenet: An efficient densenet using learned group convolutions},
  author={Huang, Gao and Liu, Shichen and Van der Maaten, Laurens and Weinberger, Kilian Q},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={2752--2761},
  year={2018}
}

Contents

  1. Introduction
  2. Usage
  3. Results
  4. Discussions
  5. Contacts

Introduction

CondenseNet is a novel, computationally efficient convolutional network architecture. It combines dense connectivity between layers with a mechanism to remove unused connections. The dense connectivity facilitates feature re-use in the network, whereas learned group convolutions remove connections between layers for which this feature re-use is superfluous. At test time, our model can be implemented using standard grouped convolutions —- allowing for efficient computation in practice. Our experiments demonstrate that CondenseNets are much more efficient than other compact convolutional networks such as MobileNets and ShuffleNets.

Figure 1: Learned Group Convolution with G=C=3.

Figure 2: CondenseNets with Fully Dense Connectivity and Increasing Growth Rate.

Usage

Dependencies

Train

As an example, use the following command to train a CondenseNet on ImageNet

python main.py --model condensenet -b 256 -j 20 /PATH/TO/IMAGENET \
--stages 4-6-8-10-8 --growth 8-16-32-64-128 --gpu 0,1,2,3,4,5,6,7 --resume

As another example, use the following command to train a CondenseNet on CIFAR-10

python main.py --model condensenet -b 64 -j 12 cifar10 \
--stages 14-14-14 --growth 8-16-32 --gpu 0 --resume

Evaluation

We take the ImageNet model trained above as an example.

To evaluate the trained model, use evaluate to evaluate from the default checkpoint directory:

python main.py --model condensenet -b 64 -j 20 /PATH/TO/IMAGENET \
--stages 4-6-8-10-8 --growth 8-16-32-64-128 --gpu 0 --resume \
--evaluate

or use evaluate-from to evaluate from an arbitrary path:

python main.py --model condensenet -b 64 -j 20 /PATH/TO/IMAGENET \
--stages 4-6-8-10-8 --growth 8-16-32-64-128 --gpu 0 --resume \
--evaluate-from /PATH/TO/BEST/MODEL

Note that these models are still the large models. To convert the model to group-convolution version as described in the paper, use the convert-from function:

python main.py --model condensenet -b 64 -j 20 /PATH/TO/IMAGENET \
--stages 4-6-8-10-8 --growth 8-16-32-64-128 --gpu 0 --resume \
--convert-from /PATH/TO/BEST/MODEL

Finally, to directly load from a converted model (that is, a CondenseNet), use a converted model file in combination with the evaluate-from option:

python main.py --model condensenet_converted -b 64 -j 20 /PATH/TO/IMAGENET \
--stages 4-6-8-10-8 --growth 8-16-32-64-128 --gpu 0 --resume \
--evaluate-from /PATH/TO/CONVERTED/MODEL

Other Options

We also include DenseNet implementation in this repository.
For more examples of usage, please refer to script.sh
For detailed options, please python main.py --help

Results

Results on ImageNet

Model FLOPs Params Top-1 Err. Top-5 Err. Pytorch Model
CondenseNet-74 (C=G=4) 529M 4.8M 26.2 8.3 Download (18.69M)
CondenseNet-74 (C=G=8) 274M 2.9M 29.0 10.0 Download (11.68M)

Results on CIFAR

Model FLOPs Params CIFAR-10 CIFAR-100
CondenseNet-50 28.6M 0.22M 6.22 -
CondenseNet-74 51.9M 0.41M 5.28 -
CondenseNet-86 65.8M 0.52M 5.06 23.64
CondenseNet-98 81.3M 0.65M 4.83 -
CondenseNet-110 98.2M 0.79M 4.63 -
CondenseNet-122 116.7M 0.95M 4.48 -
CondenseNet-182* 513M 4.2M 3.76 18.47

(* trained 600 epochs)

Inference time on ARM platform

Model FLOPs Top-1 Time(s)
VGG-16 15,300M 28.5 354
ResNet-18 1,818M 30.2 8.14
1.0 MobileNet-224 569M 29.4 1.96
CondenseNet-74 (C=G=4) 529M 26.2 1.89
CondenseNet-74 (C=G=8) 274M 29.0 0.99

Contact

[email protected]
[email protected]

We are working on the implementation on other frameworks.
Any discussions or concerns are welcomed!

Owner
Shichen Liu
PhD student at USC
Shichen Liu
PG2Net: Personalized and Group PreferenceGuided Network for Next Place Prediction

PG2Net PG2Net:Personalized and Group Preference Guided Network for Next Place Prediction Datasets Experiment results on two Foursquare check-in datase

Urban Mobility 5 Dec 20, 2022
PyTorch implementation of "Continual Learning with Deep Generative Replay", NIPS 2017

pytorch-deep-generative-replay PyTorch implementation of Continual Learning with Deep Generative Replay, NIPS 2017 Results Continual Learning on Permu

Junsoo Ha 127 Dec 14, 2022
An addon uses SMPL's poses and global translation to drive cartoon character in Blender.

Blender addon for driving character The addon drives the cartoon character by passing SMPL's poses and global translation into model's armature in Ble

犹在镜中 153 Dec 14, 2022
Square Root Bundle Adjustment for Large-Scale Reconstruction

RootBA: Square Root Bundle Adjustment Project Page | Paper | Poster | Video | Code Table of Contents Citation Dependencies Installing dependencies on

Nikolaus Demmel 205 Dec 20, 2022
Neural Tangent Generalization Attacks (NTGA)

Neural Tangent Generalization Attacks (NTGA) ICML 2021 Video | Paper | Quickstart | Results | Unlearnable Datasets | Competitions | Citation Overview

Chia-Hung Yuan 34 Nov 25, 2022
Robust Partial Matching for Person Search in the Wild

APNet for Person Search Introduction This is the code of Robust Partial Matching for Person Search in the Wild accepted in CVPR2020. The Align-to-Part

Yingji Zhong 36 Dec 18, 2022
Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.

AI Choreographer: Music Conditioned 3D Dance Generation with AIST++ [ICCV-2021]. Overview This package contains the model implementation and training

Google Research 365 Dec 30, 2022
A Pytorch implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE

SMU_pytorch A Pytorch Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE arXiv https://arxiv.org/ab

Fuhang 36 Dec 24, 2022
The code for two papers: Feedback Transformer and Expire-Span.

transformer-sequential This repo contains the code for two papers: Feedback Transformer Expire-Span The training code is structured for long sequentia

Facebook Research 125 Dec 25, 2022
data/code repository of "C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer"

C2F-FWN data/code repository of "C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer" (https://arxiv.org/abs/

EKILI 46 Dec 14, 2022
Creating predictive checklists from data using integer programming.

Learning Optimal Predictive Checklists A Python package to learn simple predictive checklists from data subject to customizable constraints. For more

Healthy ML 5 Apr 19, 2022
Customised to detect objects automatically by a given model file(onnx)

LabelImg LabelImg is a graphical image annotation tool. It is written in Python and uses Qt for its graphical interface. Annotations are saved as XML

Heeone Lee 1 Jun 07, 2022
Official implementation of VaxNeRF (Voxel-Accelearated NeRF).

VaxNeRF Paper | Google Colab This is the official implementation of VaxNeRF (Voxel-Accelearated NeRF). VaxNeRF provides very fast training and slightl

naruya 132 Nov 21, 2022
Pseudo-rng-app - whos needs science to make a random number when you have pseudoscience?

Pseudo-random numbers with pseudoscience rng is so complicated! Why cant we have a horoscopic, vibe-y way of calculating a random number? Why cant rng

Andrew Blance 1 Dec 27, 2021
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition Usage First, install PyTorch 1.7.1+, torchvision 0.8.2

40 Dec 12, 2022
A library of scripts that interact with the PythonTurtle module to create games, drawings, and more

TurtleLib TurtleLib is a library of scripts that interact with the PythonTurtle module to create games, drawings, and more! Using the Scripts Copy or

1 Jan 15, 2022
Official implementation of the paper ``Unifying Nonlocal Blocks for Neural Networks'' (ICCV'21)

Spectral Nonlocal Block Overview Official implementation of the paper: Unifying Nonlocal Blocks for Neural Networks (ICCV'21) Spectral View of Nonloca

91 Dec 14, 2022
Official Repsoitory for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]

Mish: Self Regularized Non-Monotonic Activation Function BMVC 2020 (Official Paper) Notes: (Click to expand) A considerably faster version based on CU

Xa9aX ツ 1.2k Dec 29, 2022
Semi-automated OpenVINO benchmark_app with variable parameters

Semi-automated OpenVINO benchmark_app with variable parameters. User can specify multiple options for any parameters in the benchmark_app and the progam runs the benchmark with all combinations of gi

Yasunori Shimura 8 Apr 11, 2022
The challenge for Quantum Coalition Hackathon 2021

Qchack 2021 Google Challenge This is a challenge for the brave 2021 qchack.io participants. Instructions Hello, intrepid qchacker, welcome to the G|o

quantumlib 18 May 04, 2022