A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

Overview

GFNet-Pytorch (NeurIPS 2020)

This repo contains the official code and pre-trained models for the glance and focus network (GFNet).

Citation

@inproceedings{NeurIPS2020_7866,
        title = {Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification},
       author = {Wang, Yulin and Lv, Kangchen and Huang, Rui and Song, Shiji and Yang, Le and Huang, Gao},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
         year = {2020},
}

Update on 2020/10/08: Release Pre-trained Models and the Inference Code on ImageNet.

Update on 2020/12/28: Release Training Code.

Introduction

Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically cropped from the original image. Experiments on ImageNet show that our method consistently improves the computational efficiency of a wide variety of deep models. For example, it further reduces the average latency of the highly efficient MobileNet-V3 on an iPhone XS Max by 20% without sacrificing accuracy.

Results

  • Top-1 accuracy on ImageNet v.s. Multiply-Adds

  • Top-1 accuracy on ImageNet v.s. Inference Latency (ms) on an iPhone XS Max

  • Visualization

Pre-trained Models

Backbone CNNs Patch Size T Links
ResNet-50 96x96 5 Tsinghua Cloud / Google Drive
ResNet-50 128x128 5 Tsinghua Cloud / Google Drive
DenseNet-121 96x96 5 Tsinghua Cloud / Google Drive
DenseNet-169 96x96 5 Tsinghua Cloud / Google Drive
DenseNet-201 96x96 5 Tsinghua Cloud / Google Drive
RegNet-Y-600MF 96x96 5 Tsinghua Cloud / Google Drive
RegNet-Y-800MF 96x96 5 Tsinghua Cloud / Google Drive
RegNet-Y-1.6GF 96x96 5 Tsinghua Cloud / Google Drive
MobileNet-V3-Large (1.00) 96x96 3 Tsinghua Cloud / Google Drive
MobileNet-V3-Large (1.00) 128x128 3 Tsinghua Cloud / Google Drive
MobileNet-V3-Large (1.25) 128x128 3 Tsinghua Cloud / Google Drive
EfficientNet-B2 128x128 4 Tsinghua Cloud / Google Drive
EfficientNet-B3 128x128 4 Tsinghua Cloud / Google Drive
EfficientNet-B3 144x144 4 Tsinghua Cloud / Google Drive
  • What are contained in the checkpoints:
**.pth.tar
├── model_name: name of the backbone CNNs (e.g., resnet50, densenet121)
├── patch_size: size of image patches (i.e., H' or W' in the paper)
├── model_prime_state_dict, model_state_dict, fc, policy: state dictionaries of the four components of GFNets
├── model_flops, policy_flops, fc_flops: Multiply-Adds of inferring the encoder, patch proposal network and classifier for once
├── flops: a list containing the Multiply-Adds corresponding to each length of the input sequence during inference
├── anytime_classification: results of anytime prediction (in Top-1 accuracy)
├── dynamic_threshold: the confidence thresholds used in budgeted batch classification
├── budgeted_batch_classification: results of budgeted batch classification (a two-item list, [0] and [1] correspond to the two coordinates of a curve)

Requirements

  • python 3.7.7
  • pytorch 1.3.1
  • torchvision 0.4.2
  • pyyaml 5.3.1 (for RegNets)

Evaluate Pre-trained Models

Read the evaluation results saved in pre-trained models

CUDA_VISIBLE_DEVICES=0 python inference.py --checkpoint_path PATH_TO_CHECKPOINTS  --eval_mode 0

Read the confidence thresholds saved in pre-trained models and infer the model on the validation set

CUDA_VISIBLE_DEVICES=0 python inference.py --data_url PATH_TO_DATASET --checkpoint_path PATH_TO_CHECKPOINTS  --eval_mode 1

Determine confidence thresholds on the training set and infer the model on the validation set

CUDA_VISIBLE_DEVICES=0 python inference.py --data_url PATH_TO_DATASET --checkpoint_path PATH_TO_CHECKPOINTS  --eval_mode 2

The dataset is expected to be prepared as follows:

ImageNet
├── train
│   ├── folder 1 (class 1)
│   ├── folder 2 (class 1)
│   ├── ...
├── val
│   ├── folder 1 (class 1)
│   ├── folder 2 (class 1)
│   ├── ...

Training

  • Here we take training ResNet-50 (96x96, T=5) for example. All the used initialization models and stage-1/2 checkpoints can be found in Tsinghua Cloud / Google Drive. Currently, this link includes ResNet and MobileNet-V3. We will update it as soon as possible. If you need other helps, feel free to contact us.

  • The Results in the paper is based on 2 Tesla V100 GPUs. For most of experiments, up to 4 Titan Xp GPUs may be enough.

Training stage 1, the initializations of global encoder (model_prime) and local encoder (model) are required:

CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --data_url PATH_TO_DATASET --train_stage 1 --model_arch resnet50 --patch_size 96 --T 5 --print_freq 10 --model_prime_path PATH_TO_CHECKPOINTS  --model_path PATH_TO_CHECKPOINTS

Training stage 2, a stage-1 checkpoint is required:

CUDA_VISIBLE_DEVICES=0 python train.py --data_url PATH_TO_DATASET --train_stage 2 --model_arch resnet50 --patch_size 96 --T 5 --print_freq 10 --checkpoint_path PATH_TO_CHECKPOINTS

Training stage 3, a stage-2 checkpoint is required:

CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --data_url PATH_TO_DATASET --train_stage 3 --model_arch resnet50 --patch_size 96 --T 5 --print_freq 10 --checkpoint_path PATH_TO_CHECKPOINTS

Contact

If you have any question, please feel free to contact the authors. Yulin Wang: [email protected].

Acknowledgment

Our code of MobileNet-V3 and EfficientNet is from here. Our code of RegNet is from here.

To Do

  • Update the code for visualizing.

  • Update the code for MIXED PRECISION TRAINING。

Owner
Rainforest Wang
Rainforest Wang
the code of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)

RMA-Net This repo is the implementation of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021). Paper

Wanquan Feng 205 Nov 09, 2022
Prevent `CUDA error: out of memory` in just 1 line of code.

🐨 Koila Koila solves CUDA error: out of memory error painlessly. Fix it with just one line of code, and forget it. 🚀 Features 🙅 Prevents CUDA error

RenChu Wang 1.7k Jan 02, 2023
Implementation of the paper All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training

SemCo The official pytorch implementation of the paper All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training

42 Nov 14, 2022
Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation

Dual super-resolution learning for semantic segmentation 2021-01-02 Subpixel Update Happy new year! The 2020-12-29 update of SISR with subpixel conv p

Sam 79 Nov 24, 2022
ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives

Status: Under development (expect bug fixes and huge updates) ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectiv

37 Dec 28, 2022
Connecting Java/ImgLib2 + Python/NumPy

imglyb imglyb aims at connecting two worlds that have been seperated for too long: Python with numpy Java with ImgLib2 imglyb uses jpype to access num

ImgLib2 29 Dec 21, 2022
This library contains a Tensorflow implementation of the paper Stability Analysis of Unfolded WMMSE for Power Allocation

UWMMSE-stability Tensorflow implementation of Stability Analysis of UWMMSE Overview This library contains a Tensorflow implementation of the paper Sta

Arindam Chowdhury 1 Nov 16, 2022
Code for: Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification Prerequisite PyTorch = 1.2.0 Python3 torch

16 Dec 14, 2022
The repository offers the official implementation of our paper in PyTorch.

Cloth Interactive Transformer (CIT) Cloth Interactive Transformer for Virtual Try-On Bin Ren1, Hao Tang1, Fanyang Meng2, Runwei Ding3, Ling Shao4, Phi

Bingoren 49 Dec 01, 2022
Tree LSTM implementation in PyTorch

Tree-Structured Long Short-Term Memory Networks This is a PyTorch implementation of Tree-LSTM as described in the paper Improved Semantic Representati

Riddhiman Dasgupta 529 Dec 10, 2022
MaskTrackRCNN for video instance segmentation based on mmdetection

MaskTrackRCNN for video instance segmentation Introduction This repo serves as the official code release of the MaskTrackRCNN model for video instance

411 Jan 05, 2023
Official implementation of "Motif-based Graph Self-Supervised Learning forMolecular Property Prediction"

Motif-based Graph Self-Supervised Learning for Molecular Property Prediction Official Pytorch implementation of NeurIPS'21 paper "Motif-based Graph Se

zaixi 71 Dec 20, 2022
Implementation of Sequence Generative Adversarial Nets with Policy Gradient

SeqGAN Requirements: Tensorflow r1.0.1 Python 2.7 CUDA 7.5+ (For GPU) Introduction Apply Generative Adversarial Nets to generating sequences of discre

Lantao Yu 2k Dec 29, 2022
A Novel Plug-in Module for Fine-grained Visual Classification

Pytorch implementation for A Novel Plug-in Module for Fine-Grained Visual Classification. fine-grained visual classification task.

ChouPoYung 109 Dec 20, 2022
code for our ECCV 2020 paper "A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation"

Code for our ECCV (2020) paper A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation. Prerequisites: python == 3.6.8 pytorch ==1.1.0

32 Nov 27, 2022
Tutorial repo for an end-to-end Data Science project

End-to-end Data Science project This is the repo with the notebooks, code, and additional material used in the ITI's workshop. The goal of the session

Deena Gergis 127 Dec 30, 2022
EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks

EncT5 (Unofficial) Pytorch Implementation of EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks About Finetune T5 model for classification & r

Jangwon Park 34 Jan 01, 2023
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

Fre-GAN Vocoder Fre-GAN: Adversarial Frequency-consistent Audio Synthesis Training: python train.py --config config.json Citation: @misc{kim2021frega

Rishikesh (ऋषिकेश) 93 Dec 17, 2022
SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning

SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning This repository is the official implementation of "SHRIMP: Sparser Random Featur

Bobby Shi 0 Dec 16, 2021
Inkscape extensions for figure resizing and editing

Academic-Inkscape: Extensions for figure resizing and editing This repository contains several Inkscape extensions designed for editing plots. Scale P

192 Dec 26, 2022