[NeurIPS'20] Multiscale Deep Equilibrium Models

Related tags

Deep Learningmdeq
Overview

Multiscale Deep Equilibrium Models

💥 💥 💥 💥

This repo is deprecated and we will soon stop actively maintaining it, as a more up-to-date (and simpler & more efficient) implementation of MDEQ with the same set of tasks as here is now available in the DEQ repo.

We STRONGLY recommend using with the MDEQ-Vision code in the DEQ repo (which also supports Jacobian-related analysis).

💥 💥 💥 💥


This repository contains the code for the multiscale deep equilibrium (MDEQ) model proposed in the paper Multiscale Deep Equilibrium Models by Shaojie Bai, Vladlen Koltun and J. Zico Kolter.

Is implicit deep learning relevant for general, large-scale pattern recognition tasks? We propose the multiscale deep equilibrium (MDEQ) model, which expands upon the DEQ formulation substantially to introduce simultaneous equilibrium modeling of multiple signal resolutions. Specifically, MDEQ solves for and backpropagates through synchronized equilibria of multiple feature representation streams. Such structure rectifies one of the major drawbacks of DEQ, and provide natural hierarchical interfaces for auxiliary losses and compound training procedures (e.g., pretraining and finetuning). Our experiment demonstrate for the first time that "shallow" implicit models can scale to and achieve near-SOTA results on practical computer vision tasks (e.g., megapixel images on Cityscapes segmentation).

We provide in this repo the implementation and the links to the pretrained classification & segmentation MDEQ models.

If you find thie repository useful for your research, please consider citing our work:

@inproceedings{bai2020multiscale,
    author    = {Shaojie Bai and Vladlen Koltun and J. Zico Kolter},
    title     = {Multiscale Deep Equilibrium Models},
    booktitle   = {Advances in Neural Information Processing Systems (NeurIPS)},
    year      = {2020},
}

Overview

The structure of a multiscale deep equilibrium model (MDEQ) is shown below. All components of the model are shown in this figure (in practice, we use n=4).

Examples

Some examples of MDEQ segmentation results on the Cityscapes dataset.

Requirements

PyTorch >=1.4.0, torchvision >= 0.4.0

Datasets

  • CIFAR-10: We download the CIFAR-10 dataset using PyTorch's torchvision package (included in this repo).
  • ImageNet We follow the implementation from the PyTorch ImageNet Training repo.
  • Cityscapes: We download the Cityscapes dataset from its official website and process it according to this repo. Cityscapes dataset additionally require a list folder that aligns each original image with its corresponding labeled segmented image. This list folder can be downloaded here.

All datasets should be downloaded, processed and put in the respective data/[DATASET_NAME] directory. The data/ directory should look like the following:

data/
  cityscapes/
  imagenet/
  ...          (other datasets)
  list/        (see above)

Usage

All experiment settings are provided in the .yaml files under the experiments/ folder.

To train an MDEQ classification model on ImageNet/CIFAR-10, do

python tools/cls_train.py --cfg experiments/[DATASET_NAME]/[CONFIG_FILE_NAME].yaml

To train an MDEQ segmentation model on Cityscapes, do

python -m torch.distributed.launch --nproc_per_node=4 tools/seg_train.py --cfg experiments/[DATASET_NAME]/[CONFIG_FILE_NAME].yaml

where you should provide the pretrained ImageNet model path in the corresponding configuration (.yaml) file. We provide a sample pretrained model extractor in pretrained_models/, but you can also write your own script.

Similarly, to test the model and generate segmentation results on Cityscapes, do

python tools/seg_test.py --cfg experiments/[DATASET_NAME]/[CONFIG_FILE_NAME].yaml

You can (and probably should) initiate the Cityscapes training with an ImageNet-pretrained MDEQ. You need to extract the state dict from the ImageNet checkpointed model, and set the MODEL.PRETRAINED entry in Cityscapes yaml file to this state dict on disk.

The model implementation and MDEQ's algorithmic components (e.g., L-Broyden's method) can be found in lib/.

Pre-trained Models

We provide some reasonably good pre-trained weights here so that one can quickly play with DEQs without training from scratch.

Description Task Dataset Model
MDEQ-XL ImageNet Classification ImageNet download (.pkl)
MDEQ-XL Cityscapes(val) Segmentation Cityscapes download (.pkl)
MDEQ-Small ImageNet Classification ImageNet download (.pkl)
MDEQ-Small Cityscapes(val) Segmentation Cityscapes download (.pkl)

I. Example of how to evaluate the pretrained ImageNet model:

  1. Download the pretrained ImageNet .pkl file. (I recommend using the gdown command!)
  2. Put the model under pretrained_models/ folder with some file name [FILENAME].
  3. Run the MDEQ classification validation command:
python tools/cls_valid.py --testModel pretrained_models/[FILENAME] --cfg experiments/imagenet/cls_mdeq_[SIZE].yaml

For example, for MDEQ-Small, you should get >75% top-1 accuracy.

II. Example of how to use the pretrained ImageNet model to train on Cityscapes:

  1. Download the pretrained ImageNet .pkl file.
  2. Put the model under pretrained_models/ folder with some file name [FILENAME].
  3. In the corresponding experiments/cityscapes/seg_MDEQ_[SIZE].yaml (where SIZE is typically SMALL, LARGE or XL), set MODEL.PRETRAINED to "pretrained_models/[FILENAME]".
  4. Run the MDEQ segmentation training command (see the "Usage" section above):
python -m torch.distributed.launch --nproc_per_node=[N_GPUS] tools/seg_train.py --cfg experiments/cityscapes/seg_MDEQ_[SIZE].yaml

III. Example of how to use the pretrained Cityscapes model for inference:

  1. Download the pretrained Cityscapes .pkl file
  2. Put the model under pretrained_models/ folder with some file name [FILENAME].
  3. In the corresponding experiments/cityscapes/seg_MDEQ_[SIZE].yaml (where SIZE is typically SMALL, LARGE or XL), set TEST.MODEL_FILE to "pretrained_models/[FILENAME]".
  4. Run the MDEQ segmentation testing command (see the "Usage" section above):
python tools/seg_test.py --cfg experiments/cityscapes/seg_MDEQ_[SIZE].yaml

Tips:

  • To load the Cityscapes pretrained model, download the .pkl file and specify the path in config.[TRAIN/TEST].MODEL_FILE (which is '' by default) in the .yaml files. This is different from setting MODEL.PRETRAINED, see the point below.
  • The difference between [TRAIN/TEST].MODEL_FILE and MODEL.PRETRAINED arguments in the yaml files: the former is used to load all of the model parameters; the latter is for compound training (e.g., when transferring from ImageNet to Cityscapes, we want to discard the final classifier FC layers).
  • The repo supports checkpointing of models at each epoch. One can resume from a previously saved checkpoint by turning on the TRAIN.RESUME argument in the yaml files.
  • Just like DEQs, the MDEQ models can be slower than explicit deep networks, and even more so as the image size increases (because larger images typically require more Broyden iterations to converge well; see Figure 5 in the paper). But one can play with the forward and backward thresholds to adjust the runtime.

Acknowledgement

Some utilization code (e.g., model summary and yaml processing) of this repo were modified from the HRNet repo and the DEQ repo.

Owner
CMU Locus Lab
Zico Kolter's Research Group
CMU Locus Lab
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance Project Page | Paper | Data This repository contains an implementatio

Lior Yariv 521 Dec 30, 2022
FedScale: Benchmarking Model and System Performance of Federated Learning

FedScale: Benchmarking Model and System Performance of Federated Learning (Paper) This repository contains scripts and instructions of building FedSca

268 Jan 01, 2023
SeqFormer: a Frustratingly Simple Model for Video Instance Segmentation

SeqFormer: a Frustratingly Simple Model for Video Instance Segmentation SeqFormer SeqFormer: a Frustratingly Simple Model for Video Instance Segmentat

Junfeng Wu 298 Dec 22, 2022
This repository contains all code and data for the Inside Out Visual Place Recognition task

Inside Out Visual Place Recognition This repository contains code and instructions to reproduce the results for the Inside Out Visual Place Recognitio

15 May 21, 2022
Code and training data for our ECCV 2016 paper on Unsupervised Learning

Shuffle and Learn (Shuffle Tuple) Created by Ishan Misra Based on the ECCV 2016 Paper - "Shuffle and Learn: Unsupervised Learning using Temporal Order

Ishan Misra 44 Dec 08, 2021
A python library for face detection and features extraction based on mediapipe library

FaceAnalyzer A python library for face detection and features extraction based on mediapipe library Introduction FaceAnalyzer is a library based on me

Saifeddine ALOUI 14 Dec 30, 2022
Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

Mingrui Yu 3 Jan 07, 2022
Simple Dynamic Batching Inference

Simple Dynamic Batching Inference 解决了什么问题? 众所周知,Batch对于GPU上深度学习模型的运行效率影响很大。。。 是在Inference时。搜索、推荐等场景自带比较大的batch,问题不大。但更多场景面临的往往是稀碎的请求(比如图片服务里一次一张图)。 如果

116 Jan 01, 2023
Code for STFT Transformer used in BirdCLEF 2021 competition.

STFT_Transformer Code for STFT Transformer used in BirdCLEF 2021 competition. The STFT Transformer is a new way to use Transformers similar to Vision

Jean-François Puget 69 Sep 29, 2022
This repository is the official implementation of Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models

Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models Link to paper Abstract We study prediction of future out

Rickard Karlsson 2 Aug 19, 2022
Predicting Semantic Map Representations from Images with Pyramid Occupancy Networks

This is the code associated with the paper Predicting Semantic Map Representations from Images with Pyramid Occupancy Networks, published at CVPR 2020.

Thomas Roddick 219 Dec 20, 2022
Generating Anime Images by Implementing Deep Convolutional Generative Adversarial Networks paper

AnimeGAN - Deep Convolutional Generative Adverserial Network PyTorch implementation of DCGAN introduced in the paper: Unsupervised Representation Lear

Rohit Kukreja 23 Jul 21, 2022
This repo will contain code to reproduce and build upon understanding transfer learning

What is being transferred in transfer learning? This repo contains the code for the following paper: Behnam Neyshabur*, Hanie Sedghi*, Chiyuan Zhang*.

4 Jun 16, 2021
PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision

Learning to Generate Grounded Visual Captions without Localization Supervision This is the PyTorch implementation of our paper: Learning to Generate G

Chih-Yao Ma 41 Nov 17, 2022
This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

CRGNN Paper : Improving the Training of Graph Neural Networks with Consistency Regularization Environments Implementing environment: GeForce RTX™ 3090

THUDM 28 Dec 09, 2022
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency[ECCV 2020]

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency(ECCV 2020) This is an official python implementati

304 Jan 03, 2023
Continual Learning of Electronic Health Records (EHR).

Continual Learning of Longitudinal Health Records Repo for reproducing the experiments in Continual Learning of Longitudinal Health Records (2021). Re

Jacob 7 Oct 21, 2022
The code for MM2021 paper "Multi-Level Counterfactual Contrast for Visual Commonsense Reasoning"

The Code for MM2021 paper "Multi-Level Counterfactual Contrast for Visual Commonsense Reasoning" Setting up and using the repo Get the dataset. Follow

4 Apr 20, 2022
AFLFast (extends AFL with Power Schedules)

AFLFast Power schedules implemented by Marcel Böhme [email protected]

Marcel Böhme 380 Jan 03, 2023
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs This is the code of paper ConE: Cone Embeddings for Multi-Hop Reasoning over Knowl

MIRA Lab 33 Dec 07, 2022