PyTorch code for our paper "Gated Multiple Feedback Network for Image Super-Resolution" (BMVC2019)

Last update: Nov 03, 2022

Related tags

Overview

Gated Multiple Feedback Network for Image Super-Resolution

This repository contains the PyTorch implementation for the proposed GMFN [arXiv].

The framework of our proposed GMFN. The colored arrows among different time steps denote the multiple feedback connections. The high-level information carried by them helps low-level features become more representative.

Demo

Clone SRFBN as the backbone and satisfy its requirements.

Test

Copy ./networks/gmfn_arch.py into SRFBN_CVPR19/networks/
Download the pre-trained models from Google driver or Baidu Netdisk, unzip and place them into SRFBN_CVPR19/models.
Copy ./options/test/ to SRFBN_CVPR19/options/test/.
Run commands cd SRFBN_CVPR19 and one of followings for evaluation on Set5:

python test.py -opt options/test/test_GMFN_x2.json
python test.py -opt options/test/test_GMFN_x3.json
python test.py -opt options/test/test_GMFN_x4.json

Finally, PSNR/SSIM values for Set5 are shown on your screen, you can find the reconstruction images in ./results.

To test GMFN on other standard SR benchmarks or your own images, please refer to the instruction in SRFBN.

Train

Prepare the training set according to this (1-3).
Modify ./options/train/train_GMFN.json by following the instructions in ./options/train/README.md.
Run commands:

cd SRFBN_CVPR19
python train.py -opt options/train/train_GNFN.json

You can monitor the training process in ./experiments.
Finally, you can follow the test pipeline to evaluate the model trained by yourself.

Performance

Quantitative Results

Quantitative evaluation under scale factors x2, x3 and x4. The best performance is shown in bold and the second best performance is underlined.

More Qualitative Results (x4)

Acknowledgment

If you find our work useful in your research or publications, please consider citing:

@inproceedings{li2019gmfn,
    author = {Li, Qilei and Li, Zhen and Lu, Lu and Jeon, Gwanggil and Liu, Kai and Yang, Xiaomin},
    title = {Gated Multiple Feedback Network for Image Super-Resolution},
    booktitle = {The British Machine Vision Conference (BMVC)},
    year = {2019}
}

@inproceedings{li2019srfbn,
    author = {Li, Zhen and Yang, Jinglei and Liu, Zheng and Yang, Xiaomin and Jeon, Gwanggil and Wu, Wei},
    title = {Feedback Network for Image Super-Resolution},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year= {2019}
}

Pytorch implementation of our paper under review — Lottery Jackpots Exist in Pre-trained Models

Lottery Jackpots Exist in Pre-trained Models (Paper Link) Requirements Python = 3.7.4 Pytorch = 1.6.1 Torchvision = 0.4.1 Reproduce the Experiment

27 Jun 28, 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

49 Dec 1, 2022

PyTorch implementations for our SIGGRAPH 2021 paper: Editable Free-viewpoint Video Using a Layered Neural Representation.

st-nerf We provide PyTorch implementations for our paper: Editable Free-viewpoint Video Using a Layered Neural Representation SIGGRAPH 2021 Jiakai Zha

258 Jan 2, 2023

PyTorch implementation of our ICCV2021 paper: StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation

StructDepth PyTorch implementation of our ICCV2021 paper: StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimat

112 Nov 28, 2022

Pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering".

TRAnsformer Routing Networks (TRAR) This is an official implementation for ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visu

49 Nov 10, 2022

This is the official pytorch implementation for our ICCV 2021 paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering" on VQA Task

🌈 ERASOR (RA-L'21 with ICRA Option) Official page of "ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point C

225 Dec 29, 2022

PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.

4 May 8, 2022

PyTorch implementation for our NeurIPS 2021 Spotlight paper "Long Short-Term Transformer for Online Action Detection".

Long Short-Term Transformer for Online Action Detection Introduction This is a PyTorch implementation for our NeurIPS 2021 Spotlight paper "Long Short

77 Dec 16, 2022

Official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels".

WarPI The official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels". Run python main.py --corruption_type

3 Sep 3, 2022

Comments

Approximately how many epoches will reach the results in the paper (4x SR result)

Hi, liqilei After I have run about 700 epoches, the reult on val set is 32.41(highest result). I want to know if my training process seems to be problematic? How long did you reach 32.47 of SRFBN when you were training? How long does it take to reach 32.70? Thank you.

opened by Senwang98 7
train error size not match

CUDA_VISIBLE_DEVICES=0 python train.py -opt options/train/train_GMFN.json I use celeba dataset train

===> Training Epoch: [1/1000]... Learning Rate: 0.000200 Epoch: [1/1000]: 0%| | 0/251718 [00:00<?, ?it/s] Traceback (most recent call last): File "train.py", line 131, in main() File "train.py", line 69, in main iter_loss = solver.train_step() File "/exp_sr/SRFBN/solvers/SRSolver.py", line 104, in train_step loss_steps = [self.criterion_pix(sr, split_HR) for sr in outputs] File "/exp_sr/SRFBN/solvers/SRSolver.py", line 104, in loss_steps = [self.criterion_pix(sr, split_HR) for sr in outputs] File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(*input, **kwargs) File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/modules/loss.py", line 87, in forward return F.l1_loss(input, target, reduction=self.reduction) File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/functional.py", line 1702, in l1_loss input, target, reduction) File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/functional.py", line 1674, in _pointwise_loss return lambd_optimized(input, target, reduction) RuntimeError: input and target shapes do not match: input [16 x 3 x 192 x 192], target [16 x 3 x 48 x 48] at /pytorch/aten/src/THCUNN/generic/AbsCriterion.cu:12

opened by yja1 3
Not an Issue

Hey @Paper99,

Thanks for sharing your code! I wonder if it is possible to help with visualizing featuer-maps as you did in your paper figure 4.

Thanks

opened by Auth0rM0rgan 1
My training result with scale = 2
Hi, After I have trained the DIV2k, I get the final result(use best_ckp.pth to test):

set5:38.16/0.9610 set14:33.91/0.9203 urban100:32.81/0.9349 B100:32.30/0.9011 manga109:39.01/0.9776

It seems much lower than that in your paper.
opened by Senwang98 6

Releases(v1.0)

v1.0(Aug 26, 2020)

Source code(tar.gz)
Source code(zip)
GMFN_BMVC19_Models.zip(104.38 MB)

Owner

Qilei Li

GitHub Repository

Generative Flow Networks

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation Implementation for our paper, submitted to NeurIPS 2021 (also chec

381 Jan 04, 2023

Learning Neural Painters Fast! using PyTorch and Fast.ai

The Joy of Neural Painting Learning Neural Painters Fast! using PyTorch and Fast.ai Blogpost with more details: The Joy of Neural Painting The impleme

72 Nov 10, 2022

Readings for "A Unified View of Relational Deep Learning for Polypharmacy Side Effect, Combination Therapy, and Drug-Drug Interaction Prediction."

Polypharmacy - DDI - Synergy Survey The Survey Paper This repository accompanies our survey paper A Unified View of Relational Deep Learning for Polyp

79 Jan 05, 2023

Image Restoration Using Swin Transformer for VapourSynth

SwinIR SwinIR function for VapourSynth, based on https://github.com/JingyunLiang/SwinIR. Dependencies NumPy PyTorch, preferably with CUDA. Note that t

11 Jun 19, 2022

A high-performance distributed deep learning system targeting large-scale and automated distributed training.

HETU Documentation | Examples Hetu is a high-performance distributed deep learning system targeting trillions of parameters DL model training, develop

150 Dec 21, 2022

Post-training Quantization for Neural Networks with Provable Guarantees

Post-training Quantization for Neural Networks with Provable Guarantees Authors: Jinjie Zhang ( Yixuan Zhou 2 Nov 29, 2022

Bot developed in Python that automates races in pegaxy.

español | português About it: This is a fork from pega-racing-bot. This bot, developed in Python, is to automate races in pegaxy. The game developers

4 Apr 08, 2022

Easy genetic ancestry predictions in Python

ezancestry Easily visualize your direct-to-consumer genetics next to 2500+ samples from the 1000 genomes project. Evaluate the performance of a custom

38 Jan 02, 2023

An interactive DNN Model deployed on web that predicts the chance of heart failure for a patient with an accuracy of 98%

Heart Failure Predictor About A Web UI deployed Dense Neural Network Model Made using Tensorflow that predicts whether the patient is healthy or has c

0 Jan 09, 2022

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

Deep Illuminator Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide

52 Nov 29, 2022

Freecodecamp Scientific Computing with Python Certification; Solution for Challenge 2: Time Calculator

Assignment Write a function named add_time that takes in two required parameters and one optional parameter: a start time in the 12-hour clock format

0 Feb 26, 2022

Source code for the GPT-2 story generation models in the EMNLP 2020 paper "STORIUM: A Dataset and Evaluation Platform for Human-in-the-Loop Story Generation"

Storium GPT-2 Models This is the official repository for the GPT-2 models described in the EMNLP 2020 paper [STORIUM: A Dataset and Evaluation Platfor

27 Dec 20, 2022

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM

Class Activation Map methods implemented in Pytorch pip install grad-cam ⭐ Tested on many Common CNN Networks and Vision Transformers. ⭐ Includes smoo

6.6k Jan 06, 2023