This repository is for a new network pruning method (Aligned Structured Sparsity Learning, ASSL) for efficient single image super-resolution (SR), introduced in our NeurIPS 2021 Spotlight paper:
Aligned Structured Sparsity Learning for Efficient Image Super-Resolution [Camera Ready]
Yulun Zhang*, Huan Wang*, Can Qin, and Yun Fu (*Contribute Equally)
Northeastern University, Boston, MA, USA
Stay tuned!
About Code release for Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy (ICLR 2022 Spotlight)
Under construction... Attention in Attention Network for Image Super-Resolution (A2N) This repository is an PyTorch implementation of the paper "Atten
Image Super-Resolution with Non-Local Sparse Attention This repository is for NLSN introduced in the following paper "Image Super-Resolution with Non-
HAN PyTorch code for our ECCV 2020 paper "Single Image Super-Resolution via a Holistic Attention Network" This repository is for HAN introduced in the
PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"
Maximum Entropy Generators for Energy-Based Models All experiments have tensorboard visualizations for samples / density / train curves etc. To run th
Machine Learning Sleep Schedule Tracker What is it? Convolutional neural network web app trained to track our infant’s sleep schedule using our Google
CoProtector Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".
LLA: Loss-aware Label Assignment for Dense Pedestrian Detection This project provides an implementation for "LLA: Loss-aware Label Assignment for Dens
@MingSun-Tse Thanks for your excellent work. I read the paper ,and I want to learn the details. Could you share the paper with me? Thank you very much!!
From the observation of training results, the hard mask's weights between the constrained layers are not exactly aligned. https://github.com/MingSun-Tse/ASSL/blob/a564556c8b578c2ee86d135044f088bfeaafc707/src/pruner/utils.py#L71
hello , I have some questiones about implementation details.
Data are obtained using the HR-LR data pairs obtained by the down-sampling code provided in BasicSR. The training data was DF2K (900 DIV2K + 2650 Flickr2K), and the test data was Set5.
I run this command to prune the EDSR_16_256 model to EDSR_16_48. Only the pruning ratio and storage path name are modified compared to the command provided by the official.
Prune from 256 to 48, pr=0.8125, x2, ASSL
python main.py --model LEDSR --scale 2 --patch_size 96 --ext sep --dir_data /home/notebook/data/group_cpfs/wurongyuan/data/data
--data_train DF2K --data_test DF2K --data_range 1-3550/3551-3555 --chop --save_results --n_resblocks 16 --n_feats 256
--method ASSL --wn --stage_pr [0-1000:0.8125] --skip_layers *mean*,*tail*
--same_pruned_wg_layers model.head.0,model.body.16,*body.2 --reg_upper_limit 0.5 --reg_granularity_prune 0.0001
--update_reg_interval 20 --stabilize_reg_interval 43150 --pre_train pretrained_models/LEDSR_F256R16BIX2_DF2K_M311.pt
--same_pruned_wg_criterion reg --save main/SR/LEDSR_F256R16BIX2_DF2K_ASSL_0.8125_RGP0.0001_RUL0.5_Pretrain_06011101 Results model_just_finished_prune ---> 33.739dB fine-tuning after one epoch ---> 37.781dB fine-tuning after 756 epoch ---> 37.940dB
The result (37.940dB) I obtained with the code provided by the official is still a certain gap from the result in the paper (38.12dB). I should have overlooked some details.
I also compared L1-norm method provided in the code. Prune from 256 to 48, pr=0.8125, x2, L1
python main.py --model LEDSR --scale 2 --patch_size 96 --ext sep --dir_data /home/notebook/data/group_cpfs/wurongyuan/data/data
--data_train DF2K --data_test DF2K --data_range 1-3550/3551-3555 --chop --save_results --n_resblocks 16 --n_feats 256
--method L1 --wn --stage_pr [0-1000:0.8125] --skip_layers *mean*,*tail*
--same_pruned_wg_layers model.head.0,model.body.16,*body.2 --reg_upper_limit 0.5 --reg_granularity_prune 0.0001
--update_reg_interval 20 --stabilize_reg_interval 43150 --pre_train pretrained_models/LEDSR_F256R16BIX2_DF2K_M311.pt
--same_pruned_wg_criterion reg --save main/SR/LEDSR_F256R16BIX2_DF2K_L1_0.8125_06011101
Results
model_just_finished_prune ---> 13.427dB fine-tuning after one epoch ---> 33.202dB fine-tuning after 756 epoch ---> 37.933dB
The difference between the results of L1-norm method and those of ASSL seems negligible at this pruning ratio (256->48)
Is there something I missed? Looking forward to your reply! >-<
Hello and thanks for your amazing work! When I try to reproduce the paper results, I met some trouble binarizing the DF2K data:
221 Dec 31, 2022
71 Dec 30, 2022
143 Dec 28, 2022
140 Nov 23, 2022
1.2k Dec 26, 2022
135 Oct 27, 2022
7 Jul 15, 2022
1 Oct 26, 2021
35 Dec 6, 2022
data/DF2K/bin/DF2K_train_LR_bicubic/X4/3548x4.pt does not exist. Now making binary...
Direct pt file without name or image
data/DF2K/bin/DF2K_train_LR_bicubic/X4/3549x4.pt does not exist. Now making binary...
Direct pt file without name or image
data/DF2K/bin/DF2K_train_LR_bicubic/X4/3550x4.pt does not exist. Now making binary...
Direct pt file without name or image
data/DF2K/bin/DF2K_train_HR/3551.pt does not exist. Now making binary...
Traceback (most recent call last):
...
FileNotFoundError: No such file: '/home/nfs_data/shixiangsheng/projects/ModelCompression/Prune/ASSL/src/data/DF2K/DF2K_train_HR/3551.png'
I created dirs like this: ----data |__DF2K |__DF2K_train_HR |__DF2K_train_LR_bicubic
I put '0001.png' - '0900.png' from ./data/DIV2K/DIV2K_train_HR and '000001.png' - '002650.png' (renamed to '0901.png' - '3550.png') from .data/Flickr2K/Flickr2K_HR to ./DF2K/DF2K_train_HR. As for downsampled images, I created folders named in ['X2', 'X3', 'X4'] under ./DF2K/DF2K_train_LR_bicubic and copied related images from DIV2K_train_LR_bicubic and Flickr2K_LR_bicubic (with images renamed as '0001x_.png' to '3550x_.png'). At the first and second stages of binarization (binarizing HR images and X4 LR images), it seems OK, but then the above error emerged. It's kind of weird since the total training images are 900 + 2650 and I have no idea why it returned to binarize the HR images after binarizing X4 LR images. I'm new to SR and have tried to look up for data preparation of DF2K in other SR repos, but in vain. I wonder how you actually get DF2K images binarized. Thanks for your help in advance XD
Pretrained models, final models, and visual results on Set5, Set14, B100, Urban100, Manga109 (at scale x4).
Source code(tar.gz)
ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers Official implementation of ViewFormer. ViewFormer is a NeRF-free neural rend
Tensorflow2 Keras-based Semantic Segmentation Models Implementation
Reference-based Video Super-Resolution (RefVSR) Official PyTorch Implementation of the CVPR 2022 Paper Project | arXiv | RealMCVSR Dataset This repo c
SPatchGAN: Official TensorFlow Implementation Paper "SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation"
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
DynaBOA Code repositoty for the paper: Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation Shanyan Guan, Jingwei Xu, Michell
True-Rarity True per-item rarity for Loot (For Adventurers) and More Loot A.K.A mLoot each out/true_rarity_{item_type}.json file contains probabilitie
Follow the development of our desktop client here Paaster Paaster is a secure by default end-to-end encrypted pastebin built with the objective of sim
MUSCO - Multimodal Descriptions of Social Concepts Automatic Modeling of (Highly Abstract) Social Concepts evoked by Art Images This project aims to i
CLIP-ONNX It is a simple library to speed up CLIP inference up to 3x (K80 GPU) Usage Install clip-onnx module and requirements first. Use this trick !
Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation Prerequisites This repo is built upon a local copy of transfo
AugMix Introduction We propose AugMix, a data processing technique that mixes augmented images and enforces consistent embeddings of the augmented ima
iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis Andreas Bl
Visually Grounded Bert Language Model This repository is the official implementation of Explainable Semantic Space by Grounding Language to Vision wit
Neural Scene Flow Fields PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes", CVPR 20
Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs, ICCV 2021 Global Pooling, More than Meets the Eye: Posi
Bottleneck Transformer - Pytorch Implementation of Bottleneck Transformer, SotA visual recognition model with convolution + attention that outperforms
Learn Deep Learning with AI Summer A collection of all articles (almost 100) written for the AI Summer blog organized by topic. Deep Learning Theory M
Benchmarks for Object Detection in Aerial Images
MVP Benchmark: Multi-View Partial Point Clouds for Completion and Registration [NEWS] 2021-07-12 [NEW 🎉 ] The submission on Codalab starts! 2021-07-1
169 Dec 30, 2022
1 Feb 08, 2022
151 Dec 30, 2022
39 Dec 30, 2022
3k Jan 08, 2023
197 Jan 07, 2023
3 Jul 26, 2022
211 Dec 25, 2022
0 Aug 22, 2021
93 Dec 20, 2022
10 Sep 28, 2022
876 Dec 17, 2022
36 Dec 25, 2022
17 Dec 17, 2022
585 Jan 04, 2023
32 Apr 24, 2022
621 Jan 06, 2023
95 Dec 29, 2022
691 Dec 30, 2022
93 Dec 21, 2022