GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → zhaohengyuan1 → Pan

zhaohengyuan1 / Pan

[Params: Only 272K!!!] Efficient Image Super-Resolution Using Pixel Attention, in ECCV Workshop, 2020.

Programming Languages

python
139335 projects - #7 most used programming language

Labels

attention-mechanismsuper-resolution

Projects that are alternatives of or similar to Pan

PAM
[TPAMI 2020] Parallax Attention for Unsupervised Stereo Correspondence Learning
Stars: ✭ 62 (-58.94%)
Mutual labels:  attention-mechanism, super-resolution
Mirnet
Official repository for "Learning Enriched Features for Real Image Restoration and Enhancement" (ECCV 2020). SOTA results for image denoising, super-resolution, and image enhancement.
Stars: ✭ 247 (+63.58%)
Mutual labels:  attention-mechanism, super-resolution
Drln
Densely Residual Laplacian Super-resolution, IEEE Pattern Analysis and Machine Intelligence (TPAMI), 2020
Stars: ✭ 120 (-20.53%)
Mutual labels:  attention-mechanism, super-resolution
Awesome Gan For Medical Imaging
Awesome GAN for Medical Imaging
Stars: ✭ 1,814 (+1101.32%)
Mutual labels:  super-resolution
3pu
Patch-base progressive 3D Point Set Upsampling
Stars: ✭ 131 (-13.25%)
Mutual labels:  super-resolution
Attribute Aware Attention
[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning
Stars: ✭ 143 (-5.3%)
Mutual labels:  attention-mechanism
Hart
Hierarchical Attentive Recurrent Tracking
Stars: ✭ 149 (-1.32%)
Mutual labels:  attention-mechanism
Image Caption Generator
A neural network to generate captions for an image using CNN and RNN with BEAM Search.
Stars: ✭ 126 (-16.56%)
Mutual labels:  attention-mechanism
Waifu2x Extension
Image, GIF and Video enlarger/upscaler achieved with waifu2x and Anime4K. [NO LONGER UPDATED]
Stars: ✭ 149 (-1.32%)
Mutual labels:  super-resolution
Enhancenet Code
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (official repository)
Stars: ✭ 142 (-5.96%)
Mutual labels:  super-resolution
Document Classifier Lstm
A bidirectional LSTM with attention for multiclass/multilabel text classification.
Stars: ✭ 136 (-9.93%)
Mutual labels:  attention-mechanism
Hierarchical Multi Label Text Classification
The code of CIKM'19 paper《Hierarchical Multi-label Text Classification: An Attention-based Recurrent Network Approach》
Stars: ✭ 133 (-11.92%)
Mutual labels:  attention-mechanism
Seq2seq chatbot new
基于seq2seq模型的简单对话系统的tf实现，具有embedding、attention、beam_search等功能，数据集是Cornell Movie Dialogs
Stars: ✭ 144 (-4.64%)
Mutual labels:  attention-mechanism
Perceiver Pytorch
Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch
Stars: ✭ 130 (-13.91%)
Mutual labels:  attention-mechanism
Basicsr
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
Stars: ✭ 2,708 (+1693.38%)
Mutual labels:  super-resolution
Abstractive Summarization
Implementation of abstractive summarization using LSTM in the encoder-decoder architecture with local attention.
Stars: ✭ 128 (-15.23%)
Mutual labels:  attention-mechanism
Routing Transformer
Fully featured implementation of Routing Transformer
Stars: ✭ 149 (-1.32%)
Mutual labels:  attention-mechanism
Prediction Flow
Deep-Learning based CTR models implemented by PyTorch
Stars: ✭ 138 (-8.61%)
Mutual labels:  attention-mechanism
Rdn Tensorflow
A TensorFlow implementation of CVPR 2018 paper "Residual Dense Network for Image Super-Resolution".
Stars: ✭ 136 (-9.93%)
Mutual labels:  super-resolution
Keras Image Super Resolution
EDSR, RCAN, SRGAN, SRFEAT, ESRGAN
Stars: ✭ 143 (-5.3%)
Mutual labels:  super-resolution
View All Similar Projects ➔

If you have questions about results, please check the new update version of file PAN_arch.py.

PAN [⚡️ 272K parameters]

Lowest parameters in AIM2020 Efficient Super Resolution.

Paper | Video

Efficient Image Super-Resolution Using Pixel Attention

Authors: Hengyuan Zhao, Xiangtao Kong, Jingwen He, Yu Qiao, Chao Dong

Dependencies

Codes

  • Our codes version based on mmsr.
  • This codes provide the testing and training code.

How to Test

  1. Clone this github repo.
git clone https://github.com/zhaohengyuan1/PAN.git
cd PAN

  1. Download the five test datasets (Set5, Set14, B100, Urban100, Manga109) from Google Drive

  2. Pretrained models have be placed in ./experiments/pretrained_models/ folder. More models can be download from Google Drive.

  3. Run test. We provide x2,x3,x4 pretrained models.

cd codes
python test.py -opt option/test/test_PANx4.yml

More testing commond can be found in ./codes/run_scripts.sh file. 5. The output results will be sorted in ./results. (We have been put our testing log file in ./results) We also provide our testing results on five benchmark datasets on Google Drive or Baidu Drive, password: 8mrn.

How to Train

  1. Download DIV2K and Flickr2K from Google Drive or Baidu Drive

  2. Generate Training patches. Modified the path of your training datasets in ./codes/data_scripts/extract_subimages.py file.

  3. Run Training.

python train.py -opt options/train/train_PANx4.yml
  1. More training commond can be found in ./codes/run_scripts.sh file.

Testing the Parameters, Mult-Adds and Running Time

  1. Testing the parameters and Mult-Adds.
python test_summary.py
  1. Testing the Running Time.
python test_running_time.py

Related Work on AIM2020

Enhanced Quadratic Video Interpolation (winning solution of AIM2020 VTSR Challenge) paper | code

Contact

Email: [email protected]

If you find our work is useful, please kindly cite it.

@misc{zhao2020efficient,
      title={Efficient Image Super-Resolution Using Pixel Attention}, 
      author={Hengyuan Zhao and Xiangtao Kong and Jingwen He and Yu Qiao and Chao Dong},
      year={2020},
      eprint={2010.01073},
      archivePrefix={arXiv},
      primaryClass={eess.IV}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].