# IDN-tensorflow **Repository Path**: greitzmann/IDN-tensorflow ## Basic Information - **Project Name**: IDN-tensorflow - **Description**: Tensorflow implementation of IDN (CVPR 2018) - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-11-04 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # IDN-tensorflow [[Original Caffe version]](https://github.com/Zheng222/IDN-Caffe) ## Testing * Install Tensorflow 1.11, Matlab R2017a * Download [Test datasets](https://drive.google.com/open?id=1_K6mchwDGOQMIXuBIGrlDA4EAYgbtdmU) * Modify `config.py` (if you want to test x3 model on Set14, `config.TEST.model_path = 'checkpoint_x3/model.ckpt'` `config.TEST.dataset = 'Set14'`) and `test.py` (`scale = 3`). * Run testing: ```bash python test.py ``` ## Training * Download [Training dataset](https://drive.google.com/open?id=12hOYsMa8t1ErKj6PZA352icsx9mz1TwB) * Modify `config.py` (if you want to train x4 model, `config.TRAIN.hr_img_path = '/path/to/DIV2K_train_HR/'` `config.TRAIN.checkpoint_dir = 'checkpoint_x4/'` `config.VALID.hr_img_path = '/path/to/DIV2K_valid_HR/'` `config.VALID.lr_img_path = '/path/to/DIV2K_valid_LR_x4/'`) and `train_SR.py` (`scale = 4`) * Run training: ```bash python train_SR.py ``` ## Note This TensorFlow version is trained with DIV2K training dataset on RGB channels. Additionally, We modify the upsample layer to subpixel convolution (the original version is transposed convolution). ## Results [Test_results](https://drive.google.com/open?id=1saFhGV8t2ytzRLHE2CaFc4H_UkvJo9KS) The following PSNR/SSIMs are evaluated on Matlab R2017a and the code can be referred to [Evaluate_PSNR_SSIM.m](https://github.com/yulunzhang/RCAN/blob/master/RCAN_TestCode/Evaluate_PSNR_SSIM.m). | _{Training dataset} | _Scale | _Set5 | _Set14 | _B100 | _Urban100 | |:---:|:---:|:---:|:---:|:---:|:---:| | ₂₉₁ | _×2 | _{37.83 / 0.9600_{| _{33.30 / 0.9148}|_{32.08 / 0.8985}|_{31.27 / 0.9196}|
| _DIV2K | _×2 | _{37.85 / 0.9598_{| _{33.58 / 0.9178}|_{32.11 / 0.8989}|_{31.95 / 0.9266}|
| ₂₉₁ | _×3 | _{34.11 / 0.9253_{| _{29.99 / 0.8354}|_{28.95 / 0.8013}|_{27.42 / 0.8359}|
| _DIV2K | _×3 | _{34.24 / 0.9260_{| _{30.27 / 0.8408}|_{29.03 / 0.8038}|_{27.99 / 0.8489}|
| ₂₉₁ | _×4 | _{31.82 / 0.8903_{| _{28.25 / 0.7730}|_{27.41 / 0.7297}|_{25.41 / 0.7632}|
| _DIV2K | _×4 | _{31.99 / 0.8928_{| _{28.52 / 0.7794}|_{27.52 / 0.7339}|_{25.92 / 0.7801}|

## Model Parameters
| _Scale| _{Model size} |
|:---:|:---:|
| _×2 | _**579,276** |
| _×3 | _**587,931** |
| _×4 | _**600,048** |
## Citation

If you find IDN useful in your research, please consider citing:

```
@inproceedings{Hui-IDN-2018,
title={Fast and Accurate Single Image Super-Resolution via Information Distillation Network},
author={Hui, Zheng and Wang, Xiumei and Gao, Xinbo},
booktitle={CVPR},
pages = {723--731},
year={2018}
}
```}}}}}}}}}}}}