RuntimeError: Trying to resize storage that is not resizable

Aradhana · September 19, 2023, 5:27am

The scenario: Training SWINIR for classical Super resolution.

Using Available DIV2K (900 image pairs, using Ground truth and bicubic x2). It works
Using combination of DIV2K and Flickr total 3550 images, facing above issue. Now Flickr pair was not available, therefore I down sized bicubic x2 and create the pairs.

To give an idea: ground truth image: 2040 pixels. X2 bicubic: 1020 pixels

I am giving the code github here:

cszn/KAIR/blob/master/docs/README_SwinIR.md

# SwinIR: Image Restoration Using Shifted Window Transformer
[paper](https://arxiv.org/abs/2108.10257)
**|** 
[supplementary](https://github.com/JingyunLiang/SwinIR/releases/tag/v0.0)
**|** 
[visual results](https://github.com/JingyunLiang/SwinIR/releases/tag/v0.0)
**|** 
[original project page](https://github.com/JingyunLiang/SwinIR)
**|**
[online Colab demo](https://colab.research.google.com/gist/JingyunLiang/a5e3e54bc9ef8d7bf594f6fee8208533/swinir-demo-on-real-world-image-sr.ipynb)

[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/abs/2108.10257)
[![GitHub Stars](https://img.shields.io/github/stars/JingyunLiang/SwinIR?style=social)](https://github.com/JingyunLiang/SwinIR)
[![download](https://img.shields.io/github/downloads/JingyunLiang/SwinIR/total.svg)](https://github.com/JingyunLiang/SwinIR/releases)
[ <a href="https://colab.research.google.com/gist/JingyunLiang/a5e3e54bc9ef8d7bf594f6fee8208533/swinir-demo-on-real-world-image-sr.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google colab logo"></a>](https://colab.research.google.com/gist/JingyunLiang/a5e3e54bc9ef8d7bf594f6fee8208533/swinir-demo-on-real-world-image-sr.ipynb)

> Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14~0.45dB, while the total number of parameters can be reduced by up to 67%.


### Dataset Preparation

This file has been truncated. show original

Also full error:

Traceback (most recent call last):
File “/data1/aradhana/KAIR/main_train_psnr.py”, line 253, in
main()
File “/data1/aradhana/KAIR/main_train_psnr.py”, line 173, in main
for i, train_data in enumerate(train_loader):
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/dataloader.py”, line 633, in next
data = self._next_data()
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/dataloader.py”, line 1345, in _next_data
return self._process_data(data)
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/dataloader.py”, line 1371, in _process_data
data.reraise()
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/_utils.py”, line 644, in reraise
raise exception
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py”, line 308, in _worker_loop
data = fetcher.fetch(index)
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py”, line 54, in fetch
return self.collate_fn(data)
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py”, line 265, in default_collate
return collate(batch, collate_fn_map=default_collate_fn_map)
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py”, line 127, in collate
return elem_type({key: collate([d[key] for d in batch], collate_fn_map=collate_fn_map) for key in elem})
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py”, line 127, in
return elem_type({key: collate([d[key] for d in batch], collate_fn_map=collate_fn_map) for key in elem})
File “/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/_utils/collate.py”, line 119, in collate
return collate_fn_map[elem_type](batch, collate_fn_map=collate_fn_map)
File "/home/aradhana/PycharmProjects/pythonProject/venv/lib/python3.8/site-packages/torch/utils/data/utils/collate.py", line 161, in collate_tensor_fn
out = elem.new(storage).resize(len(batch), *list(elem.size()))
RuntimeError: Trying to resize storage that is not resizable