v2.5.0
Datasets ⭐
EXAMPLE CODE
RESIDE dataset
Load the RESIDE dataset fast. Stream data while training models in PyTorch & TensorFlow. Visualize RESIDE a dataset of both synthetic & real-world hazy images.
Visualization of Reside dataset on the Activeloop Platform

RESIDE dataset

What is RESIDE Dataset?

The REalistic Single Image DEhazing (RESIDE) dataset is a new large-scale benchmark dataset that includes both synthetic and real-world hazy photos. RESIDE is organized into five subsets. Each subset provides serves a different training or evaluation purpose. RESIDE highlights diverse data sources and image contents.

Download RESIDE Dataset in Python

Instead of downloading the Reside dataset in Python, you can effortlessly load it in Python via our open-source package Hub with just one line of code.

Load RESIDE Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/reside")
Copied!

RESIDE Dataset Structure

RESIDE Data Fields

  • image: tensor containing the image.
  • labels: tensor to distinguish between 'hazy', 'trans' & 'clear'.

RESIDE Data Splits

How to use RESIDERESIDE Dataset with PyTorch and TensorFlow in Python

Train a model on RESIDE dataset with PyTorch in Python

Let's use Hub's built-in PyTorch one-line dataloader to connect the data to the compute:
1
dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)
Copied!

Train a model on RESIDE dataset with TensorFlow in Python

1
dataloader = ds.tensorflow()
Copied!

Additional Information about RESIDE Dataset

RESIDE Dataset Description

RESIDE Dataset Curators

Li, Boyi and Ren, Wenqi and Fu, Dengpan and Tao, Dacheng and Feng, Dan and Zeng, Wenjun and Wang, Zhangyang

RESIDE Dataset Licensing Information

Hub users may have access to a variety of publicly available datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have a license to use the datasets. It is your responsibility to determine whether you have permission to use the datasets under their license.
If you're a dataset owner and do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thank you for your contribution to the ML community!

RESIDE Dataset Citation Information

1
@article{li2019benchmarking,
2
itle={Benchmarking Single-Image Dehazing and Beyond},
3
author={Li, Boyi and Ren, Wenqi and Fu, Dengpan and Tao, Dacheng and Feng, Dan and Zeng, Wenjun and Wang, Zhangyang},
4
journal={IEEE Transactions on Image Processing},
5
volume={28},
6
number={1},
7
pages={492--505},
8
year={2019},
9
publisher={IEEE}
10
}
Copied!

RESIDE Dataset FAQs

What is the RESIDE dataset for Python?

The RESIDE (REalistic Single Image DEhazing) dataset is a popular benchmark consisting of both synthetic and real-world hazy images. The RESIDE dataset showcases a large range of data sources and image contents. It is divided into five subsets, each serving different training or evaluation purposes.

How can I use RESIDE dataset in PyTorch or TensorFlow?

You can stream the RESIDE dataset while training a model in PyTorch or TensorFlow with one line of code using the open-source package Activeloop Hub in Python. See detailed instructions on how to train a model on RESIDE dataset with PyTorch in Python or train a model on RESIDE dataset with TensorFlow in Python.