v2.5.0
Datasets ⭐
EXAMPLE CODE
DomainNet Dataset
Load the DomainNet dataset in Python with one line of code. 345 classes of objects in six different domains. Stream DomainNet datasets while training ML models.
Visualization of the Domainnet Clipart Train dataset on the Activeloop Platform

DomainNet dataset

What is DomainNet Dataset?

The DomainNet dataset comprises of common objects in six different domains. There are 345 classes of objects in all sectors of DomainNet. Bracelets, aircraft, birds, and cellos are among the 345 objects within the dataset. A more detailed breakdown of the six different domains is presented below.

Different DomainNet Datasets

  • DomainNet Clipart: a clipart image collection
  • DomainNet Real: photography and real-world imagery
  • DomainNet Infograph: infographics with specific objects
  • DomainNet Sketch: sketches of specific things
  • DomainNet Paint: creative renderings of objects in the form of paintings
  • DomainNet Quickdraw: drawings by participants from across the world of the game "Quick Draw!"

Download DomainNet Datasets in Python

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

Load DomainNet CLIPART Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-clip-train")
Copied!

Load DomainNet CLIPART Dataset Testing Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-clip-test")
Copied!

Load DomainNet INFOGRAPH Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-info-train")
Copied!

Load DomainNet INFOGRAPH Dataset Testing Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-info-test")
Copied!

Load DomainNet REAL Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-real-train")
Copied!

Load DomainNet REAL Dataset Testing Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-real-test")
Copied!

Load DomainNet PAINT Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-paint-train")
Copied!

Load DomainNet PAINT Dataset Testing Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-paint-test")
Copied!

Load DomainNet SKETCH Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-sketch-train")
Copied!

Load DomainNet SKETCH Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-sketch-test")
Copied!

Load DomainNet QUICKDRAW Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-quick-train")
Copied!

Load DomainNet QUICKDRAW Dataset Testing Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/domainnet-quick-test")
Copied!

DomainNet Dataset Structure

DomainNet Data Fields

  • images: tensor containing the face image.
  • labels: tensor to identify the type of object.

DomainNet Data Splits

How to use DomainNet Dataset with PyTorch and TensorFlow in Python

Train a model on DomainNet 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 DomainNet dataset with TensorFlow in Python

1
dataloader = ds.tensorflow()
Copied!

Additional Information about DomainNet Dataset

DomainNet Dataset Description

  • Paper: Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo Wang Our paper is accepted by ICCV 2019 as an Oral Presentation!
  • Point of Contact: N/A

DomainNet Dataset Curators

Peng, Xingchao and Bai, Qinxun and Xia, Xide and Huang, Zijun and Saenko, Kate and Wang, Bo

DomainNet 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!

DomainNet Dataset Citation Information

1
@inproceedings{peng2019moment,
2
title={Moment matching for multi-source domain adaptation},
3
author={Peng, Xingchao and Bai, Qinxun and Xia, Xide and Huang, Zijun and Saenko, Kate and Wang, Bo},
4
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
5
pages={1406--1415},
6
year={2019}
7
}
Copied!

DomainNet Dataset FAQs

What is the DomainNet dataset for Python?

The DomainNet was collected and annotated by the largest UDA dataset with six distinct domains and approximately 0.6 million images distributed among 345 categories. DomainNet was created to address the gap in data availability for multi-source UDA research.
How to download the DomainNet dataset in Python?
You can load DomainNet dataset fast with one line of code using the open-source package Activeloop Hub in Python. See detailed instructions on how to load DomainNet dataset training subset and testing subset in Python.

How can I use the DomainNet dataset in PyTorch or TensorFlow?

You can stream DomainNet 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 DomainNet dataset with PyTorch in Python or train a model on Domainnet dataset with TensorFlow in Python.