v2.5.0
Datasets ⭐
EXAMPLE CODE
PPM-100 Dataset
Load the PPM-100 dataset in Python with one line of code. Portrait matting benchmark dataset. Stream PPM-100 while training models in PyTorch & TensorFlow.
Visualization of PPM-100 Dataset on the Activeloop Platform

PPM-100 Dataset

What is PPM-100 Dataset?

The PPM-100 (Photography Portrait Matting 100) Dataset is a portrait matting benchmark dataset that contains carefully collected images with respective masks. All the images are diverse and they contain full/half body poses. These images use their original background, and the image resolution is between 1080p and 4k.

Downloading PPM-100 Dataset in Python

Instead of downloading the PPM-100 in Python, you can effortlessly load it in Python via our open-source package Hub with just one line of code.

Load PPM-100 Dataset Subset in Python

1
import hub
2
ds = hub.load('hub://activeloop/ppm100')
Copied!

PPM-100 Dataset Structure

Data Fields

  • images: tensor containing the image
  • masks: tensor containing the image

How to use PPM-100 Dataset with PyTorch and TensorFlow in Python

Train a model on PPM-100 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 PPM-100 dataset with TensorFlow in Python

1
dataloader = ds.tensorflow()
Copied!

Additional Information about PPM-100 Dataset

PPM-100 Dataset Description

PPM-100 Dataset Licensing Information

All original portrait images in PPM are from Flickr and constrained by Flickr Creative Commons License (Commercial use & mods allowed).
All annotated alpha mattes in PPM are released under the Creative Commons Attribution NonCommercial ShareAlike 4.0 license.

PPM-100 Dataset Citation Information

1
@article{ke2020green,
2
title={Is a Green Screen Really Necessary for Real-Time Portrait Matting?},
3
author={Ke, Zhanghan and Li, Kaican and Zhou, Yurou and Wu, Qiuhua and Mao, Xiangyu and Yan, Qiong and Lau, Rynson WH},
4
journal={arXiv preprint arXiv:2011.11961},
5
year={2020}
6
}
Copied!