Skip to main content

Downloading sky image datasets for pytorch applications

Project description

skyimages

Download sky images for solar power forecasting as pytorch-ready datasets.

Installation using pypi

From release v0.0.1, skyimages will be installable via pip:

pip install skyimages

Installation using github

Download skyimages from github. Change the CWD to the download folder skyimages/ and install the package using pip.

git clone git@github.com:FlorianK13/skyimages.git
cd skyimages
pip install .

Getting started

To download the dataset SKIPP'D (source) and use it as a pytorch torchvision dataset, run the following code in python

from skyimages.dataset import SKIPPDDataSet
import torch


traindata = SKIPPDDataSet(download=True)
testdata = SKIPPDDataSet(download=True, train=False)

trainloader = torch.utils.data.DataLoader(
    traindata, batch_size=200, shuffle=True, num_workers=0
)
testloader = torch.utils.data.DataLoader(
    testdata, batch_size=20, shuffle=False, num_workers=0
)

Running code on Windows

If you use windows, wrap your code in the if __name__ == '__main__' clause to support multiprocessing. Here you can find more info on this issue.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

skyimages-0.0.2.tar.gz (7.5 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page