CSAILVision / semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
http://sceneparsing.csail.mit.edu/
BSD 3-Clause "New" or "Revised" License
4.95k stars 1.1k forks source link

What's the difference between ADE20K and ADEChallengeData2016? #290

Open Sinodaiiii opened 8 months ago

Sinodaiiii commented 8 months ago

I've used the download_ADE20K.sh download the dataset, the data downloaded is ADEChallengeData2016 with 20210 training images. The official link of ADE20K shows that the training set of the ADE20K contains 25574 images.

So what's the differences between ADE20K and ADEChallengeData2016? Why they have different training set?