Tramac / awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Apache License 2.0
2.79k stars 580 forks source link

Dataset Directory Structure #210

Open bbbts opened 2 weeks ago

bbbts commented 2 weeks ago

Hi, Could you please provide the way your dataset is arranged/ structured in your directory (i.e. train data, validation data and test data). I tried running the downloading script to download the ade20k dataset but I am running into some errors. Hence, I downloaded the ade20k dataset manually from Kaggle. Please kindly help how I should arrange them in my directory that will adhere to the train.py and eval.py file in the 'scripts' folder. Let me know how I can arrange the test images as well. Thanks! This is how I have kept it currently.

ssss

And this is how I have edited the ade.py file in dataloader folder -

image