Experimented with a U-Net variant to perform pixel wise multi-class classification to segment high resolution satellite imagery into land use types with potential applications in deforestation and flood monitoring. Developed with TensorFlow framework.
Hi, I saw you recently changed the dataset source from kaggle to the official website, however I note it is not actually available there and moreover there appear to be many unanswered requests for access on https://competitions.codalab.org/forums/15208/
You could suggest both locations with the above caveat.
Cheers
Thank you very much for sharing your implementation. I am learning a lot from your Land_Cover_Segmentation.ipynb file.
Unfortunately, I cannot find the file "Land_Cover_Segmentation.ipynb" to load the pretrained weights. Can you please help me?