Amazon Rainforest dataset for semantic segmentation

This database contains images used for the semantic segmentation of forest and non-forest areas from a fully convolutional neural network U-Net .

1. Training dataset: it contains 30 GeoTIFF images with 512x512 pixels and associated PNG masks (forest indicated in white and non-forest in black color).

2. Validation dataset: it contains 15 GeoTIFF images with 512x512 pixels and associated PNG masks used for U-Net validation step.

3. Test dataset: it contains 15 GeoTIFF images 512x512 pixels for testing.