I retrained a L-RASPP(Light-Reduced Astrous Spatial Pyramid Pooling) model to detect water level using Pytorch.
I used the WSOC dataset containing 496 images for training and 278 images for testing. The ROC score was close to 1 by epoch 25.
I also tried out 100 epochs just in case to see whether it would improve or not. It turns out the model with only epochs 25 made more better prediction
Unfortunately, I can’t ACTUALLY create dependable results with this model, so I’ll have to do something about that.
