Hey Andrej! Cool repo :+1: This is a small change that effectually computes model(x - 0.5) in visualize.ipynb. Otherwise model(x) - 0.5 looks like this
After the change we get
And since we always want to normalize (e.g. before training, validating, or visualizing), I just moved the normalization/inmapping back to the data loader.
Hey Andrej! Cool repo :+1: This is a small change that effectually computes
After the change we get
And since we always want to normalize (e.g. before training, validating, or visualizing), I just moved the normalization/inmapping back to the data loader.
model(x - 0.5)invisualize.ipynb. Otherwisemodel(x) - 0.5looks like this