On GM dataset, hard training :

eheh this model is bloody good hum
As mentioned, I would recommend checking the values of the input arrays, here.
If that's the source of the error --> what about throwing an error if values are out of the range [0, 1] to avoid such error?
If that's not the source of the error... well... that's concerning eheh... so let's hope that's not the case (-:
```
im1 : max, min 2.0 0.0
im2 : max, min 1.0 0.0
````
I am relieved! Great news :')
Most helpful comment
I am relieved! Great news :')