This is great! One thing I did was add something to handle tensors with negative values (e.g. one that had been 0 mean scaled at some point):
# Push positive before scaling:
tensor_vec.add(tensor_vec.min() * -1)
This is great! One thing I did was add something to handle tensors with negative values (e.g. one that had been 0 mean scaled at some point):
# Push positive before scaling:
tensor_vec.add(tensor_vec.min() * -1)