Home > OS >  parameters of tf.keras.layers.Rescaling: scale, offset
parameters of tf.keras.layers.Rescaling: scale, offset

Time:11-05

To rescale an input in the [0, 255] range to be in the [0, 1] range, you would pass scale=1./255.

To rescale an input in the [0, 255] range to be in the [-1, 1] range, you would pass scale=1./127.5, offset=-1.

I understood the above example.

but, I can't understand this code

tf.keras.layers.Rescaling(scale=4.0, offset=1.0)

As above, if I pass the scale and offset values ​​as above, I wonder what the range of the input value will be, and I'm curious about the meaning of scale and offset.

CodePudding user response:

Rescaling is done by scale*inputs offset.

In this case for

[0,255] range it would give 4*[0, 255] 1 : [1, 1021]
  • Related