2

I have an MLP with 3072 input nodes which are for 1024 rgb pixels. My datasets is in an array with each row representing one image and looking like this:

[red_pix1, red_pix2, ..., red_pix1024, green_pix1, green_pix2, ..., green_pix1024, blue_pix1, blue_pix2, ..., blue_pix1024]

Each array value is an integer between 0 and 255.

My question is, before training the network, should I "normalize" my dataset by dividing each element by 255? That way, each input element would have values between 0 and 1. Is this better than having values between 0 and 255?

Sahand
  • 143
  • 1
  • 6
  • 3
    Yes, typically. You might want to center it too. This is to make it easier to initialize the network. – Emre Apr 05 '18 at 18:39

1 Answers1

3

The component values are often stored as integer numbers in the range 0 to 255, the range that a single 8-bit byte can offer,

Yes, If you divide by 255 the range can be described with a 0.0-1.0 where 0.0 means 0 (0x00) and 1.0 means 255 (0xFF). Normalization will help you to remove distortions caused by lights and shadows in an image.

Refer to this Normalize RGB

Anmol Kumar
  • 73
  • 6