0

I was trying to execute the code below in Google Colab for learning purposes.I got this message when i executed the following code.

Tensor("args_0:0", shape=(28, 28, 1), dtype=float32)

def normalize(images, labels):
  print(images)

  images = tf.cast(images, tf.float32)
  print(images)

  images /= 255
  print(images)


  return images, labels

I am trying to understand what this message means but I am not able ti understand it. Tried searching in web , but couldn't find much resources. Can anyone say what this statements mean?

stephen_mugisha
  • 889
  • 1
  • 8
  • 18
Kulothungan Senthil
  • 77
  • 1
  • 10
  • It's the result of `print(images)`. `images` is a `Tensor` object, with name `"args_0:0"`, of shape `(28,28,1)` and of type float. – GPhilo Oct 15 '19 at 09:21
  • Thanks.I also got the this statement as well. Tensor("truediv:0", shape=(28, 28, 1), dtype=float32) Here does "truediv:0" also refers the name of the tensor ? – Kulothungan Senthil Oct 15 '19 at 09:34
  • @KulothunganSenthil truediv (true division) is the name of the division operation performed at ```images /= 255``` – stephen_mugisha Oct 15 '19 at 11:07

1 Answers1

0

This output means that your images are a tensor of shape (28,28,1) and type float32 the 1 in (28,28,1) is a single byte for gray-scale meaning you have gray-scale images (basing on your code)

stephen_mugisha
  • 889
  • 1
  • 8
  • 18