0

Running "Get started with TensorFlow 2.0 for beginners" from https://www.tensorflow.org/beta/tutorials/quickstart/beginner in Colab https://colab.research.google.com/github/tensorflow/docs/blob/r2.0rc/site/en/r2/tutorials/quickstart/beginner.ipynb works fine and only takes a few seconds. The output generated is:

output in colab

But I would like to run it locally. I extracted the python code from the notebook. When started, the output does not look as intended (problem with backspace?) and the ETA (estimated arrival time) keeps growing and the program does not finish within reasonable time.

console output

Can you please help me out finding what the problem is?

user2757572
  • 463
  • 1
  • 4
  • 9

1 Answers1

1

The tutorial on Colab uses CPU by default, so make sure you are not using GPU there. If not then look at your CPU RAM power, on colab, CPU has 13 GB RAM approx. Here are the specs of colab. The problem is mostly because of the CPU power.

Rishabh Sahrawat
  • 2,437
  • 1
  • 15
  • 32
  • How would I make sure to avoid GPU? Also the problem persists even if I drastically reduce the amount of hidden neurons, for example from 128 to 32. – user2757572 Sep 24 '19 at 15:47
  • You need to do Runtime>>Change Runtime Type>>Hardware selector to None. This you will find in the top left corner of the Colab notebook. As I said this should not be happening, there must be some memory that is changing this behaviour. Try running the same example on different local machine, if the behaviour is still the same then maybe raise an issue on Tensorflow. – Rishabh Sahrawat Sep 25 '19 at 06:37
  • No, you misunderstood. Im running locally not in colab. – user2757572 Oct 02 '19 at 06:44