Kernel dying while training

Course Q&A Deep Learning Specialization Convolutional Neural Networks
, ,
1

When creating a post, please add:

  • Week # must be added in the tags option of the post.
  • Link to the classroom item you are referring to:
  • Description (include relevant info but please do not post solution code or your entire notebook)

Good evening Mentors and everyone,
Kindly help a brother. Kernel keep dying while training. What could be the problem?

2

Does your code contain an infinite loop?
Did you add a lot of debugging print() outputs to the notebook?
Both of these can make the kernel stall-out.

3

Good morning TMosh,

I worked according to the instructions provided in the notebook. Nothing more! Was training a ResNet. Followed all the instruction to the letter.

4

The thread is tagged for both Week 2 and Week 4. Are you having the same issue in both weeks, but not in Week 3?

5

And you’re sure there are no bugs in your code like the infinite loops or unnecessary print statements that Tom mentioned?

Also note that if you are having this problem on multiple notebooks at or around the same time, it could also be caused by “bad weather” in the Cloud. The servers may be overloaded in general or the particular VM image running your various Docker instances may be overloaded. You could try closing all your active notebooks, doing the old “therapeutic re-login” to your Coursera account and opening them again.