Hello Saif.
YES it worked. Trying at night got me the code working. It looks like it is a platform resources issue, or maximum response time, or something like that.
Rebooting the kernel doesn’t seem to help. It looks like it is just a student bottleneck.
Thanks for the help.
Glad to know that 
I had this problem. The kernel kept dying when trying to train the model. It worked when I re-ran only the important code (i.e. no testing code/code to view images). Whether this was the reason or it was a fluke, I don’t know.
Coursera is aware of the problem and is said to be working on it.
Good trick… Its a memory issue and Coursera is looking at it…
may i know if there is any update on this topic? i’ve tried below 3 tips and they didn’t work.
- Are you sure you didn’t add any print statements in the inner loops that are causing the output to be more voluminous than necessary?
- Try doing “Kernel → Restart and Clear Output, and then run all.
- It could be random “bad weather in the cloud”. It means that server is busy. You may try later when server isn’t busy. Try tomorrow.
haha this works a little - the training process started, but died again after several seconds.
I don’t know when this Kernel dying error will be resolved. If you completed all the exercises, I suggest submitting your assignment as the grader doesn’t need the output of your code.
This resolved the kernel dying issue. Thanks!
Still the kernel error persists (C4 W2 A1).
I don’t have any print statements or other code, I have strictly sticked to the lines of code the exercise requires. Even after kernel restarting. It is 100% a Coursera platform issue and considering the remaining assignments it is very frustrating not to see the model working. When are the peak hours? I am located in Greece.
Oh! I am sorry that you are still facing this issue.
Currently, I do not have any update regarding this, as one of our staff you discussed this issue with Coursera is on vacation. Can you please contact Coursera directly? Check this on how to contact them.
FYI the dead kernel issue still persists (C4 W2 A1)
Same situation as Charalampos above.
That happens sometimes with some users. If your code is correct, try running your code at different time.
Go to the Files menu, and report back on the size of your notebook file.
Downloading the ipynb, it’s 97 KB. Was that the info you needed?
Yes, thanks.
The possible issue I was thinking of doesn’t apply to a notebook file that small.
Note: I re-tested my solution (C4 W2 A1), which previously worked 100%, and also got the “dead kernel” issue.
My notebook crashed during “model.fit()” for ResNet50.
However, after I used “Help->Reboot server”, I was able to submit my notebook for grading successfully.
I tried again and it worked this time, using this sequence. I don’t know if it was helpful, or if I just got lucky:
- “Kernel → Restart & clear output”
- “File → Save and checkpoint”
- “Cell → Run all”
Hi @msmart,
Thank you for letting us know. Indeed, this issue is back. I’m seeing the same on my end.
For now, if you are passing the all exercises above, you can submit your assignment for grading. The autograder doesn’t need anything beyond the last exercise. So, if your code is correct, you should get full grade.
I’ll have this issue looked into.
Thanks,
Mubsi