All tests passed. However, when I try to run the code for training the model (4 - Train the Model) the kernel restarts after 30 sec. No error. I submitted the assignment without training (since all test cases were passed) the grader gave me 0.
The Kernel dies is a known issue and we are discussing this with Coursera. However, if your code is correct, you should pass the grader. What error/feedback grader give you?
Cell #3. Can’t compile the student’s code. Error: IndexError(‘list index out of range’)
I am assuming cell 3 is just to check out some masked and unmasked images. I didn’t add any code to it. And it (cell 3) runs perfectly on my machine.
The following hint in the notebook seems like it might be relevant to your situation. 
Check out the some of the unmasked and masked images from the dataset:
After you are done exploring, revert back to N=2. Otherwise the autograder will throw a list index out of range error.
Thanks! Felt really stupid 
If it’s any comfort, you are far from the first person to step on that landmine, which is why I recognized the scenario. Apparently the grader uses a much smaller dataset …
But there is a valuable lesson to be learned there: reading the instructions carefully may cost you a few more minutes, but it frequently can end up saving you a lot more time than that. 
2 Likes
Absolutely! I will try to increase the resolution of my perceptions and it will be computationally more expensive (will take a few more minutes).
Thanks a lot for taking the time to make this comment. I appreciate it!