https://colab.research.google.com/drive/1J_cuV6OPJ7FlVSj7WRxNzf-c02uREEf2
If you put (28,28,1) then you will resolve the error while creating the CNN model.
But when you will compile you will again get a error
Saying the training data has 1 less dimension.
Lastly Can U pls guide where to look for the answers posted by TAs in efficient manner.
Because I have doubts in alot of section and it would be really cumbersome to visit each topic to read ans of the doubts asked earlier
Error when checking input: expected conv2d_2_input to have 4 dimensions, but got array with shape (60000, 28, 28)
Kindly refer to block 10 and 11 …and tell me if I remove the temporary modification I have made…the code doesnt work or shows ERROR
Hey @chiragwxN, yes you have made the correct deicssion,
Xtrain=Xtrain.reshape(-1,28,28,1)
The last 1 is due to the reason that image has only one channel, i.e. ‘gray’. You could always visist my doubts section to refer to the previously asked doubts. Also whenever any TA responds to your doubt, you will recieve a mail notification as well in gmail. You could keep track of that as well.
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.