C1_W3_Assignment final

[Deepti_Prasad]

based on your latest share of grader output which provides information which codes were incorrect,

for UNQ-C1 grade function code correction refer the below link, your code for one hot label, needs to use the keras categorical function and Use np.moveaxis function to check the dimension, numerical are mentioned correctly in the brackets(below link comments should help you understand how both codes need to be corrected

W3 assignment - Grading

@ardonp you didn’t do this correction mentioned in my first comment response to your debugging. Please read the comments carefully and follow each of them one by one. I understand the discomfort, but debugging requires patience, attention to detail and more self-reflection. The instructions mentions to change the dimension of X and y from the x dim, y dim, z dim, number of channels to num , x dim, y dim, z dim So mention X, (3, 0, 1, 2) is incorrect Instructions before grade cell mentions …

W3 assignment - Grading

hi @ardonp You seem to have edited codes and instructions between the assigned markers ###START AND END CODE HERE### which you are not suppose to do. First get a fresh copy and re-do the assignment(make sure you saved a copy of your old file so you can compare them for your learning), and then mention codes only between the assigned markers ###START AND END CODE HERE### Codes which required corrections: then for the first code line where randomly sample the sub-volume, You are suppose to …

For UNQ-C3 codes correction, your code implement needs to be the way you implemented in UNQ-C4. Do not include 2 in denominator for the last equation while calculating single soft dice coefficient. 2 need to need to be mentioned for the dice_numerator. compare the code implement with UNQ_C4 codes you wrote. Also in UNQ_C3 you used tf.reduce (incorrect function) where as in c4 you used K.sum. You are suppose to use the same function you used in UNQ_C4 i.e. K.sum.

Let me know if issue still persist.