Jaccard Loss Updated

[stalhabukhari]

#526

- What I did

Fixed the issue referenced, which concerns implementation of Jaccard Loss function.

- How I did it

I changed the axis argument of summation terms from only channels to all except channels, which is the correct way according to what I have studied. Consequently, this returns a per-channel loss vector for each sample.

- How you can verify it

The functionality and correctness demands (other than theoretical reasoning) verification by training via this loss function. I have used this as well as dice loss (also arranged in a similar configuration) for multiple training sessions which yield good performance.

---

This pull request fixes Issue #526 opened by me