found a small formal bug

[mg64ve]

Hi @vincent-leguen,

nice work, congrats.
I am still studying the way you calculate DILATE loss.
However I think there is a small formal bug in main.py at row 78:

bath_size, N_output = target.shape[0:2]

should be:

batch_size, N_output = target.shape[0:2]

it is a small typo, but I do't think it impacts the normal flow of the code.
Cheers

[vincent-leguen]

Hi @mg64ve ! Yes thank you for finding out this bug, I have corrected it. It had indeed no impact since batch_size was already defined earlier.

[mg64ve]

You are welcome @vincent-leguen.
If you have 5 mins I would appreciate if you could help me to understand one thing.
At line 75 in main.py you get breakpoints:

inputs, target, breakpoints = data

and at line 120 you get breaks:

test_inputs, test_targets, breaks = next(gen_test)

How do you use this values? I don't see any use of them.
Could you please clarify?

[vincent-leguen]

Hi @mg64ve , I added these additional breakpoints when I wanted to add new external metrics for the paper (here the Hausdorff distance). But for simplicity of the published code, I removed the computation of external metrics so the breakpoint piece of code is not useful here.

[mg64ve]

Ok thanks @vincent-leguen