Rank error in function misc.resolve_shape when trying to use flag upsample_logits about epos

[thodan]

Hi @kmkajak, as far as I remember, I always kept upsample_logits set to False, so unfortunately I am not familiar with this issue. Is it necessary to upsample the logits in your case?

[kmkajak]

Hi @thodan , I have a dataset where the object appears at high range variations, meaning it can be 5 - 30 meters from the camera, which can cause the target to only show a small amount of pixels on the output side. I was hoping that maybe I would not have to use an object detector to solve this problem and therefore I have been playing with hyperparameters to see what can be achieved without it. Upsampling to input image size seems to solve some of that as post-processing then has more information to work with.

I managed to get upsampling to work now by fixing the resizing commands to the appropriate rank and selecting the appropriate dimensions. However, I have yet to verify conclusively if the results are indeed correct. It SEEMS to work and a test run of training SEEMS to verify the changes.

The changes:

1. in the function add_obj_cls_loss within module loss:

if upsample_logits:
      targets_shape = misc.resolve_shape(targets,3)[1:3]

2. in the function add_frag_cls_loss within module loss:

if upsample_logits:
      logits = resize_logits(logits, shape[1:3])

3. in the function add_frag_loc_loss within module loss:

if upsample_logits:
      logits = resize_logits(logits, shape[1:3])

In conclusion, within add_obj_cls_loss the wrong rank (originally 4, now 3) was specified, and within all three loss functions too many dimensions were previously selected for resizing the feature maps.