liviaets / boxes_tightness_prior Goto Github PK

Todo

An output with one or more elements was resized since it had shape [2], which does not match the required output shape [1, 2]. This behavior is deprecated, and in a future PyTorch release outputs will not be resized unless they have zero elements. You can explicitly reuse an out tensor t by resizing it, inplace, to zero elements with t.resize_(0). (Triggered internally at ../aten/src/ATen/native/Resize.cpp:26.) return torch.stack(batch, 0, out=out)

Could you share the ATLAS dataset via google drive? Thanks a lot!

How to test the effect of the trained network on the test set？Thank you very much！

Hello, I'm doing the final thesis of my bachelor's degree about object detection and I'm trying to apply your method to get a mask instead of the bounding boxes.

I've been extracting the key parts of your code (bounds and losses) to adapt it to my code but there is something I don't understand.

When applying the LogBarrierLoss, the bounds are given by parameter, as they are calculated when loading the data from the dataloader for the whole image (the positive area for the whole image times the margins).

However, the inference is done for each slice of the image (I guess it's because of memory issues, otherwise I'd appreciate to know why). When applying this loss to the prediction, the predicted mask for that slice is compared with the bounds of the full image from what I understand, instead of the bounds for that slice.

What am I missing?

Thanks in advance and great job! It's being very helpful.

Dear Hoel,

Thank you for sharing your code. I have the following error when running your code:
AttributeError: module 'bounds' has no attribute 'BoxBounds'

Could you add the BoxBounds class in bounds, please?

Thanks!
Cheers

Also include latest makefile tricks for readability