pytorch-toolbelt

pytorch-toolbelt copied to clipboard

Detailed documentation is recommended

1

Thank you very much for making such a good library. It would be nice to have a more detailed document, for example, https://smp.readthedocs.io/en/latest/

Hengwei-Zhao96

Dice Loss/Score question

5

Hey Eugene, First of all, thank you for this very useful package. I'm transferring my environment from TF to Pytorch now and having your advanced losses is very helpful. However,...

JanSobus

0.5.2 Release

BloodAxe

Dice loss is smaller when computed on entire batch

1

## 🐛 Bug I noticed that when I compute the dice loss on an entire batch the loss is smaller than computing it singularly for each sample and then averaging...

AlessandroGrassi1998

AttributeError: module 'pytorch_toolbelt.losses' has no attribute 'JointLoss'

8

AttributeError: module 'pytorch_toolbelt.losses' has no attribute 'JointLoss'

likepd

## 🐛 Question about tiled inference Hello, thank you for your excellent work. I understand the advantage of tiled inference, but the way we use it confuses me. For each...

hoangkhoiLE

Hi, it was mentioned that we can get list of tensors, from fine (high-resolution, indexed 0) to coarse (low-resolution) feature maps. do you have example on how to do that?...

ramdhan1989

BloodAxe

Add MCCLoss implementation for binary image segmentation

2

Added loss function for binary image segmentation with the Matthews Correlation Coefficient (MCC). Based on [the reference implementation](https://github.com/kakumarabhishek/MCC-Loss) and [the paper](https://doi.org/10.1109/ISBI48211.2021.9433782).

kakumarabhishek