segmentation_models.pytorch

segmentation_models.pytorch copied to clipboard

was trying to use segmentation_models_pytorch with Unet++. I tried to look at the example at [HuBMAP - Pytorch smp Unet++](https://www.kaggle.com/code/nayuts/hubmap-pytorch-smp-unet). My understanding Unet++ returns 4 outputs (as part of deep...

alqurri77

I am trying to calculate weighted IoU but I do not understand how to pass class weights list to the function, thats my code: ``` tp, fp, fn, tn =...

alepistola

add generic precommit hooks

5

Adding some genric pre-commit hooks like trailing space removal...

Borda

use precommit for code linting

4

Calling pre-commit, which is defined already, instead of `flake8` and `black` separately Also, I would highly recommend installing [pre-commit bot](https://github.com/marketplace/pre-commit-ci), which would also update a PR with fixable on the...

Borda

Bump timm from 0.9.7 to 0.9.12

3

Bumps [timm](https://github.com/huggingface/pytorch-image-models) from 0.9.7 to 0.9.12. Release notes Sourced from timm's releases. Release v0.9.12 Nov 23, 2023 Added EfficientViT-Large models, thanks SeeFun Fix Python 3.7 compat, will be dropping support...

dependabot[bot]

Multiclass segmentation, some basic questions

5

Hello All, This is a great library which i am already using for couple of my projects. But I couldnt manage to make it work for multiclass segmentation. There is...

karaposu

Getting unexpected output after conversion of model to ONNX

2

Hi, I am trying to convert "timm-efficientnet-b0" to ONNX with mixed-precision and facing issues while validating the onnx model. In full-precision, outputs are approximately matching, but in mixed-precision, there are...

prateek9623

Multiclass Segmentation

8

Hi, I already used this framework for binary classification and it basically worked out of the box! Thanks @qubvel for this framework! Right now I want to use it for...

polijn

The `DecoderBlock` used in `UnetDecoder` hardcodes the upsampling factor to 2. This works for ResNet encoders however this is problematic for models like ConvNext which downsample by a factor of...

isaaccorley

When training on the server, the training is interrupted due to network problems. What should I do to continue training? Many thanks!

rssyhhu