segmentation_models.pytorch

segmentation_models.pytorch copied to clipboard

Bumps [timm](https://github.com/rwightman/pytorch-image-models) from 0.4.12 to 0.6.7. Release notes Sourced from timm's releases. v0.6.7 Release Minor bug fixes and a few more weights since 0.6.5 A few more weights & model...

dependabot[bot]

Locked version of `timm` dependency

6

Is there a reason to depend on specific version of PyTorch Image Models `timm==0.4.12` instead of using something like `>=0.4.12` as a version specifier? The context for the question is...

ligaz

Update efficientnet-pytorch dependency

4

efficientnet-pytorch has been updated with numerous bug fixes and features, resulting in the [0.7.1 release](https://pypi.org/project/efficientnet-pytorch/0.7.1/). Can we update the efficientnet-pytorch version dependency to 0.7.1?

rover-debug

Best way to integrate with fastai?

3

@qubvel -- we've been chatting on the fast.ai Discord channel about how cool this lib is, and how much our community loves it! I'm wondering whether there might be ways...

jph00

Fix: soft_dice_score

1

Fix soft dice score I think the part where the denominator needs to be multiplied by 2 in front of the true positive is missing. As a result of my...

jeongHwarr

Multi-class segmentation can't predict classes other than 0, 1

2

Hello, Thanks for your great contribution. I used your model to train my images dataset, in which there are 5 classes. I tried Unet and DeepLabV3+ in different activation functions...

wfeng66

Problem with shapes for input

1

Hi, I currently try to get the UNet up and running and i have the following problem: My data is in the shape of [batch_size, 3, 800, 275]. This already...

flixmk

Why do `JaccardLoss`, `DiceLoss`, `TverskyLoss`, and `LovaszLoss` all have a parameter called `from_logits` to switch between logits and non-logits output, but `FocalLoss` doesn't? Apparently, it is hardcoded in the code...

xoiga123

can i use swintransformer bu smp?

1

zebrazjx

Throws AttributeError should a user chooses to utilize any loss function from 'segmentation_models_pytorch.losses'

jtzanetatos