segmentation_models.pytorch

segmentation_models.pytorch copied to clipboard

examples folder is out of date

1

Binary segmentation works, with some warnings. Cars segmentation flat out refuses to work. The smp API has changed quite a lot and the example uses the old API. That's unfortunate,...

FlorinAndrei

Support for continuous output?

2

Thank you for creating this great package! My question might not be very closely related to image segmentation, but I'll ask anyway: is it possible to use your package for...

ma-sadeghi

Hello! Let's say I define a segmentation model as follows. Is there a way that I can access multiple prediction layers from different levels of the decoder so that I...

meshghi

issue generating models with mix vision transformer encoders

6

I noticed that Mix Vision Transformer encoders are now listed as available. I was trying to generate a unet model with one of these encoders, but have been getting an...

K-D-Gallagher

Substantive differences between pytorch & tensorflow versions of FPN?

3

Reviewing https://github.com/qubvel/segmentation_models.pytorch/blob/master/segmentation_models_pytorch/decoders/fpn/model.py and comparing it to https://github.com/qubvel/segmentation_models/blob/master/segmentation_models/models/fpn.py a couple of things stand out: * The pytorch FPN produces a `[classes, h/4, w/4]`-sized intermediate result that is then upsampled bilinearly to...

jxtps

I am just getting a list of supported networks. Is there a way for the network to use HRNetv1/v2?

sarmientoj24

Requesting to merge auxiliary CNNs support back to main

1

This PR is to request to merge auxiliary CNNs support (for the Unet) back to main. If `auxiliary_cnns = True`, the segmentation model will return auxiliary CNN outputs as per...

bariskanber

Got this error when initializing `Unet` model with the `aux_params`. Exception happens In the `TrainEpoch.batch_update` while calling `self.model.forward(x)` which relates to the `SegmentationModel.forward`. In the `SegmentationModel.forward` we can see inconsistent...

bvsn

sarmientoj24

Runtime Error on dice loss But model calculating loss while training

6

RuntimeError: cannot reshape tensor of 0 elements into shape [0, 1, -1] because the unspecified dimension size -1 can be any value and is ambiguous  But how the loss...

MUKILAN-2003