nnUNet VS segmentation_models.pytorch

Now just run your images and masks in nnUNet to see if it works. https://github.com/MIC-DKFZ/nnUNet

I would also try the nnU-Net which should give state-of-the-art performance, and so will give you a good idea of what's possible with the dataset that you have: https://github.com/MIC-DKFZ/nnUNet

I used the nnUnet repo and their guide on using it on your own data

Hi all, Does anyone have experience with converting a nnUNet pytorch models into Tf using Onnx?

If you want my honest opinion, you should probably always use nnUnet as a baseline for any 3d segmentation tasks - https://github.com/MIC-DKFZ/nnUNet.

Not a "detection" but a "segmenting" CNN: https://github.com/MIC-DKFZ/nnunet

I ran some model fitting performance benchmarks on a 3D (medical) image segmentation UNET on various cloud providers and I am flabbergasted by the very low performance of V100 and A100 machines on vast.ai.

Also, I’d suggest considering switching to the segmentation-models library - it provides U-Net models with a variety of pretrained backbones of as encoders. The author also put out a PyTorch version. https://github.com/qubvel/segmentation_models.pytorch https://github.com/qubvel/segmentation_models

SMP offers a wide variety of segmentation models with the option to use pre-trained weights.

SMP has a lot of different choices for architecture other than unet, and a ton of different encoders. I like deeplabv3+/unet with regnety encoder, works well for most things https://github.com/qubvel/segmentation_models.pytorch

This basic example from segmentation models PyTorch repo would be good tutorial to start with. The library is very good, I like the unet, fpn and deeplabv3+ architectures with regnety as encoder https://github.com/qubvel/segmentation_models.pytorch/blob/master/examples/binary_segmentation_intro.ipynb

Sounds like a good semantic segmentation problem, I like this repo: https://github.com/qubvel/segmentation_models.pytorch

When i pass the CT-Scans and the masks to the Loss Function, which is the Jaccard-Loss from the segmentation_models.pytorch library, the value does not decrease but stay in the range of 1.0-0.9 over 50 epochs training on only one batch of 32 images. As far as I have understood, my network should overfit and the loss should decrease since I am only training on one batch of a small amount of images. However this does not happen. I also tried more batches with all the data over 100 epochs, but the loss does not decrease either obviously. Does anyone have an idea what I might have done wrong? Do I have to change anything when passing the masks to my loss function?

I know there is a decent one in segmentation models python (MA-Net: A Multi-Scale Attention Network for Liver and Tumor Segmentation)

You could also use qubvel's segmentation models if you would like to explore semantic segmentation.

Check out segmentation models pytorch, really easy to use, has a great interface.

Have you tried another implementation? For example: qubvel/segmentation_models.pytorch