nobrainer
nobrainer copied to clipboard
neuronets
A framework for developing neural network models for 3D image processing.
To approximate something like "stylized imagenet", let's try to permute the grayscale data in the features volumes. Hopefully this will cause the models to rely more on the shape of...
"boundary loss for highly unbalanced segmentation" https://arxiv.org/abs/1812.07032
In the colab example for training a 3D GAN, will the conversion to TFrecord include resizing to power of 2 dimensions in each direction? Most datasets do not have volumes...
Hi folks, not sure if my question makes sense, but I thought I give it a try. I was wondering if a fetcher for `pre-trained model weights` could be added...
currently it seems all the predict functions assumes that the models are trying to predict an image. the generic functions should also be able to determine if a model output...
nobrainer tests on macOS and windows in github_action CI workflow are failing.
Ahoi hoi folks, I just stumbled across [nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation](nature.com/articles/s41592-020-01008-z) and thought it might be interesting wrt `nobrainer`. The GitHub is [here](https://github.com/mic-dkfz/nnunet) and...
Nibabel has a function _almost_ equivalent to `mri_convert --conform`: https://github.com/nipy/nibabel/pull/853 The main difference is that the nibabel version does not implement histogram normalization. The histogram normalization code is translated to...
following the keras api, let's add a module to fetch datasets for training. we can again use datalad to distribute public datasets for tutorials, tests, and training. i would suggest...
Implement methods in https://bmcmedimaging.biomedcentral.com/articles/10.1186/s12880-015-0068-x#Sec4 in tensorflow. I have implemented most of them, but some were giving me issue. I think this would be a useful addition because these methods will...