Maxim Ziatdinov
The [deep image prior](https://dmitryulyanov.github.io/deep_image_prior) could be a powerful general method for unsupervised data cleaning, which is also not limited to only images. @tommycwong is currently exploring its limitations and potential...
Per SVK's suggestion, it is worth exploring if one can use an autoencoder (regular or variational) instead of PCA for the sliding-window-based image denoising originally written by @ramav87 . @saimani5...
The [semantic segmentation models](https://github.com/pycroscopy/atomai/blob/master/atomai/nets/fcnn.py) need to be extended to work with 3D data. This should be very straightforward - just introduce an option to select between 1D, 2D, and 3D...
We may want to add the following neural network architecture to nets/fcnn.py module: https://www.pnas.org/content/115/2/254 @aghosh92 Can you please take a look at it?
Currently, we have rather archaic [data augmentation pipelines](https://github.com/pycroscopy/atomai/blob/master/atomai/transforms/imaug.py), which employ a combination of scikit-learn and open-cv image processing functions. This leads to a significant slow down of the training with...
Passing a custom data loader in AtomAI models can be a useful feature. This would allow using e.g. Kornia data augmentation pipelines. It could look like this ```python3 segmodel =...
The ```utils.priors``` ([code](https://github.com/ziatdinovmax/gpax/blob/main/gpax/utils/priors.py)) have beed introduced to streamline the placement of priors over model parameters as well as to simplify the incorporation of prior mean functions. Several examples (in docstrings...
Per discussion in https://github.com/ziatdinovmax/gpax/discussions/57: Implement the batch acquisition methods that allow one to set a value for q such that the best combination of q points that jointly optimize the...
Currently, the ```manifold_traversal()``` in joint iVAE supports only plotting the 2D images. It needs to be expanded to 1D spectral data since there's an increasing interest in applying joint iVAE...
This should be easy to implement by using von Mises Fisher distribution (or the qualitatively similar [Projected Normal](https://docs.pyro.ai/en/dev/distributions.html#pyro.distributions.ProjectedNormal) distribution) instead of the Normal distribution for sampling a latent angle. One...