maxkazmsft comments

Results 14 comments of


                                            maxkazmsft

Missing license

+1 please add license

run time error on MacOS installed via conda

I have a similar error with the same steps ``` [I 21:26:06.790 NotebookApp] Creating new notebook in [I 21:26:07.562 NotebookApp] Kernel started: 5158e60d-c203-4e37-b5fe-418b63000f2f, name: xcpp17 [W 21:26:07.571 NotebookApp] 404 GET...

run time error on MacOS installed via conda

Posted a question on SO about this https://stackoverflow.com/questions/68534960/how-to-fix-a-xeus-cling-kernel-runtime-error-on-mac-os-c-jupyter-kernel-std

add unit test to check that each input slice has uniform distribution - facilitates uniform sampling of training data for better model accuracy

We should re-scope this issue - there should be a tolerance for sampling synthetic checkerboard training data where with a large enough number of samples the distribution of two classes...

Support SEGY files that do not have geometry - consistent support of segy files

> > > The current code uses segyio.tools.cube() to extract a volume of data from segy files that can easily be chuncked up. However, most segy files do not have...

[Draft] Modify the Dutch F3 notebook to add the ability for the end user to pick any model for a given dataset, this will help the end user with their experimentation & comparision

> > > Does this mean to provide canned config files for all models or a notebook widget to pick the mode? The latter I would think. Also let me...

automate update of pre-run notebooks (linked from README) before release - allows the user to view up to date pre-run notebooks (faster repo exploration) without running the repo

- change .ipynb and .HTML notebook links in README to point to a permanent static location - add a build, triggered by PR to master branch only which runs the...

automate update of pre-run notebooks (linked from README) before release - allows the user to view up to date pre-run notebooks (faster repo exploration) without running the repo

HRNet is a slow model to train - pre-reqs should be https://github.com/microsoft/seismic-deeplearning/issues/172 https://github.com/microsoft/seismic-deeplearning/issues/138

notebook showing how to score 3D data with one of pre-trained models - facilitates showcasing 3D models to the user

Pre-requisites are https://github.com/microsoft/seismic-deeplearning/issues/159 and https://github.com/microsoft/seismic-deeplearning/issues/158

create HRNet Azure ML notebook based on existing HRNet notebook - showcases the use of Azure ML

Current ADO feature carried to github