sgraine / point-label-aware-superpixels Goto Github PK

Find a better name for flag (

Rename hard() to soft_to_hard() and rename the first argument to soft.

I think x is y and y is x in:

See https://goodresearch.dev/setup.html#create-a-pip-installable-package-recommended and https://github.com/QVPR/Patch-NetVLAD/blob/main/setup.py

This will require a split of the code into re-useable modules, and a script that calls those modules. The code is already well organised so this shouldn't be much of a deal.

Once that's done, we can publish the package automatically to PyPi for everyone to use (https://github.com/QVPR/Patch-NetVLAD/blob/main/.github/workflows/python-publish.yml) and then create a conda package, too.

Can the UCSD Mosaics dataset be sent to me? I contacted the author, but never got back to me

UCSD Mosaics dataset

Make sure to adhere to code licenses that you use within the code

Using something like https://github.com/QVPR/Patch-NetVLAD/blob/main/download_models.py

where is dataset.can't find it.Link has expired

• All packages are available on conda-forge, so let's stick to just a single channel. pyg is called (py?)torch_geometric on conda-forge.
• Installing dependencies can then be done in a one-liner: mamba create -n pointlabelspix python pytorch .... -c conda-forge
• Loosen version requirements (e.g. there is no need to pin to cuda=11.3).