Ross Barnowski

> Thank you for your reply. I am training on nuclear channel, how do i change the configuration The linked notebook on model training is likely the best place to...

Starting with deepcell v0.12.7, models and datasets are accessed via an authentication system in alignment with the [license terms](https://github.com/vanvalenlab/deepcell-tf/blob/master/LICENSE), particularly the provisions re: commercial use. The mods for the authentication...

@DorisxinDU Mesmer is still available in older releases without the need for an API key. If you are getting exceptions related to access tokens, that means you are in an...

Yeah there's certainly a larger discussion to be had about which data loading/generating functionality in `deepcell-tf` is still in use with the current pipelines, and what (if any) may be...

Are you defining a custom `weighted_categorical_crossentropy` function or using the one directly from the `losses` module? The traceback indicates that the problem appears to be due to a shape mismatch...

That's a good question. Until recently(-ish), Graphviz hadn't had many major releases but that has certainly changed: there have been 7 major releases in the last 2 years! In principle...

It's certainly possible, but would be quite clunky to do manually. The positions are specified according to the dot language spec; specifically the ["pos" attribute of edges](https://graphviz.org/docs/edges/). The typical way...

It looks like the warning originates from the NixOS test suite, not pygraphviz's. In this case I'd recommend adding a warnings filter to your test configuration to catch/ignore the runtime...

> The warning originates from graphviz itself when its run on macos 12, it's not nixos-specific. Yes I understand - I'm trying to determine whether there's an action item here....

I can't reproduce this with pygraphviz 1.10 or 1.11 on either Python 3.10 or 3.11. If I copy the contents `dot_file` from the previous post into a file called `cinn_subgraph.dot`...