Benjamin Weinstein

NEON has added some test files.

I'll need to think about this more, but I believe this is intended. I'll add a note to the front of the readME, but not all data in the evaluation/lidar...

``` # Multi-class models from deepforest import main from deepforest import get_data import pandas as pd import os import tempfile m = main.deepforest(num_classes=3, label_dict={"label1": 0, "label2": 1, "label3": 2}) #...

https://github.com/arc53/DocsGPT General idea of labeling the docs.

@henrykironde this will be an issue i'll connect to alive/dead model.

Sure. I don't have any expertise in this area. I'm not even sure how needed it is given all the in browser language translation. We would need to survey users...

Worth exploring slicing inference. https://colab.research.google.com/github/obss/sahi/blob/main/demo/inference_for_torchvision.ipynb

Can we reverse this question? What's your goal and use case and then we can find the best solution for you.

Given that we don't have a use case yet, its difficult to know what the pros and cons are here. I think the simplest thing is here: https://github.com/weecology/DeepForest/blob/906730656579ed215d69d10e0757cf5dcceeb759/deepforest/utilities.py#L143, we need...

Yes, these are different. check_release relates to our underlying (poor) choice of how to store the model. https://github.com/weecology/DeepForest/issues/380 Especially during unit tests, we often hit github API query limits. update=True...