Andrew Scouten

This might not be what you mean, but I usually just go to the [backbones](https://github.com/open-mmlab/mmsegmentation/tree/main/mmseg/models/backbones) folder. Most backbones that I have encountered have the paper in the comment of the...

Following the stacktrace, it's in `data_preprocessor`. Only `size` or `size_divisor` should be set in your data_preprocessor config. You likely set both. Check your config in your `work_dirs` to find out...

If you're doing binary segmentation the [FAQ](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/notes/faq.md#how-to-handle-binary-segmentation-task) might help. I say this as your `num_classes=1`, and you are using softmax (`use_sigmoid=False`) which can be odd for binary segmentation. Something similar...

It's odd, as it looks like the changes for [transforms.py](https://github.com/open-mmlab/mmyolo/blob/main/mmyolo/datasets/transforms/transforms.py) from the original PR stayed in main as well in some form or fashion.

Thank you for your kind reply! With this help, I was able to google more and get a better understanding.

Related to https://github.com/open-mmlab/mmyolo/pull/895 and https://github.com/open-mmlab/mmyolo/pull/636

Another ambiguous error: ```python import fastdup fd = fastdup.create(input_dir=my_path) fd.run( annotations=df, run_stats=True, run_advanced_stats=True, verbose=True, ) fd.explore() ``` ``` ERROR:vl.fastdup.fastdup.fastdup_runner.run:input_dir is required for the first run ``` Solved with: ```python fastdup.explore(...