rxjx

I tried it with miniconda: !pip install https://github.com/rxjx/condacolab/archive/refs/heads/main.zip import condacolab condacolab.install_from_url("https://repo.anaconda.com/miniconda/Miniconda3-py38_4.10.3-Linux-x86_64.sh") which seemed to work but after the restart condacolab.check() gave me this: --------------------------------------------------------------------------- AssertionError Traceback (most recent call last)...

Ah, looks like line 296 also needed to be changed.

OK, this seems to sort of work but I have to make every cell a bash cell else Colab seems to revert to its default python 3.7. I'm thinking some...

Does sample_weight only work for Tabular? Is there a similar option for TextPredictor?

Sorry, haven't found time to work on it at all. Work has been overloaded and the advent of LLMs has added to the load. Realistically, it doesn't look like I...

On autogluon 1.0, ubuntu 20, g5.xlarge --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) File [~/.local/lib/python3.11/site-packages/autogluon/multimodal/predictor.py:518](https://vscode-remote+ssh-002dremote-002brj5-005f2.vscode-resource.vscode-cdn.net/home/ubuntu/~/.local/lib/python3.11/site-packages/autogluon/multimodal/predictor.py:518), in MultiModalPredictor.fit(self, train_data, presets, tuning_data, max_num_tuning_data, id_mappings, time_limit, save_path, hyperparameters, column_types, holdout_frac, teacher_predictor, seed, standalone,...

Workaround: add a 'background' class and boxes for it spanning nearly the whole image. Not a great solution but does improve metrics.

I believe this can be resolved by installing the same version of CUDA as used in PyTorch. Your error log tells you that PyTorch is using 11.7 so you need...

That workaround doesn't work for `from autogluon.multimodal import MultiModalPredictor`