asappresearch / aum Goto Github PK

In examples/paper_replication/runner.py:
:param bool threshold_samples_set_idx: (default 1) Which set of threshold samples to use (based on index)
However in examples/paper_replication/small_dataset_aum.sh, the value of threshold_samples_set_idx was provided as 2.

Can current method be used for filtering mislabeled data in object detection task?

Hi. I am trying to install aum on ubuntu, using pip install -U aum. However, I am getting this error:
ERROR: Could not find a version that satisfies the requirement aum (from versions: none) ERROR: No matching distribution found for aum

I have torch: 1.9.1, torchvision: 0.10.1, pandas: 1.1.5.
Do you have any idea why this is happening?

Can the milestones generated for producing the results be made available?

HI, I just downloaded clothing 100k dataset from your link here "Download and untar the file here for all 5 datasets: https://drive.google.com/file/d/1rr2nvnnBMsbo1qcU3i3urJsDw86PJ9tR/view?usp=sharing". But, i found that there's a make_dataset.py in clothing 100k, so i wonder if extra noise has been added to these data, or it's only used to divided 100k from 1M?

Can I use AUM with tensorflow models? Any alternate repository?

Can it be used with Binary classification problem?