Cory Cornelius

I'm not sure why the colab link disappeared. Maybe @shangtse knows? You can also run the notebook in the repository on your local machine or upload it to colab on...

> @dxoigmn Can you generate an image for any given hash (preimage attack) or do you need access to the source image first (second preimage attack)? Not sure. My sense...

This is a nice datapoint. What was the simple NN model you used? I'm wondering if we could learn something about which bits of the hash are biased.

OmegaConf (which is what Hydra uses under the hood for configuration) accomplishes this via variable interpolation: https://omegaconf.readthedocs.io/en/2.2_branch/usage.html#variable-interpolation

Ideally both.

The reason we used `torchmetrics == 0.6.0` is because `MeanAveragePrecision` is super slow in newer versions. It looks like they're finally going to revert back to the original implementation that...

Should this be closed @mzweilin?

> > Why is this necessary? Usually you want to log the actual loss you compute gradients of? > > The trend could be confusing in the past. While we...

Do you think we should wait to merge this until we change MART to bound inputs between `[0, 1]` instead of `[0, 255]`? See #70.

See: https://pytorch.org/docs/stable/data.html#torch.utils.data.default_collate