Weilin Xu

Hi @taeu-bahk , you would need to change the code for this. Please follow the implementation of our example models: https://github.com/mzweilin/EvadeML-Zoo/blob/master/main.py#L92

Hi @Gabriele91 , thanks for your interest in our work. We have made a detailed guideline to reproduce the results in the paper: https://github.com/mzweilin/EvadeML-Zoo/blob/master/Reproduce_FeatureSqueezing.md#6-evaluate-with-the-imagenet-dataset

Hi @Gabriele91 , the code we provided should generate exactly the same results, as we had verified three years ago before releasing the instructions. Please note that our code has...

No, the `datasets` in the import path refers to the `datasets` folder: https://github.com/mzweilin/EvadeML-Zoo/tree/master/datasets

I encountered the same issue. I hope this will be fixed soon @davidslater

@davidslater I think the root cause of my issue is that the `Lambda Stack` (https://lambdalabs.com/lambda-stack-deep-learning-software) which we use in our Lambda workstation deleted the `nvidia-container-runtime` package in a recent update...

> So in Docker 19+, you would just use runtime "runc" and the GPU would just work? Yes, if you have `nvidia-container-toolkit` and you specify something like `--gpus all` to...

We should also upgrade to the latest template: https://github.com/ashleve/lightning-hydra-template/compare/v1.4.0...v2.0.2 Notable changes - `pytorch_lightning` -> `lightning.pytorch` - use `lightning.fabric` for TPU - upgrade to hydra 1.3 - upgrade toolkits in `pre-commit`...

Changes in `pytorch-lightning ~= 1.6.5` -> `lightning ~= 2.0.2`. - `import pytorch_lightning as pl` -> `from lightning import pytorch as pl` - `LightningModule`: `training_epoch_end(self, outputs)` -> `on_train_epoch_end(self)`. - `LightningModule`: remove...

`lightning 2.0.2` depends on `torchmetrics=0.7.0`. However, we want to keep `torchmetrics == 0.6.0` because mAP is super slow in later versions. I hope `torchmetrics` will change the backend of mAP...