Layne

Hi, regarding your questions: 1) I am not familiar with tabular data, but I think it is worth a try if your goal is classification and you were using the...

In my opinion, the data modality is not a crucial problem for SAT. Say you have an input data $x$ of any modality and a deep model $f(\cdot)$ that produces...

Still got the same error when generating adversarial examples using backprop. Any updates?

@shoaibahmed Thanks for your code snippet! BTW, I adapt the `add_fp16_bn_wrapper` function to make it compatible with sync bn: ```python def add_fp16_bn_wrapper(model): for child_name, child in model.named_children(): classname = child.__class__.__name__...

Hi, @danielchyeh Have you tried fixed predictor lr? If you did, could you please share your results?