Keunwoo Choi

You can apply global average pooling.

I see. How about adding it in the docstring? That would be more easily accessible for the users.

I tried this but somehow, after applying the second classifier, the result is always `[]`.

A follow-up question. What would be the best practice to apply a sequence of augmentation to the examples in a batch while varying the randomized parameters per example?

Thanks for all the answers! Knowing the difference between `p_mode` and `mode`, it seems clear to me that in `Compose()`, only `p_mode=per_batch` is allowed. It's still confusing to me, but...

(I drew the image at www.draw.io. You can open this file there https://www.dropbox.com/s/taapi8jaskts6yx/torch-audiomentation?dl=0)

- I was trying to make a PR but do you think we should add visualizations whee `p_mode` is `per_example` or `per_channel`? - And.. I realized, maybe that figures on...

Agree that `p_mode="per_example"` would be the most relevant. I changed the figure on my side. Related to that, I think `p_mode="per_example"` would be quite necessary in `Compose()`. I don't know...

not sure if i have the same issue. in my case - after `index.query()`, there was quite some case where it returns distance of `np.inf` or some absurdly large numbers...

@Adenialzz hi, could i ask you for a clarification? how was it used to fixed which problem exactly? i'd appreciate it very much.