Sebastian Raschka
Sebastian Raschka
Hi there, it could be due to the low resolution indeed. Also, I suspect that a model trained on one dataset does not generalize well to other datasets. To get...
That makes sense! One thing to note though is that AFAD does come with several low-resolution images, which could result in the AFAD network being a bit more robust to...
Both preprocessing steps work fine. The one for MORPH-2 is a bit more expensive (takes much longer). The main reason was that we already had the datasets preprocessed from other...
> Here are the MAE values when datasets are resized in to smaller shape. AFAD seems little bit more robust to low resolution images. Thanks for this analysis. That's very...
It wouldn't really matter in this case whether you choose nn.AvgPool2d(4) or nn.AvgPool2d(7, stride=1, padding=2) or in general any number >= 4. In all cases all the values are averaged...
Yeah. AvgPooling doesn't have any parameters. It's just averaging the pixels.
Oh I see. That's because of the padding=2 then and you may be right that there are duplicated values. We probably did this because we were initially working with larger...
i agree
yeah, i think it could make a small difference. I don't think it will substantially change anything because these are just some redundancies; and it probably will also affect all...
I got curious and am currently rerunning the experiments. Looks like speed is not affected (makes sense because of broadcasting in PyTorch/CUDA probably) but performance does seem to improve a...