VSainteuf

I'm not sure I understood everything but what I can say is that we follow the metric formulation of the Panoptic Segmentation paper. In our code all the metrics are...

Again, this equality holds for the scores per class, but not on the class average metric. In fact, if you do the math 0.815x0.532=43.35 not 43.8 We follow the metric...

Hi again, I remember I once did a quick test with PyTorch Scatter to handle that more elegantly. But I didn't push much further because I didn't see noticeable gains....

hi @manapshymyr-OB , If your dataset has time series of varying lengths, you can normalise with statistics of shape C. So you compute the mean and standard deviation of each...

> @VSainteuf in that case I will have an array with shape 1xC, right? Yes > @VSainteuf i think I figured out (I got 8x1048576, because my imgae 1024 by...

OK I'm not sure what the question is anymore, let me know if you need clarification on one point!

yes if you have time series of varying length the best option is to compute the channelwise mean across all samples and dates. So you end up with mean and...

are you giving different arguments to the train and val data loaders ? Any idea why the behaviour is different between train and val ?

HI @manapshymyr-OB , can you have a look at [this issue](https://github.com/VSainteuf/lightweight-temporal-attention-pytorch/issues/1) and see if it helps you?

yes if you have time series of varying length, you need to implement a "collate" function with a padding strategy to form batches of equal size. You can have a...