Florian S.

I can confirm that I have the same problem. (also the Watch4 Classic, 46mm in my case) Using the bezel and swiping works just fine in normal use, but as...

I suppose I got the same problem as you guys. I haven't checked for tensor values, but my loss is nan and all my predicted images remain black. Changing from...

I dug a little bit deeper and seemingly found a solution for this issue. Only thing you have to do is disable autocast in the `train_fn`: ``` # forward with...

The `path_num` variable represents the number of paths used for the model. When running the td4_psp18 model, you're essentially running 4 psp18 models, for td2_psp50, you're using 2 psp50 models....

I'm not sure, that I can correctly explain how it works, but regarding the "why" have a look at Table 7 in the original paper and at the paragraph "Shared...

That's correct, PIDNet only performs resizing if multi_scale is True. However I personally wouldn't call this in issue as I want to test my predictions on full size whatsoever. I'm...

Yes, I actually did some testing on 50% prediction as well as using upscaling for full-scale predictions. Using PIDNet and my highly imbalanced binary dataset, I was able to get...

Resizing the weights actually solved my problem and improved my prediction. Thanks! However I still don't understand how you managed to use multi scale while having fixed layer_norm sizes. Shouldn't...