StuartIanNaylor
StuartIanNaylor
https://github.com/breizhn/DTLN/issues/52#issuecomment-1109893740
I never got round to trying but somehow the tensor sizes get mixed up so prob do a print(shape) and set the input tensors accordingly. I ended up busy so...
Yeah its really confusing for the likes of me as the in_mag shape is the output shape not the input maybe @breizhn might have time to give us some pointers...
OK I am still having an off day but got to line 100 but thrown in loads of print statements so you can see. I kept the load order but...
So if that was as confusing as it was for this slightly befuddled brain at the moment just try this ``` """ This is an example how to implement real...
@DyncEric I only have a RTX3050 but I am pretty sure that error is a memory error Error occurred when finalizing GeneratorDataset iterator. I did change my code as the...
Totally forgot what I got now but probably because you have changed from 500 -> 40. As when valaidation is much higher than train loss usually its a sign of...
I tell it what it might be as git clone breizhn not the microsoft one https://github.com/breizhn/DNS-Challenge and create the dataset as I remember at 1st the dataset I was creating...
All I remember is to use the breizhn fork and the exact same instructtions 1st. > Training data preparation: > Clone the forked DNS-Challenge [repository](https://github.com/breizhn/DNS-Challenge). Before cloning the repository make...
I just ran it clone @breizhn repo of https://github.com/breizhn/DNS-Challenge and run the splt and runs fine