-
Perhaps in a new module `data_viz` or something, we can add some tools for interpretation of classifiers. The first one I'd like to add is something I already have a prototype of - a notebook using in…
-
Hello everyone! I found my last NPX recording got polluted with some potential AC noises possibly due to poor GND and REF. Here are some of the noises after sorting with KS4, which is spikes approxima…
-
I would like to know how to explain the classification of audio that can be achieved using ImageNet pretrained models based on spectrograms? As we all know, most of the pictures included in Imagenet a…
-
In a program for creating spectrograms called spek the output looks like the following:
…
-
Is it possible to have multiple feature extractors for a single Cut?
e.g. if you want mel spectrograms, F0, energy, etc. as separate features in a model, can you implement each one separately and cal…
-
Assess uality of feature space/similarity of items. Especially, the quality of audio/spectrograms
-
will need to turn them into multiple batches, probably within predict function?
or maybe the data loader can take care of this using a clever `collate_fn`
-
Hello!
I've restarted/shutdown my computer a couple times since beginning to analyze spectrograms in Luscinia, and when I open Luscinia back up, the database location I created and what I analyzed …
-
Hello, why did you switch back to building on DAC-style waveform outputs for SNAC after showing it's possible to completely get rid of aliasing by generating complex spectrograms with Vocos? I'm also …
-
here is everything:
wb@i7:~/git/6th/audiotagging2019$ python run.py --model xresnet18ssa --base_dim 128 --SZ 256 --fold_number -1 --n_epochs 80 --loss_name FocalLoss --weights_fil…