Share your work here ✅

Part 1 (2019)
1171

Hey, @MicPie is right, data augmentations are not helpful for spectrograms, neither is pretraining with imagenet.

Try this and see if you can improve even more.

  1. set pretrained=False when creating your cnn_learner (this will turn off transfer learning from imagenet which isn’t helpful since imagenet doesn’t have spectrograms)
learn = cnn_learner(data, base_arch=models.resnet34, 
                   metrics=[accuracy], pretrained=False)
  1. Turn off transforms. You do this in the databunch constructor, set tfms = None
  2. Also make sure you are normalizing for your dataset, not imagenet stats. If you have the line .normalize(imagenet_stats), change it to .normalize().
databunch(dl_tfms=None).normalize()

Hope this helps and if you’re especially interested in audio come join us in the Deep Learning With Audio Thread

4 Likes