Skip to content
Tensorflow - Very Deep Convolutional Neural Networks For Raw Waveforms -
Branch: master
Clone or download
Latest commit 32fbfa7 Dec 19, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
assets results May 17, 2017
samples add some audio samples Jun 3, 2017
LICENSE Initial commit May 14, 2017 Update Dec 19, 2018 full keras implementation now May 16, 2017 full keras implementation now May 16, 2017 full keras implementation now May 16, 2017 add res net. fixed small bug for m11 and m18 (max pool was not placed… May 16, 2017 Update Jul 25, 2018 full keras implementation now May 16, 2017
requirements.txt results May 17, 2017 results May 17, 2017

Very Deep Convolutional Networks For Raw Waveforms

Keras (Tensorflow) implementation of the paper:


  • Going really deep does not seem to help much on this dataset. We clearly overfit very easily. Adding more regularization might help. I haven't tried to use the FC layers (though it has been implemented).
  • We use the fold10 folder for the testing set and the remaining for the training set.
  • Models implemented:
[x] M3
[x] M5
[x] M11
[x] M18
[x] M34 (ResNet)

How to re-run the experiments?

Dataset can be downloaded here:

git clone
cd very-deep-convnets-raw-waveforms
sudo pip3 install -r requirements.txt
./ # will run M3, M5, M11, M18 and M34
M3 model - best accuracy: 0.673, trainable params = 221,194

M5 model - best accuracy: 0.743, trainable params = 559,114

M11 model - best accuracy: 0.752, trainable params = 1,786,442

M18 model - best accuracy: 0.710, trainable params = 3,683,786

M34 model - best accuracy: 0.725, trainable params = 3,984,154

You can’t perform that action at this time.