Merging inferences - Githubissues

JVass / background_sensitivity_of_CNNs

This repository will contain the assignment for the module of "Deep Learning for Audio and Music". The objective is to implement two Deep Neural Network architectures, for two different kind of tasks and try to combine those inferences. I chose to implement a U-Net for Spectrogram denoising and a DenseNet for Environmental Sound Classification.

0 stars 0 forks source link

Merging inferences #3

Closed JVass closed 1 year ago

JVass commented 1 year ago

Connect the trained U-Net (that will denoise or 'lose some information') with the DenseNet, for classification and eavluate if the accuracy changes

[x] Load the saved and trained Autoencoder
[x] Load the saved and trained DenseNet
[x] Connect those as: Autoencoder -> DenseNet
[x] Evaluate the classification error of this pipeline
[x] Compare it with using only the DenseNet
[x] Evaluate classification of DenseNet with noisy input
[x] Evaluate classification of Autoencoder to DenseNet with noisy input

JVass commented 1 year ago

This sums up the assignment.