Closed JVass closed 1 year ago
https://pytorch.org/hub/pytorch_vision_densenet/ says input image has to be:
Palanisamy et al didn't do any of those things, where HxW for UrbanSound8k is (128,250) and not normalized.
Global params for classification will be based on Palanisamy et al: No Early Stopping (I discarded the learning rate scheduler) EPOCHS = 70 LR = 1e-4
The results are not very promising, but it is as good it will get for the assignment.
This will be the second section of the assignment that is: environmental sound classification with the use of a DenseNet