Experiment 5

Binary classification with validation set implementation.

Parameters

clip_length: 5.0 # [sec]

sample_rate: 44100

hop_length: 512

n_fft: 1024

n_mels: 64

number of audio samples: 220500

learning rate: 0.001

batch size: 130

number of epochs: 30

number of samples: 1040

balanced dataset: False

random clip cut: False

scheduler: True

grime jazz

Dataset	Class	Class ID	Samples
Train	`grime` `jazz`	[0, 1]	1040
Validation	`grime` `jazz`	[0, 1]	160
Test	`grime` `jazz`	[0, 1]	400

ID	Epochs	Batch	Classes	LR	samples	Loss	Accuracy
	30	130	2	0.001	1040	0.15	0.94