Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images

Table 3

CNN-Baseline model summary.

Layer (type)	Output shape	Number of parameters
conv2d (Conv2D)	(None, 62, 62, 32)	320
max_pooling2d (MaxPooling2D)	(None, 31, 31, 32)	0
Flatten (flatten)	(None, 30752)	0
Dense (dense)	(None, 128)	3,936,384
Dense_1 (dense)	(None, 6)	774
Total params: 3,937,478	Trainable params: 3,937,478	Nontrainable params: 0