[Retracted] Deep Convolutional Neural Network Mechanism Assessment of COVID-19 Severity

Table 1

Proposed deep CNN.

Deep CNN	Type of layer	Activation layer	Training parameter	Overall trainers
	I/P			—
	Convolution		Weights and bias	13,954
Rectified unit	Rectified unit			—
Cross normalization	Normalization			—
Maximum pooling	Max pooling			—
Fully connected	FC		Weight	3,146,245
35% dropout	Dropout			—
Fully connected layer	FC		Weight	2054
Softmax	Softmax			—
O/P	Categorization			—