Railway Fastener Fault Diagnosis Based on Generative Adversarial Network and Residual Network Model

Table 1

Different depths of ResNet.

Layer name	Output size	18-layer	34-layer	50-layer	101-layer	152-layer
Conv1		, 64, stride2; max pool, stride2
Conv2_x
Conv3_x
Conv4_x
Conv5_x
		Average pool, 1000-d fc, softmax
FLOPs