An Empirical Study on GAN-Based Traffic Congestion Attack Analysis: A Visualized Method

Table 3

Experimental parameter settings.

	Parameters	Value
CycleGAN framework		10.0
		1.0
	Initial learning rate	0.0002
	Optimizer	Adam
	Batch size	1
	Dropout rate	No dropout
	Net	Basic
	Net	Resnet_9blocks
pix2pix framework	Weight for loss	100.0
	Initial learning rate	0.0002
	Optimizer	Minibatch SGD, Adam
	Batch size	1
	Dropout rate	0.5
	Net	Basic
	Net	U-Net