What is the rationale behind sampling from the normal distribution for the W latent code, which is not a normal distribution at all?

[wztdream]

Hi,
In the lines below, you use randn, which represents a normal distribution, to sample latent code for W space. It appears to be unreasonable since W space is not a normal distribution. Can you please explain why this approach is used despite that? Additionally, it seems to be effective. Could you provide an explanation for its success? Moreover, why not first sample from a normal distribution and then map it to W space, which seems more reasonable?

interfacegan/models/stylegan_generator.py

Lines 151 to 152 in 8da3fc0

	elif latent_space_type == 'W':
	latent_codes = np.random.randn(num, self.w_space_dim)