search

clovaai / generative-evaluation-prdc

Code base for the precision, recall, density, and coverage metrics for generative models. ICML 2020.
MIT License
243 stars 28 forks source link

About a specific random embedding extraction method #8

Closed subinium closed 2 years ago

subinium commented 2 years ago

When extracting random embeddings, does use a randomly initialized vgg16 mean using an untrained model?

Or does it mean to train and select vgg16 up to a certain threshold as in the deep prior image? If so, how did you set the threshold for that threshold?

May I know the specific code you used or the code you referenced?

hellog2n commented 2 years ago

Hi, I think that they used untrained vgg16 which is randomly initialized and the the parameters of the model is fixed in their paper.

I think we can use this code for extracting random embedding from the random init model. vgg16 = models.vgg16(pretrained=False)