Open LsFlyt opened 9 months ago
And another question, in VQ-VAE, the data are normalized to [-0.5, 0.5], but in the training phase 2, the content image (which feeds to the content encoder) is normalized [-1, 1].
Sorry for the late reply, i can not remember the reason i use 'data = data - 0.5 # normalize to [-0.5, 0.5]' due to the long time. Maybe is a mistake or not.
In VQ-Font/model/VQ-VAE.ipynb.
for i in xrange(num_training_updates): data = next(iter(train_loader)) train_data_variance = torch.var(data)
print(train_data_variance)
The code normalize data to [-0.5, 0.5]. However, the last layer of the decoder of the VQ-VAE model is sigmoid. Is this a mistake?