You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi,
In your code, you use the following code to set whether using null text vector:
is_empty_text = torch.logical_not(input['condition_mask'][:, 2]).unsqueeze(1).unsqueeze(2).repeat(1, 77, 512)
But, I found that if all of the caption length larger than 2, is_empty_text will always be False. So, I want to ask how to control the classifier free guidance? Whether we add some <image, null text> pair to the training dataset?
The text was updated successfully, but these errors were encountered:
Hi,
In your code, you use the following code to set whether using null text vector:
is_empty_text = torch.logical_not(input['condition_mask'][:, 2]).unsqueeze(1).unsqueeze(2).repeat(1, 77, 512)
But, I found that if all of the caption length larger than 2, is_empty_text will always be False. So, I want to ask how to control the classifier free guidance? Whether we add some <image, null text> pair to the training dataset?
The text was updated successfully, but these errors were encountered: