Skip to content

Conversation

@rotatorotator
Copy link

As proposed by @hack-mans in #332 I have tested this on a RTX 6000 Pro with batch size 8 and trained over 5000 steps. It fixes the Tensor Size Missmach. All credit for the fix needs to go to him!

As proposed by @hack-mans in ostris#332 I have tested this on a RTX 6000 Pro with batch size 8 and trained over 5000 steps. It fixes the Tensor Size Missmach. All credit for the fix needs to go to him!
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant