-
-
Notifications
You must be signed in to change notification settings - Fork 1.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Train on custom input -> noise as output #315
Comments
Update: |
hey, did you get the correct output without noise? I still dont know how to run the code, would you please provide your train code? thanks!! |
Hello, yes. I'm still an amateur, but I got it working. Attached is basically my whole model. There are definitely a few inconsistencies, but after I put DallE together, it produces images as I envisioned them. You can read about how to "assemble" DallE here: #282 You load the trainer checkpoints as in the code I provided and add a ["model"] after it as follows: torch.load(checkpoint_path)['model'] Thats it. |
Thank you very much! It helps me a lot!! |
Yeah no problem. Because of that size it took nearly 24h for 3 epochs on a A100 GPU. It took maybe 5-8 epochs each to see some quite good results on that low resolution. |
Thank you very much for your answer, which gave me a great help!!! :) |
FIY: had an Error in the Priortrainer. You need to insert Otherwise you would just train your Prior from one image the whole time... |
Usually dataset class does not handle batching, shuffling, etc. You use torch dataloader class which takes care of dataset iterating, parallel data loading, batching and etc. |
Thanks for your scripts, and I want to know if you use the OpenCLIP or train a CLIP model from scratch? |
Hey there,
I'm fairly new to Machine learning in general, but need to train a Txt2Img-model on a custom input.
I've seen this implementation and it seemed like a relatively "small effort" to make this model work... I'm not sure about this anymore
I got the setup script from the readMe, which loads my own Dataset.
Are there any Clues on how to make this work or can you provide me with a functional training script, inference Script?
Any help is highly appreciated!
The text was updated successfully, but these errors were encountered: