gmongaras / diffusion_models_from_scratch Goto Github PK

Hello!

I am trying to make to train a model myself using Imagenet64x64 for a test; on a MAC using "mps" device.

It took me a little while to see that after downloading Imagenet64x64, I have to
— use "loadImagenet64.py" to generate .pkl files in an "Imagenet64" folder.
— THEN use "make_massive_tensor.py" to make a large .pt file.
— THEN use "train.py" which will call "model_trainer.py"

Apparently (tell me if I am wrong):
— "loadImagenet64.py" needs "Imagenet64_train_part1.zip" and "Imagenet64_train_part2.zip".
Imagenet64x64 does not have these files. It rather has:
train_data_batch_1, train_data_batch_2, train_data_batch_3... etc

— I changed the code in "loadImagenet64.py" to make a series of img and label .pkl files within the "Imagenet64" folder.
— Then, when running "make_massive_tensor.py", I get the following errors:

Shape error with file data/Imagenet64/n.pkl
Key error with file data/Imagenet64/metadata.pkl

— I probably did something wrong in "loadImagenet64.py" with the formatting of pickles. But I do not know where that is happening. Dict's keys seem fine: loadImagenet64 seems to replace 'data', 'mean', 'labels' found in Imagenet64 with 'data', 'mean', 'labels'.

=> Where did you get "Imagenet64_train_part1.zip" OR how did you make them?
=> How to deal with the shape and dict keys within those .pkl ?

Thank you for your help!!!

O.

Hi, thank you for your great repository.
I think there is an issue in Line 27-28 in src/blocks/PositionalEncoding.py.

        # Sin/Cos transformation for even, odd indices
        embeddings[::2] = embeddings[::2].sin()
        embeddings[1::2] = embeddings[1::2].cos()

I think it has to be

        # Sin/Cos transformation for even, odd indices
        embeddings[:, ::2] = embeddings[:, ::2].sin()
        embeddings[:, 1::2] = embeddings[:, 1::2].cos()

when I run this code,
X = torch.einsum("nclw, ncC -> nclw", X, KQ)
A issue was occurred as the title describes

Any tips?