While running the clip_guided notebook in CPU mode I get: "RuntimeError - Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.FloatTensor instead" about glide-text2im HOT 8 CLOSED

Ok, thanks! Now at least in CPU mode it works!
In GPU mode a completely black image is generated (at some points tensors become NaN), but I'll open another thread for that, as it must be caused by a different problem.

from glide-text2im.

Not sure what is happening here, but you should try to aim for a GPU if possible.

See the comment in the notebook:

# This notebook supports both CPU and GPU.
# On CPU, generating one sample may take on the order of 20 minutes.
# On a GPU, it should be under a minute.

CPU mode takes 20 times more computation time than GPU mode.

from glide-text2im.

I know, but my current GPU doesn't have enough VRAM... that's why I was running in CPU mode.
In my case I'm getting a new GPU soon, but think it would still be cool if this could still work on CPU...

from glide-text2im.

Yes, sure. In the meantime, try to use a free GPU on Google Colab.

from glide-text2im.

@woctezuma I finally got hold of a new GPU with 6 GB VRAM... so I am now running again the clip_guided notebook in GPU mode, but I am seeing exactly the same error I documented above...

from glide-text2im.

Try:

• pytorch/captum#405 (comment)
• huggingface/transformers#7026 (comment)
• https://forums.fast.ai/t/eembedding-error-expected-tensor-for-argument-1-indices-to-have-scalar-type-long-but-got-torch-floattensor-instead/41045/7

from glide-text2im.

Thanks! I saw them already but I don't have the necessary ML & rel. libs knowledge to properly make use of them...
I also already tried kind of blindly playing with those types and their conversion, but without success...
Honestly, I see it very hard I can come up with something useful just by myself... 🤷‍♂️

from glide-text2im.

It could be just a simple change of this line:

You could try to replace:

F.embedding(cast(torch.Tensor, t), self.w_t)

with either:

F.embedding(cast(torch.Tensor, t.long()), self.w_t)

or:

F.embedding(cast(torch.Tensor, t).long(), self.w_t)

from glide-text2im.