x-clip

x-clip copied to clipboard

Distributed training setup

1

PR for the distributed training setup.

MicPie

NaN with mock data

1

Hi lucidrains, Try this and it will NaN within 100 steps (latest Github code). The loss looks fine before NaN. ``` import torch torch.backends.cudnn.allow_tf32 = True torch.backends.cuda.matmul.allow_tf32 = True torch.backends.cudnn.benchmark...

BlinkDL

Unable to train to convergence (small dataset)

9

Hi nice work with x-clip. Hoping to play around with it and eventually combine it into your DALLE2 work. Currently having some trouble training on roughly 30k image-text pairs. Loss...

jacobwjs

Suggest your favorite papers to add!

20

will start with 1. FILIP https://arxiv.org/abs/2111.07783 2. CLOOB https://arxiv.org/abs/2110.11316 3. https://arxiv.org/abs/2110.05208

lucidrains

Can we extract embeddings of size (say dim_text = 256, dim_image = 256) other than 512 from a pre-trained CLIP?

abhishekaich27

[DOCUMENTATION REQUEST] add demonstration for loading openai pretrained clip weights

1

dmarx

Loss goes in -ve with mock data

yayati29

Dear Lucidrains, Thanks for your selfless contribution and outstanding work, it is beneficial. I'm an ML beginner, so my foundation is not solid. I have a question about x_clip. I'm...

chengyi-21

Hi and thanks for all the work done in this repository! I noticed that the implementation of the CLS token in the Vision transformer, as well as the tokens used...

MLRadfys