Junjie
Junjie
same problem, did you solve it?
> hi, bro. The scipy library already provides a method to calculate the correlation coefficient: from scipy.stats import pearsonr from scipy.stats import spearmanr As for emd, you can check the...
Hello, I have also encountered a situation where the DL2 memory usage has skyrocketed. I have temporarily decided to switch back to DL1. May I ask how to set up...
This DistributedSampler requires my dataset(datapipe) must have __len__ method, but the length of my datapipe cannot be calculated cause it is a iterable datapipe. Have you ever met problem like...
Thanks, please let me know when you make progress.
set `torch.utils.data.graph_settings.apply_sharding(datapipe, world_size, rank)` seems to solve the problem in my case.
> It's a gradio problem. Please run in python script first. run what python script ?
you can try set use_safetensors as True for the first problem. and the second problem may be caused by different operating systems.
Thanks for the replies. Of course, StoryDiffusion and ConsiStory are concurrent work. They are both nice. I opened this issue not to question this, but to discuss the method itself....
Got it, thanks.