zigma

zigma copied to clipboard

code is error

2

TypeError: Mamba.__init__() got an unexpected keyword argument 'scan_type'.

Mr-Harry

How to implement torch.compile for Mamba models?

1

Hi, I notice from your README file that torch.compile provides a great speedup. However, I didn't see where you implemented torch.compile for your train_acc.py. I tried to add torch.compile(model) for...

yyNoBug

Can I input a image that w is not equal to the h?

6

66ling66

Classification

1

Hi @GrebenkovaO @dimakot55 @m990130 ,Thanks for the great work.I am looking to try this approach for simple classification.How can I make changes in the code?Can you epxlain in little detail?

sivaji123256

Request for UCF101 video generation results and checkpoints

2

Thank you for sharing your work on the Zigzag Mamba Diffusion Model. The paper mentions video generation experiments on the UCF101 dataset, but I noticed that the video generation results...

1111112

Taking making inputs from multiple directions

1

Rather than a purely sequential scan through the patches, I feel it would make more sense to use take inputs from multiple patches at once. Obviously you are limited in...

EndingCredits

install error in

1

when: cd dis_causal_conv1d && pip install -e . && cd .. error: anaconda3/envs/zigma/compiler_compat/ld: cannot find -lgcc_s: No such file or directory collect2: error: ld returned 1 exit status Can I...

huangjch526

How do I download and pre-process the facehq dataset

zzj311

continuous scan

1

请问连续扫描的实现是哪一部分代码呢？

Beliefs666

Hi @stefan-baumann @GrebenkovaO @dongzhuoyao @dimakot55 @m990130 , I would like to train a model using my custom dataset. Is there a way to provide a custom prompt for each image...

rutuja1409