-
# ❓ Questions and Help
Hi,
I've installed the xformers library (windows, install via pip)
When running the microGPT.py script, I have this error (see trace bellow). What's the problem?
regards,
…
-
Hello,
I'm having some challenges reproducing the values in Table 2 (CIFAR-100). Hoping to get some feedback on how to fix this:
(1) Train from Scratch:
Could you please advise on the correct …
-
Thank you very much for sharing the code and patiently answering any questions you may have. But I have another question:
When searching based on NAS, the objective function should include the infe…
-
Hi, @Yangsenqiao, thanks for releasing your code. I really appreciate it.
Btw, how can I train by myself [this source model](https://drive.google.com/file/d/13R0ZoHaUUXL4PYHWWIwl2NvEcU_3JJxU/view) u…
-
Hi! Amazing work! I've been working on reproducing the results and ran into a few things that I was hoping you could clarify when you have a moment.
1. **Winoground Compositionality Results**: I no…
-
Thanks for the amazing paper! I have a few questions about the details of the results in Figure 6 in the paper. I tried to use the linear probing code in the `README.md` on CIFAR to run one-shot evalu…
-
Im `vfsddpm.py` line 223-225: `x_set_tmp = batch[:, ix]` yout select `ns - 1` of data, but you don't select `ns-1` t_emd, that cause `vitset.py` line 176 :`t_emb = t_emb.view(b, ns, -1)` error, this t…
-
Hey -
first of all - thank you for your inspiring research.
there's a lot of work around how to make efficient self attention - especially as the sequence length increases.
it seems to me that…
-
thanks for your nice work!
I have some issue following the repo and run the code for transfer learning.
I get the pretrain model for cifar10 from the link and locate it in the appropriate location a…
-
Thank you for your work on CLIP!
I was trying to reproduce the zeroshot prediction results listed in Table 11 in the paper. Though I can reproduce most of the results in the Table 11, I found there…