-
Your paper, GitHub, and issues have been very helpful to me. Thank you.
I would like to perform transfer learning using the pre-trained model you provided.
- Objective: I want to use the capabilitie…
-
**Describe the bug**
UMAP spectral initialization yields unexpected initial layout results. Consequently, global structure of the input data often is not preserved, even when a very high `n_epochs`…
-
I saw https://github.com/SHI-Labs/NATTEN/issues/89
> As far as I know both FAv2 and xFormers' FMHA support 1-D sliding window attention with causal masking, so you probably can use them for now, bu…
-
I tried to train this model few days. However, the reconstruction results always abnormal. If there is anyone success to train this model, can you tell me some tips for training?
-
Hi!
Has anyone managed to reproduce the results from "Improved Techniques For Consistency Training" on the CIFAR10 dataset?
Thank you for the great repository!
-
Hi! I would like to ask few questions regarding the visual encoder part.
1. How does the SpatialBot model load the SigLip pre-trained model? I have downloaded the `siglip-so400m-patch14-384` model…
-
Anyone has interest to utilize the sparsity to accelerate DNNs?
I am working on the fork https://github.com/wenwei202/caffe/tree/scnn and currently, on average, achieve ~5x CPU and ~3x GPU layer-wi…
-
I observe most methods tested on the People Snapshot Dataset optimize the test poses one by one before evaluation. Does your method also need this optimization. I have tried directly evaluating the t…
-
**Describe the bug**
In my own implementation, I combine a large language model and a speculator model. And my goal is to train the speculator model to make it better at predicting the n+2, n+3... tok…
-
In the paper, you said weights of the spatial cross-attention modules of ReferenceNet was optimized.
But, why both Reference Net and runwayml/stable-diffusion-v1-5 have same checkpoints?
They have e…