-
As far as i understand, when using cross_attention we first compute `qkv = self.qkv(hidden_states)`, and then `cross_qkv = self.qkv(encoder_output)`. But later only `q` from `qkv` is used, and only `k…
-
This issue is not in response to a performance regression.
The method of performing cross-attention QKV computations introduced in #4942 could be improved. Because this issue relates to cross-atten…
-
请问这个代码是不全吗,我对图像和文本的特征做cross attention那块有点疑惑,我在代码的基础上加了
def save_attention_hook(module, input, output):
attention_scores = output[1]
module.save_attention_map(attention_scores)
来捕获注意力得分,但是…
-
作者你好!感谢你写了这么完整的TimeXer的代码!我看完后有一个问题想向你请教一下:TimeXerEncoderLayer中,Self attention得到的X1是不是应该取variate embedding部分去做cross attention?我看你的代码里面没有拆分
![image](https://github.com/user-attachments/assets/14bc8887…
-
Hello,
Thank you so much for your great work and codebase!
I would appreciate your clarifications on a few items.
1) From within ```TextToVideoSDPipelineCall.py```, at this [line](https://g…
-
First, give a thumbs up to your work. But I have a question. The paper mentions decomposing cross attention into space and channels. What is the difference between these two and why is it called space…
-
Hello, I have recently implemented a cross attention application with multi-modal fusion, but because the image resolution is too large, cuda OOM occurs when calculating q and k, so I found your paper…
-
-
Hi,
thank you for your indepth analysis,
could you open source how to compute the cross-attention Difference code given in Figue 2 ?
-
Dear author, I have another question for you:
In Visual Prompt Encoder, is it stacking three layers of deformable cross-attention layer, then connecting one self attention and one FFN?
Or stacki…