PKU-YuanGroup/LanguageBind Issues
关于数据集的一些问题
ClosedFine-tuneing LLM + LanguageBind?
Updated 1gpu资源
Updated 1where is LanguageBind_Image
Updated 2关于视频文本的训练问题
ClosedCombination of multiple modalities
Updated 3Vision encoder version
Closed 1Congrats on Acceptance !!!
Updated 1batch inference
Updated视频特征的提取支持动态帧数吗,效果相对于8帧会有下降或者变差吗
Closed 1Add flash attention 2
Closed 7Choice of Vit-L over Vit-H
Closed 2VIT-H model release
Closed 2about LanguageBind_Video_merge
Closed 1Hashtags and prompts?
Closed 4用于特征提取对齐,选用输出为什么参数
Closed 1About download weights
Closed 1cannot run the code train
Closed 1pretraining details
Closed 1Text input length
Closed 2how to use hugging face model
Closed 1bug in install requirements.txt
Closed 1GPU sources
Closed 2