Closed StanLei52 closed 4 months ago
Sorry for late reply. You can refer to this. We didn't add any tricks, just removed LoRA.
Sorry for late reply. You can refer to this. We didn't add any tricks, just removed LoRA.
Hyperlink is not found and please update. Thank you!
Sorry for late reply. You can refer to this. We didn't add any tricks, just removed LoRA.
Hyperlink is not found and please update. Thank you!
Sorry, we update it. https://github.com/PKU-YuanGroup/LanguageBind/blob/main/scripts/video_language/train_1.5_large.sh
Sorry for late reply. You can refer to this. We didn't add any tricks, just removed LoRA.
Hyperlink is not found and please update. Thank you!
Sorry, we update it. https://github.com/PKU-YuanGroup/LanguageBind/blob/main/scripts/video_language/train_1.5_large.sh
Thanks for your response!
Hi, I notice that in your paper, the results for full-tuning are reported. I'd like to know the training configurations for full tuning -- do you use the text prompt and input modality data with contrastive learning during full tuning, or use class labels with traditional classification setting (e.g., cross-entropy loss)? Thank you.