OFA-Sys
Why are all the sentences generated by image captioning the same sentence?
My dataset is medical images (x-rays), but after fine-tuning ， the generated captions of all the images are the same sentence.Is there something else that needs to be modified?Hope the author can give me some advice.
Any more details? You can first check whether you can reproduce the performance following our instructions for finetuning on coco captions. If everything is alright, you can check your code or provide a colab notebook for us to follow up.
Any more details? You can first check whether you can reproduce the performance following our instructions for finetuning on coco captions. If everything is alright, you can check your code or provide a colab notebook for us to follow up.
Because I just have one not 5 captions about an image, so I didn't do the stage 2 training, is it because of that?
My dataset is medical images (x-rays), but after fine-tuning ， the generated captions of all the images are the same sentence.Is there something else that needs to be modified?Hope the author can give me some advice.
Hi, did you find out the reasons and solutions?
