Replies: 4 comments 1 reply
-
Hey @ShuxunoO. You have two options here. One is to put those samples in shards by compressing n pairs of files into a Your other option is to create a csv file with two columns, a For fine-tuning, you can run the sample training commands from our readme, but be sure to set the |
Beta Was this translation helpful? Give feedback.
-
demo like this:
is it all right?
should I replace the --model RN50 to a local path of a released pretrained model? |
Beta Was this translation helpful? Give feedback.
-
If you're going with csvs, you should have the actual captions in the second column, not a pointer to the files. If you're using a pre-trained model we support, you can use a string for the |
Beta Was this translation helpful? Give feedback.
-
and my args is like following:
I am going to have a try! |
Beta Was this translation helpful? Give feedback.
-
Hello, I have prepared a local dataset,including img-caption pairs just like:
dataset_folder:
Now I want to finetune a released pretrained CLIP model (such as ViT-B/32), in what form should I organize the csv file, can you give me an example? Or is there any ready-made script for generating csv files?
Besides, which script can I use to finetune the model? Can you give me a reference link or a tutorial?
Thanks a lot!
Beta Was this translation helpful? Give feedback.
All reactions