Thanks for the awesome implementation!
After training in my own datasets, the classification acc1 of model is bad. I do not know how to analysis the problem. When finetuning CLIP, is there some criterion to measure whether the model has been trained well?
Thanks for your answers ahead of time.
Thanks for the awesome implementation! After training in my own datasets, the classification acc1 of model is bad. I do not know how to analysis the problem. When finetuning CLIP, is there some criterion to measure whether the model has been trained well? Thanks for your answers ahead of time.