search

moein-shariatnia / OpenAI-CLIP

Simple implementation of OpenAI CLIP model in PyTorch.
MIT License
574 stars 85 forks source link

difference in config parameters in notebook vs config #5

Open nahidalam opened 1 year ago

nahidalam commented 1 year ago

In your config.py you have https://github.com/moein-shariatnia/OpenAI-CLIP/blob/master/config.py#L22-L23 

pretrained = False # for both image encoder and text encoder
trainable = False # for both image encoder and text encoder

But in your notebook you have

pretrained = True # for both image encoder and text encoder
trainable = True # for both image encoder and text encoder

Can you please explain?