![]() In particular, we need images with captions that describe them. To train CLIP in Italian we need one thing: Data. Our model is the first CLIP model made for the Italian language. With our project, we tried to provide another resource for the Italian NLP and CV community. You can read more about this in the original paper. When projected into the space, the image of a cat and the label “cat” will be close (considering some distance metric in the space).ĬLIP shows incredibly zero-shot performance on datasets like ImageNet without seeing one training sample. If you prefer the video format, I gave a talk at LightOn AI in September, you find the video right here: After that, I’ll describe a bit more in detail how we trained it to cover the Italian language (Section 2). I will try to stay at an high-level of abstraction, but at the same time, I’ll try to share all the information needed to understand how this model does its job. In this article, I’ll first go over a general introduction of how CLIP works (Section 1).
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |