CLIP (ViT L/14@336px)
OpenAIZero-shot image classificationCharacter recognition (OCR)Video descriptionOpen weights
Developed by OpenAI in 2021, CLIP (ViT L/14@336px) is a zero-shot image classification model with 370000000.0 parameters with openly available weights.
About CLIP (ViT L/14@336px)
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other vis
Details
- Provider
- OpenAI
- Task
- Zero-shot image classification,Character recognition (OCR),Video description
- Parameters
- 370000000.0
- Released
- 2021-01-05
- Open weights
- Yes