ijyliu / computer-vision-project

Using classical and neural image embeddings and finetuned end-to-end networks to achieve top-tier performance on a vehicle type classification task. Containerized and deployed model as a web app
https://cv-web-app-3m4f2rmfzq-uc.a.run.app/
0 stars 0 forks source link

investigate CLIP #22

Open ijyliu opened 6 months ago

ijyliu commented 6 months ago

pretrained image captioning model that can be used for zero-shot classification

ijyliu commented 5 months ago

very buggy, at least in current implementation through autogluon

openai clip package might work better but shelving for now