playing around with image-captioning model and try to make it prod ready.
- add an python flask http endpoint
- move this endpoint into a docker image and mount the model and images from the host
- try to make flask server prod save. with waitress server
- adding CORS
- adding Prometheus Metrics
- loading the model in an extzra service for better seperation
- testing other servicer than waitress
Infos: the model is: https://huggingface.co/nlpconnect/vit-gpt2-image-captioning
this need be downloaded separate and place in the folder modle/transformers/*