How do I deploy my custom model I have trained on …

I have trained a detectron2 model on vertex ai workbench. i have NOT used tensorflow, xgboost or scikit-learn. 

i have a model.pth file and a metrics.json file stored in my bucket when i run the model. 

How do i deploy this model on GCP and further evaluate it? Is it possible for me to create an endpoint and directly deploy my model on this or will i have to use something like cloud build?

Read more here: Source link