Docker Container about cog HOT 1 CLOSED

Hi @selintunr. cog predict starts up a container, runs the model once, and shuts down. To keep it running, you can do cog build to build the image, docker run to run the container, and curl to send predictions to the running container.

From the README:

$ cog build -t my-colorization-model
--> Building Docker image...
--> Built my-colorization-model:latest

$ docker run -d -p 5000:5000 --gpus all my-colorization-model

$ curl http://localhost:5000/predictions -X POST \
    -H 'Content-Type: application/json' \
    -d '{"input": {"image": "https://.../input.jpg"}}'

from cog.