Ming M Qin

I know, it is doable in a OO way, but given that there are many transforms, and the image capture/validation needs to be on specific transforms, having a blanket instrumentation...

Agree @vikashg . Using SaveImageD is just a stop-gap till we have the proper impl that cleanly integrates with visualization, perf analysis, image QA etc.

A simple DICOM SR writer operator has been added as in the V0.2 release, in [PR](https://github.com/Project-MONAI/monai-deploy-app-sdk/pull/201), to support wrapping/reporting textual classification results. This operator supports customizing the model info (used...

I don't see the "--rm" option in the statement, maybe it is somewhere else.

Doesn't Docker already incorporate nvidia-docker, or the latter when installed registers with docker. Anyway, the model I am testing was trained with GPU and scripted with such dependency.

nvidia-docker2 overwrites the default daemon.json file on installation, so yes, the daemon.json file needs to change, but done automatically. In any case, requirements on nvidia-docker2 then needs to be clearly...

I am actually thinking greedy. Instead of exposing the command line options of docker, maybe just have Runner support a single option to take them all in one Runner CLI...

The MONAI Deploy App SDK Packager does not support ARM-V8 AArch64 officially, for one it currently restricts building app docker (aka MAP) on certain base images (Ubuntu on x86) and...

This is more than a feature request, and in fact this is an `area` that requires a suite of software. - Model themselves, specifically the one App SDK support, do...

The runner may not know the semantics of "a set of folders" as it has to generically run all possible MAP's. The best way is for the application, or rather,...