Hyun Sik Yoon (Eric Yoon)

Question. `one-import-onnx` also has `--model_format` and `--converter_version`. Is there any case where user should call `--model_format graph_def` or `--converter_version v1`? https://github.com/Samsung/ONE/blob/c426200a29e4236c73562331c70e5bf35663c0a8/compiler/one-cmds/one-import-onnx#L75-L78

@glistening, Thanks for the good questions. It's kinda hard to track the history. 😢 > Could you please point out the issues to get background about one-init? - one-init is...

I added two more lines in action list of https://github.com/Samsung/ONE/issues/9450#issue-1307418648: > - If cfg file be used to compile models (except some unusual models), make PRs and make one-init to...

@glistening FYI this name was originated from https://github.com/Samsung/ONE/issues/9153 > In addition, if it just creates a default configuration, why users need to execute this tool explicitly? It may be created...

I tested models with generated cfg files. (internal one vscode repo issue 93) Let me start make commits for PR.

@ai-moiseev IMHO there are a few thing to consider. > The idea is to make this utility a part of ONE's toolchain (by introducing a new tool, e.g. one-visualizer) so...

@lemmaa I write the following, > One way around is > 1. for now, how about providing memory info to ONE-vscode? > later, if it become certain that the tool...

For general relation between ONE, ONE-vscode and backends, I created https://github.com/Samsung/ONE/issues/8743.

I'd like to also discuss output format of backends other than tflite or onnx. For example, assume that there is a backend company FOO... :-) Assume that FOO has their...

Discussed with @seanshpark and @yunjayh today. Current approach would be - Consider case 3 (not case 1 or 2)