Synet icon indicating copy to clipboard operation
Synet copied to clipboard

Instruction for model training

Open edward9112 opened this issue 4 years ago • 9 comments

Hello Igor!

What do you think about making a brief instruction on how to annotate and train models to be compatible with Synet? Which software to use for annotation, which for training, general recommendations/requirements, etc.

It would be awesome to have that.

Thank you!

edward9112 avatar Jul 16 '21 09:07 edward9112

Hello!

It's a good idea. I will add it to plans.

ermig1979 avatar Jul 16 '21 09:07 ermig1979

Hello!

It's a good idea. I will add it to plans.

Awesome!

edward9112 avatar Jul 16 '21 09:07 edward9112

Hey! Any updates on this?

edward9112 avatar Aug 23 '21 10:08 edward9112

I am sorry but there is no update still. I have got no free time to do this issue.

ermig1979 avatar Aug 24 '21 09:08 ermig1979

I am sorry but there is no update still. I have got no free time to do this issue.

Thanks for the update. Waiting patiently…

edward9112 avatar Aug 24 '21 09:08 edward9112

Hello! Any updates on the tutorial? Thank you!

edward9112 avatar Jan 17 '22 14:01 edward9112

Just a friendly follow-up @ermig1979

edward9112 avatar Feb 16 '22 06:02 edward9112

Hi! I see this issue is in demand. Why it does not move? One hand I don't like to make tutorial like other hand there is no definite rules to make models compatible with Synet. I try step by step to extend amount of compatible model types. If I see incompatibility I add the model (in OpenVINO or ONNX format) to test framework and achieve then of correct conversion to internal Synet format. The process still go on.

ermig1979 avatar Feb 16 '22 08:02 ermig1979

Right, but you probably do some basic model training internally in your team according to some standard procedure, i.e. Step 1: use such and such software for data labeling Step 2: run such and such command on labeled data to retrieve any kind of viable model etc.

This information would be really helpful for those who are not very proficient with model training, and it would be a great addition to your awesome Synet framework.

edward9112 avatar Feb 16 '22 10:02 edward9112