Please provide the following information when requesting support.
• Hardware (T4/V100/Xavier/Nano/etc)
Ubuntu, x86, RTX3090
• Network Type (Detectnet_v2)
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)
I have a small proprietary dataset which contains 4 classes of images, the annotations statistics when doing dataset convert (in tao jupyter note book) is:
iva.detectnet_v2.dataio.dataset_converter_lib: Wrote the following numbers of objects: b'people': 2275 b'dog': 1194 b'cat': 1102 b'horse': 450
so this is a typical imbalanced dataset.
I noticed the properties of
enable_autoweighting under section
cost_function_config both in train and retrain spec are looked like to help the scenario, I want to understanding how to set them for my case.
- if set
true, then does it mean the
class_weightare all meaningless?
class_weightfor different class should just simply reflect the linear relation of their annotation count?
class_weightfor my case is: 10, 20, 20, 40 respectively for the 4 classes?
- how much improve I can expect after apply these settings?