microsoft / VoTT

Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
MIT License
4.31k stars 838 forks source link

Reshape image in Custom Active Learning #1045

Open TaeseongMoon opened 3 years ago

TaeseongMoon commented 3 years ago

Normaly, Input image should be reshape for matching model input shape. when use tfjs model's execute function, is it unnecessary? I can't find any preprocess except expandDims.