search

Ninebell / GaneratedHandsForReal_TIME

it referenced paper of GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB.
MIT License
86 stars 17 forks source link

About RegNet Weights #18

Open egemenertugrul opened 3 years ago

egemenertugrul commented 3 years ago

Hey, thank you for sharing the RegNet weights in .h5 format. I'd like to know how many epochs this model was trained. Was it 100 or less than 100?

egemenertugrul commented 3 years ago

Alright, based on the original code test_regnet.py: reg.model.load_weights("D:\RegNet\\result\\17\\regnet.h5")

So I believe the given regnet.h5 model was trained 17 epochs.