facebookresearch / InterHand2.6M

Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020
Other
676 stars 92 forks source link

NB of params and depth #105

Open martin0496 opened 2 years ago

martin0496 commented 2 years ago

Hi sir Can you please help me on how to get information of the number of parameters and the depth of the model Internet that you applied to get these results ? Thank you

mks0601 commented 2 years ago

Add print(sum(p.numel() for p in model.parameters() if p.requires_grad)) right after https://github.com/facebookresearch/InterHand2.6M/blob/2b8061d2c8e762aa6fcb8e6f5d18f8a9e83bfd0c/common/base.py#L93

and run

python train.py --gpu 0