Training with different architectures

google-deepmind / kinetics-i3d

Convolutional neural network model for video classification trained on the Kinetics dataset.

Apache License 2.0

1.75k stars 462 forks source link

Training with different architectures #111

Open axelstram opened 3 years ago

axelstram commented 3 years ago

Hi, has anyone tried inflating a model pretrained on Imagenet from 2D to 3D and training on Kinetics using models different from Inception-v1 (like Resnets or Densenets)?. If you have code that you can share I would be very greatful.