search

facebookresearch / meshtalk

Code for MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement
Other
368 stars 56 forks source link

Dimensions of training data #29

Closed JSHZT closed 2 years ago

JSHZT commented 2 years ago

What is the shape of the data for each iteration of your dataloader iterator? Is it (BxTxVx3)?

alexanderrichard commented 2 years ago

The datareader returns elements of shape T x V x 3. So, if you wrap this into a torch DataLoader, you will get batches of shape B x T x V x 3.