search

vita-epfl / bounding-box-prediction

Bounding box prediction library. Official implementation of two papers on human 2D/3D bounding box prediction
48 stars 14 forks source link

you are losing the batch information #13

Closed Cram3r95 closed 1 year ago

Cram3r95 commented 2 years ago

imagen

Why do you do this? You are losing your batch information, since you go from:

obs_len x batch_size x 2

To:

obs_len x hidden_dim

This does not make sense.

SaeedSaadatnejad commented 1 year ago

Hello,

Which part of the code are you referring to? As far as I see, nothing is lost about the batch_size. Only a permutation is done to make the dimensions correct for lstm encoders.