Giters

lucidrains / anymal-belief-state-encoder-decoder-pytorch

Implementation of the Belief State Encoder / Decoder in the new breakthrough robotics paper from ETH Zürich

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

student training

lucidrains opened this issue · comments

commented

i'm fairly sure i got the student network correct, as well as the teacher -> student distillation code

but not confident about how the rollouts are done (and the subsequent learning and truncated BPTT)

commented

Hi, regarding the GRUCell in the Student network. How can you pass as input a batch of sequence features of shape: (batch_size, time, feature_size) ? For Example a Tensor of size: (16, 60, 2048).
From the pytorch documentation, the GRUCell() class can only take inputs with shape: (N, Hin) or (H_{in})(Hin) tensor containing input features where H_{in}Hin = input_size.
Why not use the GRU() Class? I need to keep the temporality in my input and not flatten it with the feature dim.