I've noticed a potential typo error. A few days ago, you removed the dim parameter in the MeshAutoencoder, but I still see it being used here. Is this a typo error?
for _ in range(local_attn_encoder_depth):
self.encoder_local_attn_blocks.append(nn.ModuleList([
LocalMHA(dim = dim, **attn_kwargs, **local_attn_kwargs),
nn.Sequential(RMSNorm(curr_dim), FeedForward(curr_dim, glu = True, dropout = ff_dropout))
]))
Hi Phil,
I've noticed a potential typo error. A few days ago, you removed the
dim
parameter in theMeshAutoencoder
, but I still see it being used here. Is this a typo error?Best regards, Xueqi