TODO for next refacto

Jump to bottom

ThibaultGROUEIX edited this page Oct 30, 2019 · 10 revisions

factorize SVR and autoencoder
factorise Square template and Sphere
latent vector added as bais (30% speedup)
remove last th in decoder
make large .pth tensor with all pointclouds (drop the nasty Chunk_reader)
make-it multi-gpu (at least change all .cuda() to to.device()
add netvision results
rewrite main script object oriented like 3D-CODED
check that everything works in latest pytorch version
Add more layer by default and flag for the number of layers