Large dataset that needs continuous training

facebookresearch / poincare-embeddings

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

Other

1.68k stars 231 forks source link

Large dataset that needs continuous training #84

Open lkcao opened 2 years ago

lkcao commented 2 years ago

Hi there, I have a quite large dataset and GPU usage that does not exceed 24 hours. In this case, I need to restore from checkpoint and continue to train the old models. The current situation is that, each time I try to do so, it is shown that the dimension of parameters is not correct--originally I train a 2-dimension embedding but now the dim of parameter is 21. Any thoughts on this? Any advice?

Clarioooo commented 5 months ago

Hello, I wonder if your problem has been solved. I need to use the Poincaré embeddings to my dataset's label hierarchy, How do you train it on your own dataset? Do I only need to change the file opened in transitive_closure.py and run this script, and leave the rest unchanged?