johndpope
commented
5 months ago at quick glance - this paper originated from google / tensorflow - so it seems the training / eval test sets that are baked into tensorflow got ported across.
"""Return training and evaluation/test datasets from config files.""" import jax import tensorflow as tf import tensorflow_datasets as tfds
plus tensorboard
The code below is from run_lib.py. I just wanna ask why there exists the tensorflow in the pytorch version of score_sde. Thanks for your answer
import numpy as np import tensorflow as tf import tensorflow_gan as tfgan import logging from models import ddpm, ncsnv2, ncsnpp import losses import sampling from models import utils as mutils from models.ema import ExponentialMovingAverage import datasets import evaluation import likelihood import sde_lib from absl import flags import torch from torch.utils import tensorboard from torchvision.utils import make_grid, save_image from utils import save_checkpoint, restore_checkpoint