Official PyTorch implementation of TSDiff models presented in the NeurIPS 2023 paper "Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting"
In /bin/tstr_experiment.py 182, both DeepAREstimator and TransformerEstimator use cpu as default device, maybe add a param like"trainer=Trainer(ctx=mx.gpu())" to accelerate the training and evaluation process by gpu.
@zzkkzz Indeed one can use GPU here but in the experiment setups considered here, the improvements in speed due to GPU are marginal, if any. This is especially true for DeepAR.
In /bin/tstr_experiment.py 182, both DeepAREstimator and TransformerEstimator use cpu as default device, maybe add a param like"trainer=Trainer(ctx=mx.gpu())" to accelerate the training and evaluation process by gpu.