Tensor Cores and deep learning
5 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Gerardo Suarez
le 24 Juin 2019
Commenté : Alexander Sonin
le 3 Déc 2021
Dear all
I have a GeForce RTX 2060. How can I take advantage of its 240 tensor cores for deep learning? I have read that I should set the precision to FP16, but using the "trainnetwork" function there does not seem to be any option.
Thank you
1 commentaire
Réponse acceptée
Krishna Bindumadhavan
le 14 Sep 2019
Modifié(e) : Krishna Bindumadhavan
le 14 Sep 2019
Currently, there is no support for training a neural network with half precision data type. This is expected in a future release.
You can however take advantage of tensor cores, while generating code for deploying a trained neural network with GPU Coder. You can look at Deep Learning Prediction with NVIDIA TensorRT example , but set the DataType property of the DeepLearningConfig to 'fp16'. This will use the Tensor cores on a Volta or Turing card such as the RTX series for inference.
In addition, MATLAB supports the half data type via the half precision object in the fixed point designer toolbox: https://www.mathworks.com/help/fixedpoint/ref/half.html?s_tid=doc_ta. General code generation support for the half type, via MATLAB Coder and GPU coder is under active development and can be expected in an upcoming release.
1 commentaire
Alexander Sonin
le 3 Déc 2021
Krishna kept silent about the exact answer to this question: MATLAB cannot use tensor cores to train neural networks !!!
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Deep Learning with GPU Coder dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!