The training accuracy of "trainNetwork" decreases a lot when I used another computer
1 visualización (últimos 30 días)
Mostrar comentarios más antiguos
Fu-Chen Chen
el 11 de Sept. de 2016
Comentada: Joss Knight
el 27 de Sept. de 2016
I ran EXACT the same code on two computers with function "trainNetwork" to train Convolutional Neural Networks. Both of the computers have Matlab R2016a installed. One with GPU nVidia Quadro 3000M have 99%~100% training accuracy. But the other one with newer GPU GTX 1070 only have about 65% training accuracy, and the accuracy doesn't improve through the training iterations. Is it possible that Matlab doesn't support the latest nVidia GPU?
0 comentarios
Respuesta aceptada
Joss Knight
el 19 de Sept. de 2016
NVIDIA doesn't support the latest NVIDIA GPU:
Sorry :-(
2 comentarios
Dalibor Knis
el 22 de Sept. de 2016
How does this information relates to official cuDNN release page information that "cuDNN is supported on Windows, Linux and MacOS systems with Pascal.." https://developer.nvidia.com/cudnn
I am confused.
Joss Knight
el 27 de Sept. de 2016
The latest version of cuDNN does support Pascal. The versions in MATLAB R2016a and R2016b do not. MATLAB builds with and ships with the version of cuDNN current at the time the product is completed. To upgrade an old version of MATLAB after product release is not possible. However, we have asked NVIDIA for a back-ported fix for the older versions of cuDNN, which we will bring to you as soon as we have received that. Keep your eye on the bug report.
Más respuestas (0)
Ver también
Categorías
Más información sobre Deep Learning Toolbox en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!