GPU is not detected

4 次查看（过去 30 天）
Shaw
Shaw 2021-11-19
回答： Animesh Gupta 2022-9-1
I am trying to run the example code
"Parameter Pruning and Quantization of Image Classification Network - MATLAB & Simulink (mathworks.com)"
Even though I am running on a GPU. I am getting an error
I have used the command gpuDevice. These are my GPU properties
gpuDevice
ans =
CUDADevice with properties:
Name: 'Tesla V100-SXM2-16GB'
Index: 1
ComputeCapability: '7.0'
SupportsDouble: 1
DriverVersion: 11.2000
ToolkitVersion: 11
MaxThreadsPerBlock: 1024
MaxShmemPerBlock: 49152
MaxThreadBlockSize: [1024 1024 64]
MaxGridSize: [2.1475e+09 65535 65535]
SIMDWidth: 32
TotalMemory: 1.6946e+10
AvailableMemory: 1.6009e+10
MultiprocessorCount: 80
ClockRateKHz: 1530000
ComputeMode: 'Default'
GPUOverlapsTransfers: 1
KernelExecutionTimeout: 0
CanMapHostMemory: 1
DeviceSupported: 1
DeviceAvailable: 1
DeviceSelected: 1

请先登录，再回答此问题。

回答（1 个）

Animesh Gupta
Animesh Gupta 2022-9-1
Hello,
It is my understanding that you are unable to run the calibrate method for the dlquantizer object, although you have a GPU that is recognized by MATLAB.
There are certain prerequisites that we need to meet before we can quantize and deploy deep learning networks, e,g,, setting up the prerequisite products, ensuring that the compiler is compatible with our workflow amd the supported networks/classes/layers that we can quantize and deploy.
The documentation link here might be helpful to know about some of these pre-requisites.
Hope this helps!

类别

在 Help Center 和 File Exchange 中查找有关 Quantization, Projection, and Pruning 的更多信息

标签

产品


版本

R2021a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by