Out of memory on device using GPU

I'm trying to classify images using VGG19 and I have this error: "Out of memory on device".

How can I fix it?

[Walter Roberson]

What does the output of

gpuDevice()

show ?

[Felipe Assunção]

ans =

CUDADevice with properties:

Name: 'GeForce RTX 2060'

Index: 1

ComputeCapability: '7.5'

SupportsDouble: 1

DriverVersion: 10.1000

ToolkitVersion: 9.1000

MaxThreadsPerBlock: 1024

MaxShmemPerBlock: 49152

MaxThreadBlockSize: [1024 1024 64]

MaxGridSize: [2.1475e+09 65535 65535]

SIMDWidth: 32

TotalMemory: 6.4425e+09

AvailableMemory: 4.6098e+09

MultiprocessorCount: 30

ClockRateKHz: 1710000

ComputeMode: 'Default'

GPUOverlapsTransfers: 1

KernelExecutionTimeout: 1

CanMapHostMemory: 1

DeviceSupported: 1

DeviceSelected: 1

Answer 1

[neal paze]

Have you solved the problem? I have the same problem.

[Felipe Assunção]

I don't remember if I solved this problem, but I think that you need to do a review of your dataset size and characteristics. I stayed so disoriented with Matlab that I preferred migrate to Python, using Google Colab. My life change for better 🙏🏼