When I want to train Fully convolutional neural network, I have the following error

1 view (last 30 days)
Error using trainNetwork (line 154)
Unexpected error calling cuDNN: CUDNN_STATUS_BAD_PARAM.
Error in Essai_example (line 154)
net = trainNetwork(trainingData,lgraph,options);
Caused by:
Error using nnet.internal.cnngpu.convolveForward2D
Unexpected error calling cuDNN: CUDNN_STATUS_BAD_PARAM.
  2 Comments
Ahmed Zaafouri
Ahmed Zaafouri on 3 Dec 2022
Matlab R2018a
and gpuDevice has the following characteristics
CUDADevice with properties:
Name: 'GeForce MX110'
Index: 1
ComputeCapability: '5.0'
SupportsDouble: 1
DriverVersion: 11.2000
ToolkitVersion: 9
MaxThreadsPerBlock: 1024
MaxShmemPerBlock: 49152
MaxThreadBlockSize: [1024 1024 64]
MaxGridSize: [2.1475e+09 65535 65535]
SIMDWidth: 32
TotalMemory: 2.1475e+09
AvailableMemory: 1.6950e+09
MultiprocessorCount: 2
ClockRateKHz: 1006000
ComputeMode: 'Default'
GPUOverlapsTransfers: 1
KernelExecutionTimeout: 1
CanMapHostMemory: 1
DeviceSupported: 1
DeviceSelected: 1

Sign in to comment.

Answers (1)

Joss Knight
Joss Knight on 18 Dec 2022
I suspect your best bet here is to upgrade MATLAB to a more recent version. Many of these bugs will be fixed with newer versions of the NVIDIA libraries.

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Products


Release

R2018a

Community Treasure Hunt

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

Start Hunting!