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

2 次查看（过去 30 天）
Ahmed Zaafouri
Ahmed Zaafouri 2022-12-3
回答： Joss Knight 2022-12-18
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 个评论
Ahmed Zaafouri
Ahmed Zaafouri 2022-12-3
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

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Joss Knight
Joss Knight 2022-12-18
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.

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品


版本

R2018a

Community Treasure Hunt

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

Start Hunting!

Translated by