I have a problem when I want to train fully convolutional network even i tried to find the solutions in the mathwork.

1 次查看（过去 30 天）
Ahmed Zaafouri
Ahmed Zaafouri 2022-12-1
评论： Ahmed Zaafouri 2022-12-1
Error using trainNetwork (line 154)
Unexpected error calling cuDNN: CUDNN_STATUS_BAD_PARAM.
Error in fcnAlexNet_US (line 222)
net = trainNetwork(trainingData,lgraph,options);
Caused by:
Error using nnet.internal.cnngpu.convolveForward2D
Unexpected error calling cuDNN: CUDNN_STATUS_BAD_PARAM.
The gpuDevice characteristics are
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: 1.6044e+09
MultiprocessorCount: 2
ClockRateKHz: 1006000
ComputeMode: 'Default'
GPUOverlapsTransfers: 1
KernelExecutionTimeout: 1
CanMapHostMemory: 1
DeviceSupported: 1
DeviceSelected: 1

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Introduction to Installation and Licensing 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by