- Get a new GPU with more memory
- Use a smaller model
- If your model accepts a variable input size, use a smaller input
- For object detectors, reduce the number of patches per image
- Run on the CPU
How to increase MiniBatchSize
2 visualizzazioni (ultimi 30 giorni)
Mostra commenti meno recenti
Name: 'NVIDIA GeForce RTX 2060'
Index: 1
ComputeCapability: '7.5'
SupportsDouble: 1
DriverVersion: 11.7000
ToolkitVersion: 11.2000
MaxThreadsPerBlock: 1024
MaxShmemPerBlock: 49152
MaxThreadBlockSize: [1024 1024 64]
MaxGridSize: [2.1475e+09 65535 65535]
SIMDWidth: 32
TotalMemory: 6.4421e+09
AvailableMemory: 5.0929e+09
MultiprocessorCount: 30
ClockRateKHz: 1200000
ComputeMode: 'Default'
GPUOverlapsTransfers: 1
KernelExecutionTimeout: 1
CanMapHostMemory: 1
DeviceSupported: 1
DeviceAvailable: 1
DeviceSelected: 1
** This is my GPU , so how can i increase MiniBatchSize more than 2 , with out error
0 Commenti
Risposte (1)
Joss Knight
il 11 Ago 2022
It depends on what you're doing. Some ideas:
0 Commenti
Vedere anche
Categorie
Scopri di più su Image Data Workflows in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!