TensorRT 10.5.0
nvinfer1::Weights Class Reference

An array of weights used as a layer parameter. More...

#include <NvInferRuntime.h>

Public Attributes

DataType type
 The type of the weights. More...
 
void const * values
 The weight values, in a contiguous array. More...
 
int64_t count
 The number of weights in the array. More...
 

Detailed Description

An array of weights used as a layer parameter.

When using the DLA, the cumulative size of all Weights used in a network must be less than 512MB in size. If the build option kGPU_FALLBACK is specified, then multiple DLA sub-networks may be generated from the single original network.

The weights are held by reference until the engine has been built. Therefore the data referenced by values field should be preserved until the build is complete.

The term "empty weights" refers to Weights with weight coefficients ( count == 0 and values == nullptr).

Member Data Documentation

◆ count

int64_t nvinfer1::Weights::count

The number of weights in the array.

◆ type

DataType nvinfer1::Weights::type

The type of the weights.

◆ values

void const* nvinfer1::Weights::values

The weight values, in a contiguous array.


The documentation for this class was generated from the following file:

  Copyright © 2024 NVIDIA Corporation
  Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact