Struct NetworkOptions

Holoscan v2.1.0
struct NetworkOptions

Parameters for Engine creation.

Public Members

bool use_fp16 = true

Use FP16 in engine generation.

std::vector<int32_t> batch_sizes = {1}

Batch sizes supported.

int32_t max_batch_size = 1

Max batch size allowed.

size_t max_memory = 10000000000

Maximum GPU memory allocated for model conversion.

int device_index = 0

GPU device.

Previous Struct InferenceSpecs
Next Template Struct is_array
© Copyright 2022-2024, NVIDIA. Last updated on Jun 17, 2024.