ModelProfile

class lib.infer.profile.ModelProfile(plugin: ExtractPlugin, max_batch_size: int = 128, channels_last: bool = False, run_time: int = 10)

Bases: object

Benchmark a single PyTorch GPU plugin for inference

Parameters:

• plugin (ExtractPlugin) – The plugin to benchmark for inference

• max_batch_size (int) – The maximum batch size to benchmark to

• channels_last (bool) – True if the input to the plugin is channels last

• run_time (int) – The amount of time, in seconds, to benchmark the plugin at each batch size

Attributes Summary

run_time

The amount of time, in seconds, that benchmarks were ran per batch

Methods Summary

__call__()

Runs benchmarking through the plugin, stores the data and outputs stats

Attributes Documentation

run_time

The amount of time, in seconds, that benchmarks were ran per batch

Methods Documentation

__call__() → None

Runs benchmarking through the plugin, stores the data and outputs stats

Return type:

None

__call__() → None

Runs benchmarking through the plugin, stores the data and outputs stats

Return type:

None

channels_last

True if the plugin expects channels last input

property run_time: int

The amount of time, in seconds, that benchmarks were ran per batch