Benchmark
Benchmark module
benchmark
benchmark (model:torch.nn.modules.module.Module, sample:torch.Tensor, metrics:Sequence[str]=('size', 'speed', 'compute', 'memory', 'energy'), speed_devices:Optional[Sequence[str|torch.device]]=None, memory_devices:Optional[Sequence[str|torch.device]]=None, energy_devices:Optional[Sequence[str|torch.device]]=None, **kwargs)
Type | Default | Details | |
---|---|---|---|
model | Module | the model to profile (can stay on CPU) | |
sample | Tensor | dummy input of the right shape | |
metrics | Sequence | (‘size’, ‘speed’, ‘compute’, ‘memory’, ‘energy’) | subset of {“size”,“speed”,“compute”,“memory”,“energy”} to compute |
speed_devices | Optional | None | per-family device override; None means “CPU and CUDA if available” |
memory_devices | Optional | None | |
energy_devices | Optional | None | |
kwargs | VAR_KEYWORD | ||
Returns | Dict |