Files
Super Daniel 4f59693207 [fx] provide a stable but not accurate enough version of profiler. (#1547)
* [fx] compute memory stat and flop count for MetaInfoProp.

* [fx] modify node attribute.

* [fx] modify ckpt_chen.

* [fx] fix compatibility.

* [fx] fix import error.

* [fx] skip test for MetaInfoProp.

* [fx] skip test for MetaInfoProp.

* [fx] skip test for MetaInfoProp.

* [fx] skip test for MetaInfoProp.

* [fx] skip if torch 1.11.0.

* [fx] recover MetaInfoProp support for PyTorch 1.11.

* [fx] provide a stable but not accurate enough version of profiler.

* [fx] provide a stable but not accurate enough version of profiler.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix compatibility in tests.

* [fx] fix import error.
2022-09-07 11:21:04 +08:00

15 lines
493 B
Python

from typing import Tuple
import torch
from ..registry import meta_profiler_module
@meta_profiler_module.register(torch.nn.Linear)
@meta_profiler_module.register(torch.nn.modules.linear.NonDynamicallyQuantizableLinear)
def torch_nn_linear(self: torch.nn.Linear, input: torch.Tensor) -> Tuple[int, int]:
out_features = self.weight.shape[0]
macs = input.numel() * out_features
flops = 2 * macs
if self.bias is not None:
flops += self.bias.numel()
return flops, macs