THOP: PyTorch-OpCounter

0.1.1.post2209072238 · maintenance · verified Sat Apr 11

THOP (PyTorch-OpCounter) is a Python library designed to calculate the Multiply-Accumulate Operations (MACs) and parameters of PyTorch models. It provides an intuitive API for deep learning practitioners to evaluate the computational efficiency and memory footprint of their models, aiding in optimization and architecture selection. The current PyPI version is 0.1.1.post2209072238, released in September 2022, indicating a less active maintenance cadence for this specific branch.

Warnings

gotcha THOP primarily reports Multiply-Accumulate Operations (MACs). The interpretation of 1 MAC as 1 FLOP or 2 FLOPs (multiplication + addition) varies across literature and tools. Be mindful of this distinction when comparing results with other FLOPs counters.
Fix: Understand that `thop`'s 'FLOPs' often refer to MACs. If strict FLOPs (e.g., each multiplication and addition counts as 1 FLOP) are needed, manually multiply `thop`'s MAC count by 2 for comparison, or refer to its internal definitions.
gotcha For models containing custom PyTorch modules or third-party layers not natively supported by `thop`, accurate MACs and parameter counting requires defining custom profiling rules via the `custom_ops` argument in the `profile` function.
Fix: Refer to the `thop` documentation or examples on how to define `custom_ops` for unsupported module types to ensure comprehensive and accurate profiling.
deprecated The `thop` library at `github.com/Lyken17/pytorch-OpCounter` (and PyPI version 0.1.1.post2209072238) has not been updated since September 2022. A more actively maintained fork, `ultralytics/thop`, exists with newer versions and continuous development.
Fix: For active development or newer PyTorch compatibility, consider evaluating `ultralytics/thop` (installed via `pip install ultralytics-thop`) or explicitly checking the `Lyken17` repository for any new activity before relying on this version.

Install

pip install thop PyPI

Imports

profile
```
from thop import profile
```
clever_format
```
from thop import clever_format
```

Quickstart

This quickstart demonstrates how to use `thop` to calculate the Multiply-Accumulate Operations (MACs) and parameters of a standard PyTorch model, then format the output for better readability.

import torch
import torch.nn as nn
from torchvision.models import resnet18
from thop import profile, clever_format

# 1. Define a model and a dummy input
model = resnet18()
dummy_input = torch.randn(1, 3, 224, 224)

# 2. Profile the model
macs, params = profile(model, inputs=(dummy_input, ), verbose=False)

# 3. Format the output for readability
macs, params = clever_format([macs, params], "%.3f")

print(f"MACs: {macs}")
print(f"Parameters: {params}")

view raw JSON →