ptflops

library0.7.5pypypiunverified

A Flops counter for neural networks in PyTorch. It computes the number of floating point operations (FLOPs) and parameters of a model. The current version is 0.7.5, with a slow release cadence.

ai-ml

pip install ptflops

github ↗package ↗docs ↗changelog ↗

INSTALL

IMPORT

SIG · PTFLOPS

ptflops

ai-mlpythonv0.7.5

Install

66.2s avg

Import

—

Disk

4787MB

Pass rate

4/ 10

Env Coverage4 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.7.5 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

✓ 73.6s

py 3.11

✕ build_error

✓ 69.5s

py 3.12

✕ build_error

✓ 65.2s

py 3.13

✕ build_error

✓ 56.3s

py 3.9

✕ build_error

✕ timeout

4787MB installed

● package 4787MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

get_model_complexity_info

✓ from ptflops import get_model_complexity_info

✗ from ptflops.flops_counter import get_model_complexity_info

Old import path (pre-0.7) is deprecated.

Compute FLOPs and parameters for ResNet-18 with a 224x224 input.

import torch from ptflops import get_model_complexity_info import torchvision.models as models net = models.resnet18() macs, params = get_model_complexity_info(net, (3, 224, 224), as_strings=True, print_per_layer_stat=True) print('{:<30} {:<8}'.format('Computational complexity: ', macs)) print('{:<30} {:<8}'.format('Number of parameters: ', params))

Debug

Known issues

deprecatedImporting from ptflops.flops_counter directly is deprecated. Use from ptflops import get_model_complexity_info instead.

fix

Change import to 'from ptflops import get_model_complexity_info'.

affects: >=0.7

gotchaThe function returns MACs (multiply-accumulate operations), not FLOPs. MACs are roughly half of FLOPs.

fix

Multiply the returned MACs by 2 to get FLOPs if needed.

affects: all

gotchaFor models with batch normalization, the flops count may be inaccurate if the model is not in eval mode.

fix

Set model.eval() before calling get_model_complexity_info.

affects: all

breakingThe function signature changed in version 0.7. The parameter 'input_res' was removed and replaced with 'input_shape' (tuple).

fix

Pass input_shape=(3, 224, 224) instead of input_res=224.

affects: >=0.7

Upgrade

Version history

0.7.5latest on PyPI · released Aug 20, 2025

Audit

Dependencies

torchrequiredPyTorch is required to define models and run flops computation.

Agent activity

9 hits · last 30 days

node

Resources

githubhttps://github.com/sovrasov/flops-counter.pytorch ↗

packagehttps://pypi.org/project/ptflops/ ↗

docshttps://github.com/sovrasov/flops-counter.pytorch/blob/master/README.md ↗

changeloghttps://github.com/sovrasov/flops-counter.pytorch/blob/master/CHANGELOG.md ↗