Skip to main content

Flops counter for convolutional networks in pytorch framework

Project description

# Flops counter for convolutional networks in pytorch framework

This script is designed to compute the theoretical amount of multiply-add operations
in convolutional neural networks. It also can compute the number of parameters and
print per-layer computational cost of a given network.

Supported layers:
- Convolution2d (including grouping)
- BatchNorm2d
- Activations (ReLU, PReLU, ELU, ReLU6, LeakyReLU)
- Linear
- Upsample
- Poolings (AvgPool2d, MaxPool2d and adaptive ones)

Requirements: Pytorch 0.4.1 or 1.0, torchvision 0.2.1

Thanks to @warmspringwinds for the initial version of script.

## Install
pip install git+

## Example
import torchvision.models as models
import torch
from ptflops import get_model_complexity_info

with torch.cuda.device(0):
net = models.densenet161()
flops, params = get_model_complexity_info(net, (224, 224), as_strings=True, print_per_layer_stat=True)
print('Flops: ' + flops)
print('Params: ' + params)

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for ptflops, version 0.1
Filename, size File type Python version Upload date Hashes
Filename, size ptflops-0.1-py3-none-any.whl (5.5 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size ptflops-0.1.tar.gz (4.1 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page