THOP: PyTorch-OpCounter

How to install

pip install thop (now continously intergrated on Github actions)

pip install --upgrade git+https://github.com/Lyken17/pytorch-OpCounter.git

How to use

Basic usage

from torchvision.models import resnet50
from thop import profile
model = resnet50()
input = torch.randn(1, 3, 224, 224)
flops, params = profile(model, inputs=(input, ))

Define the rule for 3rd party module.

class YourModule(nn.Module):
    # your definition
def count_your_model(model, x, y):
    # your rule here

input = torch.randn(1, 3, 224, 224)
flops, params = profile(model, inputs=(input, ), 
                        custom_ops={YourModule: count_your_model})

Improve the output readability

Call thop.clever_format to give a better format of the output.

from thop import clever_format
flops, params = clever_format([flops, params], "%.3f")

Results on Recent Models

Model	Params(M)	MACs(G)
alexnet	58.27	0.72
densenet121	7.61	2.70
densenet161	27.35	7.31
densenet169	13.49	3.20
densenet201	19.09	4.09
resnet18	11.15	1.70
resnet34	20.79	3.43
resnet50	24.37	3.85
resnet101	42.49	7.33
resnet152	57.40	10.81

Model	Params(M)	MACs(G)
squeezenet1_0	1.19	0.77
squeezenet1_1	1.18	0.33
vgg11	126.71	7.21
vgg11_bn	126.71	7.24
vgg13	126.88	10.66
vgg13_bn	126.89	10.70
vgg16	131.95	14.54
vgg16_bn	131.96	14.59
vgg19	137.01	18.41
vgg19_bn	137.02	18.47

Release files for thop 0.0.30-1908282117

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for thop 0.0.30-1908282117
File	Interpreter	ABI	Platform	Reset
thop-0.0.30.post1908282117-py3-none-any.whl 6.1 kB Aug 28, 2019	Python 3	none	any	Details

Release files / thop-0.0.30.post1908282117-py3-none-any.whl

Download URL	thop-0.0.30.post1908282117-py3-none-any.whl
Size	6.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`f82c24755e2128288a424a975a9ef5062416f36eefd2976b3c0a9564767f8429`
BLAKE2b-256 checksum How to use checksums	`7732f81064f8995f1849062a9c69f3460121c5d49da2d240c259e2c764e84503`
Upload date	Aug 28, 2019
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.35.0 CPython/3.7.4`