THOP: PyTorch-OpCounter

How to install

Through PyPi

pip install thop
Using GitHub (always latest)

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)	FLOPs(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)	FLOPs(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

Download files

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

Source Distribution

thop-0.0.30-190806.tar.gz (4.1 kB view details)

Uploaded Aug 6, 2019 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

thop-0.0.30.post190806-py3-none-any.whl (5.6 kB view details)

Uploaded Aug 6, 2019 Python 3

File details

Details for the file thop-0.0.30-190806.tar.gz.

File metadata

Download URL: thop-0.0.30-190806.tar.gz
Upload date: Aug 6, 2019
Size: 4.1 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.7.3

File hashes

Hashes for thop-0.0.30-190806.tar.gz
Algorithm	Hash digest
SHA256	`126df0082e13d21164959e2087ad10f160b076a1654a1c5e6e48979a4c225dd4`
MD5	`f7e6032664e38b90dc6b3d4ffc52f0a7`
BLAKE2b-256	`cbb0dc61f22c849c5fb8a273e26750665d5e1fc02d74b76e5e96c82167c0093f`

See more details on using hashes here.

File details

Details for the file thop-0.0.30.post190806-py3-none-any.whl.

File metadata

Download URL: thop-0.0.30.post190806-py3-none-any.whl
Upload date: Aug 6, 2019
Size: 5.6 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.7.3

File hashes

Hashes for thop-0.0.30.post190806-py3-none-any.whl
Algorithm	Hash digest
SHA256	`f9b0f4579ff010cc0b07f175786c993a08aa6073a9874e18ab54df7e424b3d34`
MD5	`29399d19420c74e614c605210bda4719`
BLAKE2b-256	`4a0827efe0dee0478e534d993362a764692d71303f91dbb7ac8bdae2652c124c`