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)
macs, 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)
macs, 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
macs, params = clever_format([flops, params], "%.3f")

Results of Recent Models

The implementation are adapted from torchvision. Following results can be obtained using benchmark/evaluate_famours_models.py.

Model	Params(M)	MACs(G)
alexnet	61.10	0.77
vgg11	132.86	7.74
vgg11_bn	132.87	7.77
vgg13	133.05	11.44
vgg13_bn	133.05	11.49
vgg16	138.36	15.61
vgg16_bn	138.37	15.66
vgg19	143.67	19.77
vgg19_bn	143.68	19.83
resnet18	11.69	1.82
resnet34	21.80	3.68
resnet50	25.56	4.14
resnet101	44.55	7.87
resnet152	60.19	11.61
wide_resnet101_2	126.89	22.84
wide_resnet50_2	68.88	11.46

Model	Params(M)	MACs(G)
resnext50_32x4d	25.03	4.29
resnext101_32x8d	88.79	16.54
densenet121	7.98	2.90
densenet161	28.68	7.85
densenet169	14.15	3.44
densenet201	20.01	4.39
squeezenet1_0	1.25	0.82
squeezenet1_1	1.24	0.35
mnasnet0_5	2.22	0.14
mnasnet0_75	3.17	0.24
mnasnet1_0	4.38	0.34
mnasnet1_3	6.28	0.53
mobilenet_v2	3.50	0.33
shufflenet_v2_x0_5	1.37	0.05
shufflenet_v2_x1_0	2.28	0.15
shufflenet_v2_x1_5	3.50	0.31
shufflenet_v2_x2_0	7.39	0.60
inception_v3	27.16	5.75

Metadata

Release files for thop 0.0.31-2005141830

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 0.0.31-2005141830
File	Interpreter	ABI	Platform	Reset
thop-0.0.31.post2005141830-py3-none-any.whl 8.2 kB May 14, 2020	Python 3	none	any	Details

Release files / thop-0.0.31.post2005141830-py3-none-any.whl

Download URL	thop-0.0.31.post2005141830-py3-none-any.whl
Size	8.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`b160b1967bea85e693c14d4e105b9e2cd6749ee760dd85a085ed24f1696df06f`
BLAKE2b-256 checksum How to use checksums	`f427bc77a9517d21a072d54a6c373362eca7f07c73a0d49812df63958196326f`
Upload date	May 14, 2020
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.3.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.7`