Data

Tools

Indexes

Applications

Experiments

Open Source Science

py-torchsummary

Model summary in PyTorch similar to `model.summary()` in Keras

https://github.com/sksq96/pytorch-summary

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ✓
    Committers with academic emails
    1 of 10 committers (10.0%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.4%) to scientific vocabulary

Keywords

deep-learning keras pytorch summary
Last synced: 6 months ago · JSON representation

Repository

Model summary in PyTorch similar to `model.summary()` in Keras

Basic Info
  • Host: GitHub
  • Owner: sksq96
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 43 KB
Statistics
  • Stars: 4,043
  • Watchers: 35
  • Forks: 415
  • Open Issues: 139
  • Releases: 0
Topics
deep-learning keras pytorch summary
Created almost 8 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License

README.md

Use the new and updated torchinfo.

Keras style model.summary() in PyTorch

PyPI version

Keras has a neat API to view the visualization of the model which is very helpful while debugging your network. Here is a barebone code to try and mimic the same in PyTorch. The aim is to provide information complementary to, what is not provided by print(your_model) in PyTorch.

Usage

  • pip install torchsummary or
  • git clone https://github.com/sksq96/pytorch-summary

python from torchsummary import summary summary(your_model, input_size=(channels, H, W))

  • Note that the input_size is required to make a forward pass through the network.

Examples

CNN for MNIST

```python import torch import torch.nn as nn import torch.nn.functional as F from torchsummary import summary

class Net(nn.Module): def init(self): super(Net, self).init() self.conv1 = nn.Conv2d(1, 10, kernelsize=5) self.conv2 = nn.Conv2d(10, 20, kernelsize=5) self.conv2_drop = nn.Dropout2d() self.fc1 = nn.Linear(320, 50) self.fc2 = nn.Linear(50, 10)

def forward(self, x):
    x = F.relu(F.max_pool2d(self.conv1(x), 2))
    x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
    x = x.view(-1, 320)
    x = F.relu(self.fc1(x))
    x = F.dropout(x, training=self.training)
    x = self.fc2(x)
    return F.log_softmax(x, dim=1)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # PyTorch v0.4.0 model = Net().to(device)

summary(model, (1, 28, 28)) ```

```

    Layer (type)               Output Shape         Param #

================================================================ Conv2d-1 [-1, 10, 24, 24] 260 Conv2d-2 [-1, 20, 8, 8] 5,020 Dropout2d-3 [-1, 20, 8, 8] 0 Linear-4 [-1, 50] 16,050

Linear-5 [-1, 10] 510

Total params: 21,840 Trainable params: 21,840

Non-trainable params: 0

Input size (MB): 0.00 Forward/backward pass size (MB): 0.06 Params size (MB): 0.08

Estimated Total Size (MB): 0.15

```

VGG16

```python import torch from torchvision import models from torchsummary import summary

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') vgg = models.vgg16().to(device)

summary(vgg, (3, 224, 224)) ```

```

    Layer (type)               Output Shape         Param #

================================================================ Conv2d-1 [-1, 64, 224, 224] 1,792 ReLU-2 [-1, 64, 224, 224] 0 Conv2d-3 [-1, 64, 224, 224] 36,928 ReLU-4 [-1, 64, 224, 224] 0 MaxPool2d-5 [-1, 64, 112, 112] 0 Conv2d-6 [-1, 128, 112, 112] 73,856 ReLU-7 [-1, 128, 112, 112] 0 Conv2d-8 [-1, 128, 112, 112] 147,584 ReLU-9 [-1, 128, 112, 112] 0 MaxPool2d-10 [-1, 128, 56, 56] 0 Conv2d-11 [-1, 256, 56, 56] 295,168 ReLU-12 [-1, 256, 56, 56] 0 Conv2d-13 [-1, 256, 56, 56] 590,080 ReLU-14 [-1, 256, 56, 56] 0 Conv2d-15 [-1, 256, 56, 56] 590,080 ReLU-16 [-1, 256, 56, 56] 0 MaxPool2d-17 [-1, 256, 28, 28] 0 Conv2d-18 [-1, 512, 28, 28] 1,180,160 ReLU-19 [-1, 512, 28, 28] 0 Conv2d-20 [-1, 512, 28, 28] 2,359,808 ReLU-21 [-1, 512, 28, 28] 0 Conv2d-22 [-1, 512, 28, 28] 2,359,808 ReLU-23 [-1, 512, 28, 28] 0 MaxPool2d-24 [-1, 512, 14, 14] 0 Conv2d-25 [-1, 512, 14, 14] 2,359,808 ReLU-26 [-1, 512, 14, 14] 0 Conv2d-27 [-1, 512, 14, 14] 2,359,808 ReLU-28 [-1, 512, 14, 14] 0 Conv2d-29 [-1, 512, 14, 14] 2,359,808 ReLU-30 [-1, 512, 14, 14] 0 MaxPool2d-31 [-1, 512, 7, 7] 0 Linear-32 [-1, 4096] 102,764,544 ReLU-33 [-1, 4096] 0 Dropout-34 [-1, 4096] 0 Linear-35 [-1, 4096] 16,781,312 ReLU-36 [-1, 4096] 0 Dropout-37 [-1, 4096] 0

Linear-38 [-1, 1000] 4,097,000

Total params: 138,357,544 Trainable params: 138,357,544

Non-trainable params: 0

Input size (MB): 0.57 Forward/backward pass size (MB): 218.59 Params size (MB): 527.79

Estimated Total Size (MB): 746.96

```

Multiple Inputs

```python import torch import torch.nn as nn from torchsummary import summary

class SimpleConv(nn.Module): def init(self): super(SimpleConv, self).init() self.features = nn.Sequential( nn.Conv2d(1, 1, kernel_size=3, stride=1, padding=1), nn.ReLU(), )

def forward(self, x, y):
    x1 = self.features(x)
    x2 = self.features(y)
    return x1, x2

device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model = SimpleConv().to(device)

summary(model, [(1, 16, 16), (1, 28, 28)]) ```

```

    Layer (type)               Output Shape         Param #

================================================================ Conv2d-1 [-1, 1, 16, 16] 10 ReLU-2 [-1, 1, 16, 16] 0 Conv2d-3 [-1, 1, 28, 28] 10

ReLU-4 [-1, 1, 28, 28] 0

Total params: 20 Trainable params: 20

Non-trainable params: 0

Input size (MB): 0.77 Forward/backward pass size (MB): 0.02 Params size (MB): 0.00

Estimated Total Size (MB): 0.78

```

References

License

pytorch-summary is MIT-licensed.

Owner

  • Name: Shubham Chandel
  • Login: sksq96
  • Kind: user

Applied Scientist at @Microsoft working on natural language and code. Previously NYU, @IBM research, @amzn.

GitHub Events

Total
  • Issues event: 6
  • Watch event: 72
  • Issue comment event: 3
  • Pull request event: 2
  • Fork event: 5
Last Year
  • Issues event: 6
  • Watch event: 72
  • Issue comment event: 3
  • Pull request event: 2
  • Fork event: 5

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 46
  • Total Committers: 10
  • Avg Commits per committer: 4.6
  • Development Distribution Score (DDS): 0.304
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Shubham Chandel s****z@g****m 32
Seyyed Hossein Hasanpour c****7@g****m 3
greenmon g****n@k****r 2
Naireen n****2@l****m 2
Lloyd Hughes h****d@g****m 2
xiaofeixia t****z@q****m 1
peakashu 3****u 1
Michael Churchill 1****h 1
CGKim412 4****2 1
Naireen Hussain n****n@m****a 1
Committer Domains (Top 20 + Academic)
mie.utoronto.ca: 1 qq.com: 1 kaist.ac.kr: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 88
  • Total pull requests: 30
  • Average time to close issues: 4 months
  • Average time to close pull requests: over 1 year
  • Total issue authors: 87
  • Total pull request authors: 27
  • Average comments per issue: 2.02
  • Average comments per pull request: 1.03
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 3
  • Pull requests: 2
  • Average time to close issues: about 1 hour
  • Average time to close pull requests: N/A
  • Issue authors: 2
  • Pull request authors: 2
  • Average comments per issue: 0.67
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • JoJo-ops (1)
  • apivovarov (1)
  • iambyd (1)
  • MartinB47 (1)
  • gchhablani (1)
  • Tord-Zhang (1)
  • rohan-paul (1)
  • thinkerthinker (1)
  • swapnil-lader (1)
  • illfang (1)
  • DataXujing (1)
  • nathanpainchaud (1)
  • sidwa (1)
  • mangotree3 (1)
  • londumas (1)
Pull Request Authors
  • z-a-f (3)
  • cijinsama (2)
  • frgfm (2)
  • intexcor (2)
  • rohansh-tty (1)
  • JasonnnW3000 (1)
  • nathanpainchaud (1)
  • mhamdan91 (1)
  • normanrz (1)
  • kice (1)
  • royank (1)
  • cainmagi (1)
  • ClashLuke (1)
  • GCS-ZHN (1)
  • luisherrmann (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 2
  • Total downloads:
    • pypi 139,390 last-month
  • Total docker downloads: 10,565
  • Total dependent packages: 56
    (may contain duplicates)
  • Total dependent repositories: 2,252
    (may contain duplicates)
  • Total versions: 8
  • Total maintainers: 3
pypi.org: torchsummary

Model summary in PyTorch similar to `model.summary()` in Keras

  • Versions: 7
  • Dependent Packages: 56
  • Dependent Repositories: 2,252
  • Downloads: 139,390 Last month
  • Docker Downloads: 10,565
Rankings
Dependent repos count: 0.2%
Dependent packages count: 0.3%
Downloads: 0.8%
Average: 1.2%
Stargazers count: 1.2%
Docker downloads count: 2.0%
Forks count: 2.6%
Maintainers (2)
sksq96 Naireen
Last synced: 6 months ago
spack.io: py-torchsummary

Keras has a neat API to view the visualization of the model which is very helpful while debugging your network. Here is a barebone code to try and mimic the same in PyTorch. The aim is to provide information complementary to, what is not provided by print(your_model) in PyTorch.

  • Versions: 1
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent repos count: 0.0%
Stargazers count: 2.5%
Forks count: 4.5%
Average: 16.1%
Dependent packages count: 57.3%
Maintainers (1)
adamjstewart
Last synced: 6 months ago