One Use pytorchviz visualization

• Install dependencies and pytorchviz

pip install graphviz
pip install tochviz （ or pip install git+https://github.com/szagoruyko/pytorchviz）

Graphviz yes AT&T Developed an open source graphics visualization software , According to dot An undirected graph drawn in a scripting language （ Shows the simplest relationships between objects ） Draw an intuitive tree diagram .
Graphviz stay Windows Installation in needs to be downloaded Release package , And configure environment variables , Otherwise, an error will be reported ：

graphviz.backend.ExecutableNotFound: failed to execute [‘dot’, ‘-Tpng’, ‘-O’, ‘tmp’], make sure the Graphviz executables are on your systems’ PATH

Graphviz Download address https://graphviz.gitlab.io/_pages/Download/Download_windows.html

After downloading, it's a “release” Folder , hold “release\bin” Directories adding to system environment variables , After that, input “dot -V”, Display the following information to indicate Graphviz Configuration is successful ：

• torchviz visualization torch Network structure

# Created by Pastoral CSDN
import torch
from torch import nn
from torchviz import make_dot, make_dot_from_trace
model = nn.Sequential()
model.add_module('W0', nn.Linear(8, 16))
model.add_module('tanh', nn.Tanh())
model.add_module('W1', nn.Linear(16, 1))
x = torch.randn(1,8)
vis_graph = make_dot(model(x), params=dict(model.named_parameters()))
vis_graph.view() # Will save one in the current directory “Digraph.gv.pdf” file , And open... In the default browser
with torch.onnx.set_training(model, False):
trace, _ = torch.jit.get_trace_graph(model, args=(x,))
make_dot_from_trace(trace)

call “make_dot” Method to create a dot object , Use “view” The method shows .

pytorch1.2 and 1.3 Used in version “torch.jit.get_trace_graph” There may be a mistake ,1.1 edition ok.

AttributeError: 'torch._C.Value' object has no attribute 'uniqueName'

Visualization results ：

Two Use Netron visualization

Netron Open source address ： https://github.com/lutzroeder/Netron
Netron The developers are Lutz Roeder, One from Microsoft Visual Studio The handsome guy of the team ：

Netron Is a support offline view “ Various ” Model visualization artifact of neural network framework , Among them “ Various ” Include ：

1. ONNX (.onnx, .pb, .pbtxt)
2. Keras (.h5, .keras)
3. Core ML (.mlmodel)
4. Caffe (.caffemodel, .prototxt)
5. Caffe2 (predict_net.pb, predict_net.pbtxt)
6. MXNet (.model, -symbol.json)
7. NCNN (.param)
8. TensorFlow Lite (.tflite)
9. TorchScript (.pt, .pth)
10. PyTorch (.pt, .pth)
11. Torch (.t7)
12. Arm NN (.armnn)
13. BigDL (.bigdl, .model)
14. Chainer, (.npz, .h5)
15. CNTK (.model, .cntk)
16. Deeplearning4j (.zip)
17. Darknet (.cfg)
18. ML.NET (.zip)
19. MNN (.mnn)
20. OpenVINO (.xml)
21. PaddlePaddle (.zip, __model__)
22. scikit-learn (.pkl)
23. TensorFlow.js (model.json, .pb)
24. TensorFlow (.pb, .meta, .pbtxt)

Um. , That's enough .

Netron It's easy to use , The author provides installation packages for each platform , Open after installation , Drag the saved model file in .
Take the model above as an example , The first pytorch The model is saved ：

import torch
from torch import nn
from torchviz import make_dot, make_dot_from_trace
model = nn.Sequential()
model.add_module('W0', nn.Linear(8, 16))
model.add_module('tanh', nn.Tanh())
model.add_module('W1', nn.Linear(16, 1))
torch.save(model, 'model.pth')  # Save the model 

After use Netron Open the saved “model.pth”：

The network structure is very clear , Be clear at a glance , Further information about the operation can also be displayed on the right side .

If you're too lazy to install , You can also use the author's online Netron viewer , Address ：https://lutzroeder.github.io/netron/