【画图】基于Python的神经网络可视化工具

项目链接：

https://github.com/Prodicode/ann-visualizer?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more

A python library for visualizing Artificial Neural Networks (ANN)

如何安装

From Github

1. Download the ann_visualizer folder from the github repository.
2. Place the ann_visualizer folder in the same directory as your main python script.

From pip

Use the following command:

pip3 install ann_visualizer

Make sure you have graphviz installed. Install it using:

sudo apt-get install graphviz && pip3 install graphviz

人工神经网络绘图示例

import keras;
from keras.models import Sequential;
from keras.layers import Dense;

network = Sequential();
        #Hidden Layer#1
network.add(Dense(units=6,
                  activation='relu',
                  kernel_initializer='uniform',
                  input_dim=11));

        #Hidden Layer#2
network.add(Dense(units=6,
                  activation='relu',
                  kernel_initializer='uniform'));

        #Exit Layer
network.add(Dense(units=1,
                  activation='sigmoid',
                  kernel_initializer='uniform'));

from ann_visualizer.visualize import ann_viz;

ann_viz(network, title="");

卷积神经网络绘图示例

import keras;
from keras.models import Sequential;
from keras.layers import Dense;
from ann_visualizer.visualize import ann_viz
model = build_cnn_model()
ann_viz(model, title="")

def build_cnn_model():
  model = keras.models.Sequential()

  model.add(
      Conv2D(
          32, (3, 3),
          padding="same",
          input_shape=(32, 32, 3),
          activation="relu"))
  model.add(Dropout(0.2))

  model.add(
      Conv2D(
          32, (3, 3),
          padding="same",
          input_shape=(32, 32, 3),
          activation="relu"))
  model.add(MaxPooling2D(pool_size=(2, 2)))
  model.add(Dropout(0.2))

  model.add(
      Conv2D(
          64, (3, 3),
          padding="same",
          input_shape=(32, 32, 3),
          activation="relu"))
  model.add(Dropout(0.2))

  model.add(
      Conv2D(
          64, (3, 3),
          padding="same",
          input_shape=(32, 32, 3),
          activation="relu"))
  model.add(MaxPooling2D(pool_size=(2, 2)))
  model.add(Dropout(0.2))

  model.add(Flatten())
  model.add(Dense(512, activation="relu"))
  model.add(Dropout(0.2))

  model.add(Dense(10, activation="softmax"))

  return model