Visualkeras is a Python package to help visualize Keras (either standalone or included in TensorFlow) neural network architectures. It allows easy styling to fit most needs. This module supports layered style architecture generation which is great for CNNs (Convolutional Neural Networks), and a graph style architecture, which works great for most models including plain feed-forward networks.
MIT License
586
stars
69
forks
source link
[BUG] layered_view and graph_view functions don't work (Keras version 1.x.x #58
from keras import Sequential
from keras.layers import Dense, LSTM, Dropout, BatchNormalization
# Make sample sequential model. One input layer, one dense layer, one output layer
model = Sequential()
model.add(Dense(10, input_dim=3))
model.compile(optimizer='adam', loss='mse')
# Visualize the model
visualkeras.layered_view(model, to_file='output.png').show()
Above code throws:
AttributeError: module 'tensorflow' has no attribute 'placeholder'
github-actions[bot]
commented
2 months ago
Code to reproduce:
Above code throws:
Versions tested: 1.x
Will fix in next commit.