[BUG] Input Tensor Not Shown on 'graph_view'

paulgavrikov / visualkeras

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

582 stars 67 forks source link

[BUG] Input Tensor Not Shown on 'graph_view' #67

Closed Soontosh closed 4 months ago

Soontosh commented 4 months ago

Title.

Code to reproduce:

model = Sequential()
model.add(Dense(16, input_dim=16, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

graph_view(model_ANN, to_file='output_folder/graph/ANN.png')

Output:

This happens even if an 'InputLayer' is specified.

I will leave this as is in release 0.1. Will be fixed in release 0.1.1.

Soontosh commented 4 months ago

Resolved in PR 71