Reputation: 61
I tried example code of tensorflow spiral dataset and constructed the neural network. I wanted to visualize the graphical structure of the network. PFB the code i tried.
with tf.Graph().as_default():
net = tflearn.input_data([None, 2])
net = tflearn.fully_connected(net,6,
activation='tanh',weights_init='normal')
print(net)
Upvotes: 4
Views: 3785
Reputation: 28198
To visualize a graph, you should use TensorBoard. Here is a tutorial for how to use it.
You can add at the end of your code a summary writer, which will write an event file (containing the visualization of the graph) into the given location.
graph = tf.Graph()
with graph.as_default():
net = tflearn.input_data([None, 2])
net = tflearn.fully_connected(net,6,
activation='tanh',weights_init='normal')
sess = tf.Session(graph=graph)
writer = tf.train.SummaryWriter('tmp/tensorboard_log', sess.graph)
Then you just need to run tensorboard --logdir tmp/tensorboard_log
and go in your browser to localhost:6006/#graphs
.
Upvotes: 3