Skip to content

Instantly share code, notes, and snippets.

@ugik

ugik/lstm tflearn example

Last active April 1, 2018 19:22
Show Gist options
  • Save ugik/cd3b74030512fcd3f7d066904bb7b0a1 to your computer and use it in GitHub Desktop.
Save ugik/cd3b74030512fcd3f7d066904bb7b0a1 to your computer and use it in GitHub Desktop.
Download ZIP
LSTM RNN tflearn example
Raw
lstm tflearn example
# Network building
net = tflearn.input_data([None, 100])
net = tflearn.embedding(net, input_dim=10000, output_dim=128)
net = tflearn.lstm(net, 128, dropout=0.8)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net, optimizer='adam', learning_rate=0.001,
loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net)
model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
batch_size=32)
@JurPasha
Copy link

JurPasha commented Apr 1, 2018

ugik, can you explain how this NN architecture process data? Is it feed input vector one by one 100 times or just put hole vectore to the embedding layer?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment