Need help to port snippet from tflearn to keras
I have this snippet from this guide, but i want to use tf.contrib.Keras instead of tflearn, can anybody help port this code. tf.reset_default_graph() net = tflearn.input_data(shape=[None, len(train_x)]) net = tflearn.fully_connected(net, 8) net = tflearn.fully_connected(net, 8) net = tflearn.fully_connected(net, len(train_y), activation='softmax') net = tflearn.regression(net) # Define model and setup tensorboard model = tflearn.DNN(net, tensorboard_dir='tflearn_logs') # Start training (apply gradient descent algorithm) model.fit(train_x, train_y, n_epoch=1000, batch_size=8, show_metric=True) model.save('model.tflearn') # loading model model.load('./model.tflearn') 1). https://chatbotsmagazine.com/contextual-chat-bots-with-tensorflow-4391749d0077
Tensorflow - LSTM state reuse within batch
Cost at all epochs are zero, even before training
TensorFlow + cloud-ml : deploy custom native op / reader
Separate gradients in tf.gradients
Tensorflow OOM on GPU
Keras ML library: how to do weight clipping after gradient updates? TensorFlow backend
keras tensorflow load_weights fails
Loss suddenly increases with Adam Optimizer in Tensorflow
Suspicious warnings on Tensorflow 1.0 [duplicate]
Is it Ok that creating TensorFlow device multiple times
What is the difference between xavier_initializer and xavier_initializer_conv2d?
How to plot grid of images in tensorboard?
TensorFlow's Estimator can only get N-1 batches from tf.train.limit_epochs
Visualize influence of an input in TensorFlow
How to correctly pass initial value of transition_params in tensorflow linear chain CRF
Why slim.nets.vgg use conv2d instead of fully_connected layers?