dec-tensorflow
dec-tensorflow copied to clipboard
Tensorflow implementation of "Unsupervised Deep Embedding for Clustering Analysis"
The author defined the target distribution because it can 1) improve cluster purity, 2) put more emphasis on data points assigned with high confidence, and 3) normalize the loss contribution...
What does z stand for in inference?I want to know how does acc compute?thanks.
q = sess.run(model.q, feed_dict={model.ae.input_: data.train_x, model.ae.input_batch_size: data.train_x.shape[0], model.ae.keep_prob: 1.0}), In my opinion, model.ae.input_ should the embedding vector, But here, it is train_x(original dataset). Thanks for your advice.