tflearn Embedding Example

# -*- coding: utf-8 -*-

""" Convolutional Neural Network for MNIST dataset classification task.

References:
    Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based
    learning applied to document recognition." Proceedings of the IEEE,
    86(11):2278-2324, November 1998.

Links:
    [MNIST Dataset] http://yann.lecun.com/exdb/mnist/

"""

from __future__ import division, print_function, absolute_import

import tflearn
from sklearn import svm
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization, l2_normalize
from tflearn.layers.estimator import regression
import tflearn.datasets.mnist as mnist
import tensorflow as tf

model_name = "test.h5"

X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])  # [:1000, ]
testX = testX.reshape([-1, 28, 28, 1])  # [:1000, ]
Y = Y  # [:1000, ]
testY = testY  # [:1000, ]

with tf.Graph().as_default():
    # Building convolutional network
    network = input_data(shape=[None, 28, 28, 1], name='input')
    network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
    network = max_pool_2d(network, 2)
    network = local_response_normalization(network)
    network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
    network = max_pool_2d(network, 2)
    network = local_response_normalization(network)
    network = fully_connected(network, 128, activation='tanh')
    network = dropout(network, 0.8)
    network = fully_connected(network, 256, activation='tanh')
    network = dropout(network, 0.8)

    embedding = l2_normalize(network, dim=1, name="embedding")
    network = fully_connected(network, 10, activation="softmax")
    network = regression(network, optimizer='adam', learning_rate=0.01, loss='categorical_crossentropy',
                         metric="accuracy", name='target')

    # Training
    model = tflearn.DNN(network, tensorboard_verbose=0)

    model.fit({'input': X}, {'target': Y}, n_epoch=1, validation_set=({'input': testX}, {'target': testY}),
              batch_size=256, run_id='convnet_mnist')

    m2 = tflearn.DNN(embedding, session=model.session)
    train_embeddings = m2.predict(X)
    print(train_embeddings.shape)

    clf = svm.SVC()
    clf.fit(train_embeddings, Y.argmax(axis=1))

    test_embeddings = m2.predict(testX)
    print(clf.score(test_embeddings, testY.argmax(axis=1)))