How can I implement deconvolution on CNN (TensorFlow)?

Question

I'm new in tensorflow and machine learning. Could you explain me how implement deconvulation on this CNN model(http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/) for text classification?

CNN model:

class TextCNN(object):
"""
A CNN for text classification.
Uses an embedding layer, followed by a convolutional, max-pooling and softmax layer.
"""
def __init__(
  self, sequence_length, num_classes, vocab_size,
  embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):

    # Placeholders for input, output and dropout
    self.input_x = tf.placeholder(tf.int32, [None, sequence_length], name="input_x")
    self.input_y = tf.placeholder(tf.float32, [None, num_classes], name="input_y")
    self.dropout_keep_prob = tf.placeholder(tf.float32, name="dropout_keep_prob")

    # Keeping track of l2 regularization loss (optional)
    l2_loss = tf.constant(0.0)

    # Embedding layer
    with tf.device('/cpu:0'), tf.name_scope("embedding"):
        self.W = tf.Variable(
            tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0),
            name="W")
        self.embedded_chars = tf.nn.embedding_lookup(self.W, self.input_x)
        self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)

    # Create a convolution + maxpool layer for each filter size
    pooled_outputs = []
    for i, filter_size in enumerate(filter_sizes):
        with tf.name_scope("conv-maxpool-%s" % filter_size):
            # Convolution Layer
            filter_shape = [filter_size, embedding_size, 1, num_filters]
            W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
            b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
            conv = tf.nn.conv2d(
                self.embedded_chars_expanded,
                W,
                strides=[1, 1, 1, 1],
                padding="VALID",
                name="conv")
            # Apply nonlinearity
            h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
            # Maxpooling over the outputs
            pooled = tf.nn.max_pool(
                h,
                ksize=[1, sequence_length - filter_size + 1, 1, 1],
                strides=[1, 1, 1, 1],
                padding='VALID',
                name="pool")
            pooled_outputs.append(pooled)

    # Combine all the pooled features
    num_filters_total = num_filters * len(filter_sizes)
    self.h_pool = tf.concat(pooled_outputs, 3)
    self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])

    # Add dropout
    with tf.name_scope("dropout"):
        self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)

    # Final (unnormalized) scores and predictions
    with tf.name_scope("output"):
        W = tf.get_variable(
            "W",
            shape=[num_filters_total, num_classes],
            initializer=tf.contrib.layers.xavier_initializer())
        b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")
        l2_loss += tf.nn.l2_loss(W)
        l2_loss += tf.nn.l2_loss(b)
        self.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
        self.predictions = tf.argmax(self.scores, 1, name="predictions")

    # CalculateMean cross-entropy loss
    with tf.name_scope("loss"):
        losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y)
        self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss

    # Accuracy
    with tf.name_scope("accuracy"):
        correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1))
        self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, "float"), name="accuracy")

I know about tf.nn.conv2d_transpose, but I don't understand how can I get original data (not embedded_chars)

Answer 1

Deconvolution have very simple structure: unpooling → deconv like this:

# Unpooling
Ps = (tf.gradients(pooled, h))[0]
unpooled = tf.multiply(Ps, P)

# Deconv
batch_size = tf.shape(self.input_x)[0]
ds = [batch_size]
ds.append(self.embedded_chars_expanded.get_shape()[1])
ds.append(self.embedded_chars_expanded.get_shape()[2])
ds.append(self.embedded_chars_expanded.get_shape()[3])
deconv_shape = tf.stack(ds)
deconv = tf.nn.conv2d_transpose(
    unpooled,
    W,
    deconv_shape,
    strides=[1, 1, 1, 1],
    padding='VALID',
    name="Deconv"
    )