Example of 3D convolutional network with TensorFlow

conv3dnet.py

import tensorflow as tf
import numpy as np

FC_SIZE = 1024
DTYPE = tf.float32


def _weight_variable(name, shape):
    return tf.get_variable(name, shape, DTYPE, tf.truncated_normal_initializer(stddev=0.1))


def _bias_variable(name, shape):
    return tf.get_variable(name, shape, DTYPE, tf.constant_initializer(0.1, dtype=DTYPE))


def inference(boxes, dataconfig):
    prev_layer = boxes

    in_filters = dataconfig.num_props
    with tf.variable_scope('conv1') as scope:
        out_filters = 16
        kernel = _weight_variable('weights', [5, 5, 5, in_filters, out_filters])
        conv = tf.nn.conv3d(prev_layer, kernel, [1, 1, 1, 1, 1], padding='SAME')
        biases = _bias_variable('biases', [out_filters])
        bias = tf.nn.bias_add(conv, biases)
        conv1 = tf.nn.relu(bias, name=scope.name)

        prev_layer = conv1
        in_filters = out_filters

    pool1 = tf.nn.max_pool3d(prev_layer, ksize=[1, 3, 3, 3, 1], strides=[1, 2, 2, 2, 1], padding='SAME')
    norm1 = pool1  # tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta = 0.75, name='norm1')

    prev_layer = norm1

    with tf.variable_scope('conv2') as scope:
        out_filters = 32
        kernel = _weight_variable('weights', [5, 5, 5, in_filters, out_filters])
        conv = tf.nn.conv3d(prev_layer, kernel, [1, 1, 1, 1, 1], padding='SAME')
        biases = _bias_variable('biases', [out_filters])
        bias = tf.nn.bias_add(conv, biases)
        conv2 = tf.nn.relu(bias, name=scope.name)

        prev_layer = conv2
        in_filters = out_filters

    # normalize prev_layer here
    prev_layer = tf.nn.max_pool3d(prev_layer, ksize=[1, 3, 3, 3, 1], strides=[1, 2, 2, 2, 1], padding='SAME')

    with tf.variable_scope('conv3_1') as scope:
        out_filters = 64
        kernel = _weight_variable('weights', [5, 5, 5, in_filters, out_filters])
        conv = tf.nn.conv3d(prev_layer, kernel, [1, 1, 1, 1, 1], padding='SAME')
        biases = _bias_variable('biases', [out_filters])
        bias = tf.nn.bias_add(conv, biases)
        prev_layer = tf.nn.relu(bias, name=scope.name)
        in_filters = out_filters

    with tf.variable_scope('conv3_2') as scope:
        out_filters = 64
        kernel = _weight_variable('weights', [5, 5, 5, in_filters, out_filters])
        conv = tf.nn.conv3d(prev_layer, kernel, [1, 1, 1, 1, 1], padding='SAME')
        biases = _bias_variable('biases', [out_filters])
        bias = tf.nn.bias_add(conv, biases)
        prev_layer = tf.nn.relu(bias, name=scope.name)
        in_filters = out_filters

    with tf.variable_scope('conv3_3') as scope:
        out_filters = 32
        kernel = _weight_variable('weights', [5, 5, 5, in_filters, out_filters])
        conv = tf.nn.conv3d(prev_layer, kernel, [1, 1, 1, 1, 1], padding='SAME')
        biases = _bias_variable('biases', [out_filters])
        bias = tf.nn.bias_add(conv, biases)
        prev_layer = tf.nn.relu(bias, name=scope.name)
        in_filters = out_filters

    # normalize prev_layer here
    prev_layer = tf.nn.max_pool3d(prev_layer, ksize=[1, 3, 3, 3, 1], strides=[1, 2, 2, 2, 1], padding='SAME')


    with tf.variable_scope('local3') as scope:
        dim = np.prod(prev_layer.get_shape().as_list()[1:])
        prev_layer_flat = tf.reshape(prev_layer, [-1, dim])
        weights = _weight_variable('weights', [dim, FC_SIZE])
        biases = _bias_variable('biases', [FC_SIZE])
        local3 = tf.nn.relu(tf.matmul(prev_layer_flat, weights) + biases, name=scope.name)

    prev_layer = local3

    with tf.variable_scope('local4') as scope:
        dim = np.prod(prev_layer.get_shape().as_list()[1:])
        prev_layer_flat = tf.reshape(prev_layer, [-1, dim])
        weights = _weight_variable('weights', [dim, FC_SIZE])
        biases = _bias_variable('biases', [FC_SIZE])
        local4 = tf.nn.relu(tf.matmul(prev_layer_flat, weights) + biases, name=scope.name)

    prev_layer = local4

    with tf.variable_scope('softmax_linear') as scope:
        dim = np.prod(prev_layer.get_shape().as_list()[1:])
        weights = _weight_variable('weights', [dim, dataconfig.num_classes])
        biases = _bias_variable('biases', [dataconfig.num_classes])
        softmax_linear = tf.add(tf.matmul(prev_layer, weights), biases, name=scope.name)

    return softmax_linear


def loss(logits, labels):
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
        logits, labels, name='cross_entropy_per_example')

    return tf.reduce_mean(cross_entropy, name='xentropy_mean')

Hi,
this is very nice code for understanding 3D convolution. did we apply this type of code for RGB image. can you share sample of input data .

thanks

It's good, thank you very much.

It's good, thank you very much.

This code is for Tensorflow 1, and it is now obsolete. It would look very different and much simpler in Tensorflow 2.