def model_pass(input):
    input_layer = tf.to_float(input)
    input_layer_norm = (2 / 255) * input_layer - 1

      # Convolutional Layer #1
    conv1 = tf.layers.conv2d(
      inputs=input_layer_norm,
      filters=32,
      kernel_size=[3, 3],
      strides = [2,2],
      padding="same",
      activation=tf.nn.relu,
      kernel_initializer=tf.contrib.layers.xavier_initializer())

    conv2 = tf.layers.conv2d(
      inputs=conv1,
      filters=64,
      kernel_size=[3, 3],
      strides = [2,2],
      padding="same",
      activation=tf.nn.relu,
      kernel_initializer=tf.contrib.layers.xavier_initializer())

    conv3 = tf.layers.conv2d(
        inputs=conv2,
        filters=128,
        kernel_size=[3, 3],
        strides = [2,2],
        padding="same",
        activation=tf.nn.relu,
        kernel_initializer=tf.contrib.layers.xavier_initializer())

    conv4 = tf.layers.conv2d(
        inputs=conv3,
        filters=256,
        kernel_size=[3, 3],
        strides = [2,2],
        padding="same",
        activation=tf.nn.relu,
        kernel_initializer=tf.contrib.layers.xavier_initializer())

    conv5 = tf.layers.conv2d(
        inputs=conv4,
        filters=512,
        kernel_size=[3, 3],
        strides = [2,2],
        padding="same",
        activation=tf.nn.relu,
        kernel_initializer=tf.contrib.layers.xavier_initializer())


    conv6 = tf.layers.conv2d(
        inputs=conv5,
        filters=1024,
        kernel_size=[3, 3],
        strides = [2,2],
        padding="same",
        activation=tf.nn.relu,
        kernel_initializer=tf.contrib.layers.xavier_initializer())

    pool = tf.layers.max_pooling2d(inputs=conv6, pool_size=[5,5], strides=[1,1])
    pool_flat = tf.reshape(pool, [-1, 1024])
    dense = tf.layers.dense(inputs=pool_flat, units=1024, activation=tf.nn.relu)

    logits = tf.layers.dense(inputs=dense, units=2)

    return logits