Python tensorflow.concat_v2() Examples

def concatenate(tensors, axis=-1):
  """Concatenates a list of tensors alongside the specified axis.

  Returns
  -------
  A tensor.
  """
  if axis < 0:
    dims = get_ndim(tensors[0])
    if dims:
      axis = axis % dims
    else:
      axis = 0

  try:
    return tf.concat_v2([x for x in tensors], axis)
  except AttributeError:
    return tf.concat(axis=axis, values=[x for x in tensors]) 

def block_inception_c(inputs, scope=None, reuse=None):
  """Builds Inception-C block for Inception v4 network."""
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockInceptionC', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 256, [1, 1], scope='Conv2d_0a_1x1')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 384, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = tf.concat_v2([
            slim.conv2d(branch_1, 256, [1, 3], scope='Conv2d_0b_1x3'),
            slim.conv2d(branch_1, 256, [3, 1], scope='Conv2d_0c_3x1')], 3)
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.conv2d(inputs, 384, [1, 1], scope='Conv2d_0a_1x1')
        branch_2 = slim.conv2d(branch_2, 448, [3, 1], scope='Conv2d_0b_3x1')
        branch_2 = slim.conv2d(branch_2, 512, [1, 3], scope='Conv2d_0c_1x3')
        branch_2 = tf.concat_v2([
            slim.conv2d(branch_2, 256, [1, 3], scope='Conv2d_0d_1x3'),
            slim.conv2d(branch_2, 256, [3, 1], scope='Conv2d_0e_3x1')], 3)
      with tf.variable_scope('Branch_3'):
        branch_3 = slim.avg_pool2d(inputs, [3, 3], scope='AvgPool_0a_3x3')
        branch_3 = slim.conv2d(branch_3, 256, [1, 1], scope='Conv2d_0b_1x1')
      return tf.concat_v2([branch_0, branch_1, branch_2, branch_3], 3) 

def block_reduction_b(inputs, scope=None, reuse=None):
  """Builds Reduction-B block for Inception v4 network."""
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockReductionB', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 192, [1, 1], scope='Conv2d_0a_1x1')
        branch_0 = slim.conv2d(branch_0, 192, [3, 3], stride=2,
                               padding='VALID', scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 256, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.conv2d(branch_1, 256, [1, 7], scope='Conv2d_0b_1x7')
        branch_1 = slim.conv2d(branch_1, 320, [7, 1], scope='Conv2d_0c_7x1')
        branch_1 = slim.conv2d(branch_1, 320, [3, 3], stride=2,
                               padding='VALID', scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.max_pool2d(inputs, [3, 3], stride=2, padding='VALID',
                                   scope='MaxPool_1a_3x3')
      return tf.concat_v2([branch_0, branch_1, branch_2], 3) 

def block_reduction_a(inputs, scope=None, reuse=None):
  """Builds Reduction-A block for Inception v4 network."""
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockReductionA', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 384, [3, 3], stride=2, padding='VALID',
                               scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 192, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.conv2d(branch_1, 224, [3, 3], scope='Conv2d_0b_3x3')
        branch_1 = slim.conv2d(branch_1, 256, [3, 3], stride=2,
                               padding='VALID', scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.max_pool2d(inputs, [3, 3], stride=2, padding='VALID',
                                   scope='MaxPool_1a_3x3')
      return tf.concat_v2([branch_0, branch_1, branch_2], 3) 

def block_inception_a(inputs, scope=None, reuse=None):
  """Builds Inception-A block for Inception v4 network."""
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockInceptionA', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 96, [1, 1], scope='Conv2d_0a_1x1')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 64, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.conv2d(branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.conv2d(inputs, 64, [1, 1], scope='Conv2d_0a_1x1')
        branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
        branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
      with tf.variable_scope('Branch_3'):
        branch_3 = slim.avg_pool2d(inputs, [3, 3], scope='AvgPool_0a_3x3')
        branch_3 = slim.conv2d(branch_3, 96, [1, 1], scope='Conv2d_0b_1x1')
      return tf.concat_v2([branch_0, branch_1, branch_2, branch_3], 3) 

def block8(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
  """Builds the 8x8 resnet block."""
  with tf.variable_scope(scope, 'Block8', [net], reuse=reuse):
    with tf.variable_scope('Branch_0'):
      tower_conv = slim.conv2d(net, 192, 1, scope='Conv2d_1x1')
    with tf.variable_scope('Branch_1'):
      tower_conv1_0 = slim.conv2d(net, 192, 1, scope='Conv2d_0a_1x1')
      tower_conv1_1 = slim.conv2d(tower_conv1_0, 224, [1, 3],
                                  scope='Conv2d_0b_1x3')
      tower_conv1_2 = slim.conv2d(tower_conv1_1, 256, [3, 1],
                                  scope='Conv2d_0c_3x1')
    mixed = tf.concat_v2([tower_conv, tower_conv1_2], 3)
    up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
                     activation_fn=None, scope='Conv2d_1x1')
    net += scale * up
    if activation_fn:
      net = activation_fn(net)
  return net 

def block17(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
  """Builds the 17x17 resnet block."""
  with tf.variable_scope(scope, 'Block17', [net], reuse=reuse):
    with tf.variable_scope('Branch_0'):
      tower_conv = slim.conv2d(net, 192, 1, scope='Conv2d_1x1')
    with tf.variable_scope('Branch_1'):
      tower_conv1_0 = slim.conv2d(net, 128, 1, scope='Conv2d_0a_1x1')
      tower_conv1_1 = slim.conv2d(tower_conv1_0, 160, [1, 7],
                                  scope='Conv2d_0b_1x7')
      tower_conv1_2 = slim.conv2d(tower_conv1_1, 192, [7, 1],
                                  scope='Conv2d_0c_7x1')
    mixed = tf.concat_v2([tower_conv, tower_conv1_2], 3)
    up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
                     activation_fn=None, scope='Conv2d_1x1')
    net += scale * up
    if activation_fn:
      net = activation_fn(net)
  return net 

def block35(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
  """Builds the 35x35 resnet block."""
  with tf.variable_scope(scope, 'Block35', [net], reuse=reuse):
    with tf.variable_scope('Branch_0'):
      tower_conv = slim.conv2d(net, 32, 1, scope='Conv2d_1x1')
    with tf.variable_scope('Branch_1'):
      tower_conv1_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
      tower_conv1_1 = slim.conv2d(tower_conv1_0, 32, 3, scope='Conv2d_0b_3x3')
    with tf.variable_scope('Branch_2'):
      tower_conv2_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
      tower_conv2_1 = slim.conv2d(tower_conv2_0, 48, 3, scope='Conv2d_0b_3x3')
      tower_conv2_2 = slim.conv2d(tower_conv2_1, 64, 3, scope='Conv2d_0c_3x3')
    mixed = tf.concat_v2([tower_conv, tower_conv1_1, tower_conv2_2], 3)
    up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
                     activation_fn=None, scope='Conv2d_1x1')
    net += scale * up
    if activation_fn:
      net = activation_fn(net)
  return net 

def omniglot():

    sess = tf.InteractiveSession()

    """    def wrapper(v):
        return tf.Print(v, [v], message="Printing v")

    v = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='Matrix')

    sess.run(tf.global_variables_initializer())
    sess.run(tf.local_variables_initializer())

    temp = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='temp')
    temp = wrapper(v)
    #with tf.control_dependencies([temp]):
    temp.eval()
    print 'Hello'"""

    def update_tensor(V, dim2, val):  # Update tensor V, with index(:,dim2[:]) by val[:]
        val = tf.cast(val, V.dtype)
        def body(_, (v, d2, chg)):
            d2_int = tf.cast(d2, tf.int32)
            return tf.slice(tf.concat_v2([v[:d2_int],[chg] ,v[d2_int+1:]], axis=0), [0], [v.get_shape().as_list()[0]])
        Z = tf.scan(body, elems=(V, dim2, val), initializer=tf.constant(1, shape=V.get_shape().as_list()[1:], dtype=tf.float32), name="Scan_Update")
        return Z 

def omniglot():

    sess = tf.InteractiveSession()

    """    def wrapper(v):
        return tf.Print(v, [v], message="Printing v")

    v = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='Matrix')

    sess.run(tf.global_variables_initializer())
    sess.run(tf.local_variables_initializer())

    temp = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='temp')
    temp = wrapper(v)
    #with tf.control_dependencies([temp]):
    temp.eval()
    print 'Hello'"""

    def update_tensor(V, dim2, val):  # Update tensor V, with index(:,dim2[:]) by val[:]
        val = tf.cast(val, V.dtype)
        def body(_, (v, d2, chg)):
            d2_int = tf.cast(d2, tf.int32)
            return tf.slice(tf.concat_v2([v[:d2_int],[chg] ,v[d2_int+1:]], axis=0), [0], [v.get_shape().as_list()[0]])
        Z = tf.scan(body, elems=(V, dim2, val), initializer=tf.constant(1, shape=V.get_shape().as_list()[1:], dtype=tf.float32), name="Scan_Update")
        return Z 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
        return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
        return tf.concat_v2(tensors, axis, *args, **kwargs) 

def average_grads(tower_grads):
  average_grads = []
  for ii, grad_and_vars in enumerate(zip(*tower_grads)):
    grads = []
    #print ii, len(grad_and_vars)
    for g, v in grad_and_vars:
      #print g, v.name
      if g is None:
        print 'skipping', v.name
        continue
      else:
        print 'averaging', v.name
      expanded_g = tf.expand_dims(g, 0)
      grads.append(expanded_g)
    if len(grads) == 0:
      #print 'no grads for', v.name
      grad = None
    else:
      #grad = tf.concat_v2(grads, 0)
      grad = tf.concat(grads, 0)
      #grad = mean_vals(grad, 0)
      grad = tf.concat(grads, 0)
      grad = tf.reduce_mean(grad, 0)
    v = grad_and_vars[0][1]
    grad_and_var = (grad, v)
    average_grads.append(grad_and_var)
  return average_grads

# def mean_vals(x, a = None):
#   if a is None:
#     return tf.div(tf.reduce_sum(x), tf.cast(tf.size(x), tf.float32))
#   else:
#     return tf.div(tf.reduce_sum(x, a), tf.cast(tf.shape(x)[a], tf.float32)) 

def prepare_input(inputs):
  #assert len(inputs) == 1, "Multiple inputs not yet implemented"
  if len(inputs) == 1:
    inp = inputs[0]
    dim = int(inp.get_shape()[-1])
  else:
    dims = [int(inp.get_shape()[3]) for inp in inputs]
    dim = sum(dims)
    inp = tf.concat_v2(inputs, 3)
  return inp, dim 

def concat(tensors, axis, *args, **kwargs):
        return tf.concat_v2(tensors, axis, *args, **kwargs) 

def conv_cond_concat(x, y):
    """Concatenate conditioning vector on feature map axis."""
    x_shapes = x.get_shape()
    y_shapes = y.get_shape()
    return tf.concat_v2([
        x, y*tf.ones([x_shapes[0], x_shapes[1], x_shapes[2], y_shapes[3]])], 3) 

def unpool(x, size):
  out = tf.concat_v2([x, tf.zeros_like(x)], 3)
  out = tf.concat_v2([out, tf.zeros_like(out)], 2)

  sh = x.get_shape().as_list()
  if None not in sh[1:]:
    out_size = [-1, sh[1] * size, sh[2] * size, sh[3]]
    return tf.reshape(out, out_size)

  shv = tf.shape(x)
  ret = tf.reshape(out, tf.stack([-1, shv[1] * size, shv[2] * size, sh[3]]))
  ret.set_shape([None, None, None, sh[3]])
  return ret 

def concat(tensors, axis, *args, **kwargs):
        return tf.concat_v2(tensors, axis, *args, **kwargs) 

def conv_cond_concat(x, y):
  """Concatenate conditioning vector on feature map axis."""
  x_shapes = x.get_shape()
  y_shapes = y.get_shape()
  return tf.concat_v2([
      x, y*tf.ones([x_shapes[0], x_shapes[1], x_shapes[2], y_shapes[3]])], 3) 

def average_gradients(tower_grads):
  """Calculate the average gradient for each shared variable across all towers.
  Note that this function provides a synchronization point across all towers.
  Args:
    tower_grads: List of lists of (gradient, variable) tuples. The outer list
      is over individual gradients. The inner list is over the gradient
      calculation for each tower.
  Returns:
     List of pairs of (gradient, variable) where the gradient has been averaged
     across all towers.
  """
  average_grads = []
  for grad_and_vars in zip(*tower_grads):
    # Note that each grad_and_vars looks like the following:
    #   ((grad0_gpu0, var0_gpu0), ... , (grad0_gpuN, var0_gpuN))
    grads = []
    for g, _ in grad_and_vars:
      # Add 0 dimension to the gradients to represent the tower.
      expanded_g = tf.expand_dims(g, 0)

      # Append on a 'tower' dimension which we will average over below.
      grads.append(expanded_g)

    # Average over the 'tower' dimension.
    grad = tf.concat_v2(grads, 0)
    grad = tf.reduce_mean(grad, 0)

    # Keep in mind that the Variables are redundant because they are shared
    # across towers. So .. we will just return the first tower's pointer to
    # the Variable.
    v = grad_and_vars[0][1]
    grad_and_var = (grad, v)
    average_grads.append(grad_and_var)
  return average_grads 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs) 

def concat(tensors, axis, *args, **kwargs):
    return tf.concat_v2(tensors, axis, *args, **kwargs)