Python python.shape方法代碼示例

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def basic_rnn_seq2seq(
        encoder_inputs, decoder_inputs, cell, dtype=dtypes.float32, scope=None):
    """Basic RNN sequence-to-sequence model.

    This model first runs an RNN to encode encoder_inputs into a state vector,
    then runs decoder, initialized with the last encoder state, on decoder_inputs.
    Encoder and decoder use the same RNN cell type, but don't share parameters.

    Args:
      encoder_inputs: A list of 2D Tensors [batch_size x input_size].
      decoder_inputs: A list of 2D Tensors [batch_size x input_size].
      cell: rnn_cell.RNNCell defining the cell function and size.
      dtype: The dtype of the initial state of the RNN cell (default: tf.float32).
      scope: VariableScope for the created subgraph; default: "basic_rnn_seq2seq".

    Returns:
      A tuple of the form (outputs, state), where:
        outputs: A list of the same length as decoder_inputs of 2D Tensors with
          shape [batch_size x output_size] containing the generated outputs.
        state: The state of each decoder cell in the final time-step.
          It is a 2D Tensor of shape [batch_size x cell.state_size].
    """
    with variable_scope.variable_scope(scope or "basic_rnn_seq2seq"):
        _, enc_state = rnn.rnn(cell, encoder_inputs, dtype=dtype)
        return rnn_decoder(decoder_inputs, enc_state, cell) 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def basic_rnn_seq2seq(
    encoder_inputs, decoder_inputs, cell, dtype=dtypes.float32, scope=None):
  """Basic RNN sequence-to-sequence model.

  This model first runs an RNN to encode encoder_inputs into a state vector,
  then runs decoder, initialized with the last encoder state, on decoder_inputs.
  Encoder and decoder use the same RNN cell type, but don't share parameters.

  Args:
    encoder_inputs: A list of 2D Tensors [batch_size x input_size].
    decoder_inputs: A list of 2D Tensors [batch_size x input_size].
    cell: rnn_cell.RNNCell defining the cell function and size.
    dtype: The dtype of the initial state of the RNN cell (default: tf.float32).
    scope: VariableScope for the created subgraph; default: "basic_rnn_seq2seq".

  Returns:
    A tuple of the form (outputs, state), where:
      outputs: A list of the same length as decoder_inputs of 2D Tensors with
        shape [batch_size x output_size] containing the generated outputs.
      state: The state of each decoder cell in the final time-step.
        It is a 2D Tensor of shape [batch_size x cell.state_size].
  """
  with variable_scope.variable_scope(scope or "basic_rnn_seq2seq"):
    _, enc_state = rnn.rnn(cell, encoder_inputs, dtype=dtype)
    return rnn_decoder(decoder_inputs, enc_state, cell) 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def sequence_loss_by_mle(logits, targets, vocab_size, sequence_length, batch_size, output_projection=None):
    #print("logits: ", np.shape(logits[0]))
    #logits: [seq_len, batch_size, emb_dim]
    #targets: [seq_len, batch_size]  =====transpose====> [batch_size, seq_len]
    # labels = tf.to_int32(tf.transpose(targets))
    #targets: [seq_len, batch_size] ====reshape[-1]====> [seq_len * batch_size]
    labels = tf.to_int32(tf.reshape(targets, [-1]))

    if output_projection is not None:
      #logits = nn_ops.xw_plus_b(logits, output_projection[0], output_projection[1])
      logits = [tf.matmul(logit, output_projection[0]) + output_projection[1] for logit in logits]

    reshape_logits = tf.reshape(logits, [-1, vocab_size]) #[seq_len * batch_size, vocab_size]

    prediction = tf.clip_by_value(reshape_logits, 1e-20, 1.0)

    pretrain_loss = -tf.reduce_sum(
        # [seq_len * batch_size , vocab_size]
        tf.one_hot(labels, vocab_size, 1.0, 0.0) * tf.log(prediction)
    ) / (sequence_length * batch_size)
    return pretrain_loss 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def tied_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
                     loop_function=None, dtype=dtypes.float32, scope=None):
    """RNN sequence-to-sequence model with tied encoder and decoder parameters.

    This model first runs an RNN to encode encoder_inputs into a state vector, and
    then runs decoder, initialized with the last encoder state, on decoder_inputs.
    Encoder and decoder use the same RNN cell and share parameters.

    Args:
      encoder_inputs: A list of 2D Tensors [batch_size x input_size].
      decoder_inputs: A list of 2D Tensors [batch_size x input_size].
      cell: rnn_cell.RNNCell defining the cell function and size.
      loop_function: If not None, this function will be applied to i-th output
        in order to generate i+1-th input, and decoder_inputs will be ignored,
        except for the first element ("GO" symbol), see rnn_decoder for details.
      dtype: The dtype of the initial state of the rnn cell (default: tf.float32).
      scope: VariableScope for the created subgraph; default: "tied_rnn_seq2seq".

    Returns:
      A tuple of the form (outputs, state), where:
        outputs: A list of the same length as decoder_inputs of 2D Tensors with
          shape [batch_size x output_size] containing the generated outputs.
        state: The state of each decoder cell in each time-step. This is a list
          with length len(decoder_inputs) -- one item for each time-step.
          It is a 2D Tensor of shape [batch_size x cell.state_size].
    """
    with variable_scope.variable_scope("combined_tied_rnn_seq2seq"):
        scope = scope or "tied_rnn_seq2seq"
        _, enc_state = rnn.rnn(
            cell, encoder_inputs, dtype=dtype, scope=scope)
        variable_scope.get_variable_scope().reuse_variables()
        return rnn_decoder(decoder_inputs, enc_state, cell,
                           loop_function=loop_function, scope=scope) 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def sequence_loss(logits, targets, weights,
                  average_across_timesteps=True, average_across_batch=True,
                  softmax_loss_function=None, name=None):
    """Weighted cross-entropy loss for a sequence of logits, batch-collapsed.

    Args:
      logits: List of 2D Tensors of shape [batch_size x num_decoder_symbols].
      targets: List of 1D batch-sized int32 Tensors of the same length as logits.
      weights: List of 1D batch-sized float-Tensors of the same length as logits.
      average_across_timesteps: If set, divide the returned cost by the total
        label weight.
      average_across_batch: If set, divide the returned cost by the batch size.
      softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
        to be used instead of the standard softmax (the default if this is None).
      name: Optional name for this operation, defaults to "sequence_loss".

    Returns:
      A scalar float Tensor: The average log-perplexity per symbol (weighted).

    Raises:
      ValueError: If len(logits) is different from len(targets) or len(weights).
    """
    with ops.name_scope(name, "sequence_loss", logits + targets + weights):
        cost = math_ops.reduce_sum(sequence_loss_by_example(
            logits, targets, weights,
            average_across_timesteps=average_across_timesteps,
            softmax_loss_function=softmax_loss_function))
        if average_across_batch:
            batch_size = array_ops.shape(targets[0])[0]
            return cost / math_ops.cast(batch_size, cost.dtype)
        else:
            return cost 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def tied_rnn_seq2seq(encoder_inputs, decoder_inputs, cell,
                     loop_function=None, dtype=dtypes.float32, scope=None):
  """RNN sequence-to-sequence model with tied encoder and decoder parameters.

  This model first runs an RNN to encode encoder_inputs into a state vector, and
  then runs decoder, initialized with the last encoder state, on decoder_inputs.
  Encoder and decoder use the same RNN cell and share parameters.

  Args:
    encoder_inputs: A list of 2D Tensors [batch_size x input_size].
    decoder_inputs: A list of 2D Tensors [batch_size x input_size].
    cell: rnn_cell.RNNCell defining the cell function and size.
    loop_function: If not None, this function will be applied to i-th output
      in order to generate i+1-th input, and decoder_inputs will be ignored,
      except for the first element ("GO" symbol), see rnn_decoder for details.
    dtype: The dtype of the initial state of the rnn cell (default: tf.float32).
    scope: VariableScope for the created subgraph; default: "tied_rnn_seq2seq".

  Returns:
    A tuple of the form (outputs, state), where:
      outputs: A list of the same length as decoder_inputs of 2D Tensors with
        shape [batch_size x output_size] containing the generated outputs.
      state: The state of each decoder cell in each time-step. This is a list
        with length len(decoder_inputs) -- one item for each time-step.
        It is a 2D Tensor of shape [batch_size x cell.state_size].
  """
  with variable_scope.variable_scope("combined_tied_rnn_seq2seq"):
    scope = scope or "tied_rnn_seq2seq"
    _, enc_state = rnn.rnn(
        cell, encoder_inputs, dtype=dtype, scope=scope)
    variable_scope.get_variable_scope().reuse_variables()
    return rnn_decoder(decoder_inputs, enc_state, cell,
                       loop_function=loop_function, scope=scope) 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def sequence_loss(logits, targets, weights,
                  average_across_timesteps=True, average_across_batch=True,
                  softmax_loss_function=None, name=None):
  """Weighted cross-entropy loss for a sequence of logits, batch-collapsed.

  Args:
    logits: List of 2D Tensors of shape [batch_size x num_decoder_symbols].
    targets: List of 1D batch-sized int32 Tensors of the same length as logits.
    weights: List of 1D batch-sized float-Tensors of the same length as logits.
    average_across_timesteps: If set, divide the returned cost by the total
      label weight.
    average_across_batch: If set, divide the returned cost by the batch size.
    softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
      to be used instead of the standard softmax (the default if this is None).
    name: Optional name for this operation, defaults to "sequence_loss".

  Returns:
    A scalar float Tensor: The average log-perplexity per symbol (weighted).

  Raises:
    ValueError: If len(logits) is different from len(targets) or len(weights).
  """
  with ops.name_scope(name, "sequence_loss", logits + targets + weights):
    cost = math_ops.reduce_sum(sequence_loss_by_example(
        logits, targets, weights,
        average_across_timesteps=average_across_timesteps,
        softmax_loss_function=softmax_loss_function))
    if average_across_batch:
      batch_size = array_ops.shape(targets[0])[0]
      return cost / math_ops.cast(batch_size, cost.dtype)
    else:
      return cost 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def sequence_loss(logits, targets, weights,
                  average_across_timesteps=True, average_across_batch=True,
                  softmax_loss_function=None, name=None):
  """Weighted cross-entropy loss for a sequence of logits, batch-collapsed.

  Args:
    logits: List of 2D Tensors of shape [batch_size x num_decoder_symbols].
    targets: List of 1D batch-sized int32 Tensors of the same length as logits.
    weights: List of 1D batch-sized float-Tensors of the same length as logits.
    average_across_timesteps: If set, divide the returned cost by the total
      label weight.
    average_across_batch: If set, divide the returned cost by the batch size.
    softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
      to be used instead of the standard softmax (the default if this is None).
    name: Optional name for this operation, defaults to "sequence_loss".

  Returns:
    A scalar float Tensor: The average log-perplexity per symbol (weighted).

  Raises:
    ValueError: If len(logits) is different from len(targets) or len(weights).
  """
  with ops.op_scope(logits + targets + weights, name, "sequence_loss"):
    cost = math_ops.reduce_sum(sequence_loss_by_example(
        logits, targets, weights,
        average_across_timesteps=average_across_timesteps,
        softmax_loss_function=softmax_loss_function))
    if average_across_batch:
      batch_size = array_ops.shape(targets[0])[0]
      return cost / math_ops.cast(batch_size, cost.dtype)
    else:
      return cost 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def rnn_decoder(decoder_inputs, initial_state, cell, loop_function=None,
                scope=None):
    """RNN decoder for the sequence-to-sequence model.

    Args:
      decoder_inputs: A list of 2D Tensors [batch_size x input_size].
      initial_state: 2D Tensor with shape [batch_size x cell.state_size].
      cell: rnn_cell.RNNCell defining the cell function and size.
      loop_function: If not None, this function will be applied to the i-th output
        in order to generate the i+1-st input, and decoder_inputs will be ignored,
        except for the first element ("GO" symbol). This can be used for decoding,
        but also for training to emulate http://arxiv.org/abs/1506.03099.
        Signature -- loop_function(prev, i) = next
          * prev is a 2D Tensor of shape [batch_size x output_size],
          * i is an integer, the step number (when advanced control is needed),
          * next is a 2D Tensor of shape [batch_size x input_size].
      scope: VariableScope for the created subgraph; defaults to "rnn_decoder".

    Returns:
      A tuple of the form (outputs, state), where:
        outputs: A list of the same length as decoder_inputs of 2D Tensors with
          shape [batch_size x output_size] containing generated outputs.
        state: The state of each cell at the final time-step.
          It is a 2D Tensor of shape [batch_size x cell.state_size].
          (Note that in some cases, like basic RNN cell or GRU cell, outputs and
           states can be the same. They are different for LSTM cells though.)
    """
    with variable_scope.variable_scope(scope or "rnn_decoder"):
        state = initial_state
        outputs = []
        prev = None
        for i, inp in enumerate(decoder_inputs):
            if loop_function is not None and prev is not None:
                with variable_scope.variable_scope("loop_function", reuse=True):
                    inp = loop_function(prev, i)
            if i > 0:
                variable_scope.get_variable_scope().reuse_variables()
            output, state = cell(inp, state)
            outputs.append(output)
            if loop_function is not None:
                prev = output
    return outputs, state 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def sequence_loss_by_example(logits, targets, weights,
                             average_across_timesteps=True,
                             softmax_loss_function=None, name=None):
    """Weighted cross-entropy loss for a sequence of logits (per example).

    Args:
      logits: List of 2D Tensors of shape [batch_size x num_decoder_symbols].
      targets: List of 1D batch-sized int32 Tensors of the same length as logits.
      weights: List of 1D batch-sized float-Tensors of the same length as logits.
      average_across_timesteps: If set, divide the returned cost by the total
        label weight.
      softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
        to be used instead of the standard softmax (the default if this is None).
      name: Optional name for this operation, default: "sequence_loss_by_example".

    Returns:
      1D batch-sized float Tensor: The log-perplexity for each sequence.

    Raises:
      ValueError: If len(logits) is different from len(targets) or len(weights).
    """
    if len(targets) != len(logits) or len(weights) != len(logits):
        raise ValueError("Lengths of logits, weights, and targets must be the same "
                         "%d, %d, %d." % (len(logits), len(weights), len(targets)))
    with ops.name_scope(name, "sequence_loss_by_example",
                        logits + targets + weights):
        log_perp_list = []
        for logit, target, weight in zip(logits, targets, weights):
            if softmax_loss_function is None:
                # TODO(irving,ebrevdo): This reshape is needed because
                # sequence_loss_by_example is called with scalars sometimes, which
                # violates our general scalar strictness policy.
                target = array_ops.reshape(target, [-1])
                crossent = nn_ops.sparse_softmax_cross_entropy_with_logits(
                    logit, target)
            else:
                crossent = softmax_loss_function(logit, target)
            log_perp_list.append(crossent * weight)
        log_perps = math_ops.add_n(log_perp_list)
        if average_across_timesteps:
            total_size = math_ops.add_n(weights)
            total_size += 1e-12  # Just to avoid division by 0 for all-0 weights.
            log_perps /= total_size
    return log_perps 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def rnn_decoder(decoder_inputs, initial_state, cell, loop_function=None,
                scope=None):
  """RNN decoder for the sequence-to-sequence model.

  Args:
    decoder_inputs: A list of 2D Tensors [batch_size x input_size].
    initial_state: 2D Tensor with shape [batch_size x cell.state_size].
    cell: rnn_cell.RNNCell defining the cell function and size.
    loop_function: If not None, this function will be applied to the i-th output
      in order to generate the i+1-st input, and decoder_inputs will be ignored,
      except for the first element ("GO" symbol). This can be used for decoding,
      but also for training to emulate http://arxiv.org/abs/1506.03099.
      Signature -- loop_function(prev, i) = next
        * prev is a 2D Tensor of shape [batch_size x output_size],
        * i is an integer, the step number (when advanced control is needed),
        * next is a 2D Tensor of shape [batch_size x input_size].
    scope: VariableScope for the created subgraph; defaults to "rnn_decoder".

  Returns:
    A tuple of the form (outputs, state), where:
      outputs: A list of the same length as decoder_inputs of 2D Tensors with
        shape [batch_size x output_size] containing generated outputs.
      state: The state of each cell at the final time-step.
        It is a 2D Tensor of shape [batch_size x cell.state_size].
        (Note that in some cases, like basic RNN cell or GRU cell, outputs and
         states can be the same. They are different for LSTM cells though.)
  """
  with variable_scope.variable_scope(scope or "rnn_decoder"):
    state = initial_state
    outputs = []
    prev = None
    for i, inp in enumerate(decoder_inputs):
      if loop_function is not None and prev is not None:
        with variable_scope.variable_scope("loop_function", reuse=True):
          inp = loop_function(prev, i)
      if i > 0:
        variable_scope.get_variable_scope().reuse_variables()
      output, state = cell(inp, state)
      outputs.append(output)
      if loop_function is not None:
        prev = output
  return outputs, state 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def sequence_loss_by_example(logits, targets, weights,
                             average_across_timesteps=True,
                             softmax_loss_function=None, name=None):
  """Weighted cross-entropy loss for a sequence of logits (per example).

  Args:
    logits: List of 2D Tensors of shape [batch_size x num_decoder_symbols].
    targets: List of 1D batch-sized int32 Tensors of the same length as logits.
    weights: List of 1D batch-sized float-Tensors of the same length as logits.
    average_across_timesteps: If set, divide the returned cost by the total
      label weight.
    softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
      to be used instead of the standard softmax (the default if this is None).
    name: Optional name for this operation, default: "sequence_loss_by_example".

  Returns:
    1D batch-sized float Tensor: The log-perplexity for each sequence.

  Raises:
    ValueError: If len(logits) is different from len(targets) or len(weights).
  """
  if len(targets) != len(logits) or len(weights) != len(logits):
    raise ValueError("Lengths of logits, weights, and targets must be the same "
                     "%d, %d, %d." % (len(logits), len(weights), len(targets)))
  with ops.op_scope(logits + targets + weights, name, "sequence_loss_by_example"
                    ):
    log_perp_list = []
    for logit, target, weight in zip(logits, targets, weights):
      if softmax_loss_function is None:
        # TODO(irving,ebrevdo): This reshape is needed because
        # sequence_loss_by_example is called with scalars sometimes, which
        # violates our general scalar strictness policy.
        target = array_ops.reshape(target, [-1])
        crossent = nn_ops.sparse_softmax_cross_entropy_with_logits(
            logit, target)
      else:
        crossent = softmax_loss_function(logit, target)
      log_perp_list.append(crossent * weight)
    log_perps = math_ops.add_n(log_perp_list)
    if average_across_timesteps:
      total_size = math_ops.add_n(weights)
      total_size += 1e-12  # Just to avoid division by 0 for all-0 weights.
      log_perps /= total_size
  return log_perps 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def rnn_decoder(decoder_inputs, initial_state, cell, loop_function=None,
                scope=None):
  """RNN decoder for the sequence-to-sequence model.

  Args:
    decoder_inputs: A list of 2D Tensors [batch_size x input_size].
    initial_state: 2D Tensor with shape [batch_size x cell.state_size].
    cell: rnn_cell.RNNCell defining the cell function and size.
    loop_function: If not None, this function will be applied to the i-th output
      in order to generate the i+1-st input, and decoder_inputs will be ignored,
      except for the first element ("GO" symbol). This can be used for decoding,
      but also for training to emulate http://arxiv.org/abs/1506.03099.
      Signature -- loop_function(prev, i) = next
        * prev is a 2D Tensor of shape [batch_size x output_size],
        * i is an integer, the step number (when advanced control is needed),
        * next is a 2D Tensor of shape [batch_size x input_size].
    scope: VariableScope for the created subgraph; defaults to "rnn_decoder".

  Returns:
    A tuple of the form (outputs, state), where:
      outputs: A list of the same length as decoder_inputs of 2D Tensors with
        shape [batch_size x output_size] containing generated outputs.
      state: The state of each cell at the final time-step.
        It is a 2D Tensor of shape [batch_size x cell.state_size].
        (Note that in some cases, like basic RNN cell or GRU cell, outputs and
         states can be the same. They are different for LSTM cells though.)
  """
  with variable_scope.variable_scope(scope or "rnn_decoder"):
    state = initial_state
    outputs = []
    states = []
    prev = None
    for i, inp in enumerate(decoder_inputs):
      if loop_function is not None and prev is not None:
        with variable_scope.variable_scope("loop_function", reuse=True):
          inp = loop_function(prev, i)
      if i > 0:
        variable_scope.get_variable_scope().reuse_variables()
      output, state = cell(inp, state)
      outputs.append(output)
      states.append(state)
      if loop_function is not None:
        prev = output
  return outputs, states 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def sequence_loss_by_example(logits, targets, weights,
                             average_across_timesteps=True,
                             softmax_loss_function=None, name=None):
  """Weighted cross-entropy loss for a sequence of logits (per example).

  Args:
    logits: List of 2D Tensors of shape [batch_size x num_decoder_symbols].
    targets: List of 1D batch-sized int32 Tensors of the same length as logits.
    weights: List of 1D batch-sized float-Tensors of the same length as logits.
    average_across_timesteps: If set, divide the returned cost by the total
      label weight.
    softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
      to be used instead of the standard softmax (the default if this is None).
    name: Optional name for this operation, default: "sequence_loss_by_example".

  Returns:
    1D batch-sized float Tensor: The log-perplexity for each sequence.

  Raises:
    ValueError: If len(logits) is different from len(targets) or len(weights).
  """
  if len(targets) != len(logits) or len(weights) != len(logits):
    raise ValueError("Lengths of logits, weights, and targets must be the same "
                     "%d, %d, %d." % (len(logits), len(weights), len(targets)))
  with ops.name_scope(name, "sequence_loss_by_example",
                      logits + targets + weights):
    log_perp_list = []
    for logit, target, weight in zip(logits, targets, weights):
      if softmax_loss_function is None:
        # TODO(irving,ebrevdo): This reshape is needed because
        # sequence_loss_by_example is called with scalars sometimes, which
        # violates our general scalar strictness policy.
        target = array_ops.reshape(target, [-1])
        crossent = nn_ops.sparse_softmax_cross_entropy_with_logits(
            logit, target)
      else:
        crossent = softmax_loss_function(logit, target)
      log_perp_list.append(crossent * weight)
    log_perps = math_ops.add_n(log_perp_list)
    if average_across_timesteps:
      total_size = math_ops.add_n(weights)
      total_size += 1e-12  # Just to avoid division by 0 for all-0 weights.
      log_perps /= total_size
  return log_perps 

# 需要導入模塊: from tensorflow import python [as 別名]
# 或者: from tensorflow.python import shape [as 別名]
def decode_model_with_buckets(encoder_inputs, decoder_inputs, targets, weights, buckets, seq2seq,
                              softmax_loss_function=None,
                              per_example_loss=False,
                              name=None):
    """Create a sequence-to-sequence models with support for bucketing.

    The seq2seq argument is a function that defines a sequence-to-sequence models,
    e.g., seq2seq = lambda x, y: basic_rnn_seq2seq(x, y, rnn_cell.GRUCell(24))

    Args:
      encoder_inputs: A list of Tensors to feed the encoder; first seq2seq input.
      decoder_inputs: A list of Tensors to feed the decoder; second seq2seq input.
      targets: A list of 1D batch-sized int32 Tensors (desired output sequence).
      weights: List of 1D batch-sized float-Tensors to weight the targets.
      buckets: A list of pairs of (input size, output size) for each bucket.
      seq2seq: A sequence-to-sequence models function; it takes 2 input that
        agree with encoder_inputs and decoder_inputs, and returns a pair
        consisting of outputs and states (as, e.g., basic_rnn_seq2seq).
      softmax_loss_function: Function (inputs-batch, labels-batch) -> loss-batch
        to be used instead of the standard softmax (the default if this is None).
      per_example_loss: Boolean. If set, the returned loss will be a batch-sized
        tensor of losses for each sequence in the batch. If unset, it will be
        a scalar with the averaged loss from all examples.
      name: Optional name for this operation, defaults to "model_with_buckets".

    Returns:
      A tuple of the form (outputs, losses), where:
        outputs: The outputs for each bucket. Its j'th element consists of a list
          of 2D Tensors of shape [batch_size x num_decoder_symbols] (jth outputs).
        losses: List of scalar Tensors, representing losses for each bucket, or,
          if per_example_loss is set, a list of 1D batch-sized float Tensors.

    Raises:
      ValueError: If length of encoder_inputsut, targets, or weights is smaller
        than the largest (last) bucket.
    """
    if len(encoder_inputs) < buckets[-1][0]:
        raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
                         "st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
    if len(targets) < buckets[-1][1]:
        raise ValueError("Length of targets (%d) must be at least that of last"
                         "bucket (%d)." % (len(targets), buckets[-1][1]))
    if len(weights) < buckets[-1][1]:
        raise ValueError("Length of weights (%d) must be at least that of last"
                         "bucket (%d)." % (len(weights), buckets[-1][1]))

    all_inputs = encoder_inputs + decoder_inputs + targets + weights
    states = []
    outputs = []
    with ops.name_scope(name, "model_with_buckets", all_inputs):
        for j, bucket in enumerate(buckets):
            with variable_scope.variable_scope(variable_scope.get_variable_scope(), reuse=True if j > 0 else None):
                bucket_outputs, bucket_states = seq2seq(encoder_inputs[:bucket[0]],
                                                        decoder_inputs[:bucket[1]])
                states.append(bucket_states)
                outputs.append(bucket_outputs)

    return outputs, states