# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Gated Recurrent Unit V1 layer."""


from keras import activations
from keras import constraints
from keras import initializers
from keras import regularizers
from keras.engine.input_spec import InputSpec
from keras.layers.rnn import gru
from keras.layers.rnn import rnn_utils
from keras.layers.rnn.base_rnn import RNN

# isort: off
from tensorflow.python.platform import tf_logging as logging
from tensorflow.python.util.tf_export import keras_export


@keras_export(v1=["keras.layers.GRUCell"])
class GRUCell(gru.GRUCell):
    """Cell class for the GRU layer.

    Args:
      units: Positive integer, dimensionality of the output space.
      activation: Activation function to use.
        Default: hyperbolic tangent (`tanh`).
        If you pass None, no activation is applied
        (ie. "linear" activation: `a(x) = x`).
      recurrent_activation: Activation function to use
        for the recurrent step.
        Default: hard sigmoid (`hard_sigmoid`).
        If you pass `None`, no activation is applied
        (ie. "linear" activation: `a(x) = x`).
      use_bias: Boolean, whether the layer uses a bias vector.
      kernel_initializer: Initializer for the `kernel` weights matrix,
        used for the linear transformation of the inputs.
      recurrent_initializer: Initializer for the `recurrent_kernel`
        weights matrix,
        used for the linear transformation of the recurrent state.
      bias_initializer: Initializer for the bias vector.
      kernel_regularizer: Regularizer function applied to
        the `kernel` weights matrix.
      recurrent_regularizer: Regularizer function applied to
        the `recurrent_kernel` weights matrix.
      bias_regularizer: Regularizer function applied to the bias vector.
      kernel_constraint: Constraint function applied to
        the `kernel` weights matrix.
      recurrent_constraint: Constraint function applied to
        the `recurrent_kernel` weights matrix.
      bias_constraint: Constraint function applied to the bias vector.
      dropout: Float between 0 and 1. Fraction of the units to drop for the
        linear transformation of the inputs.
      recurrent_dropout: Float between 0 and 1.
        Fraction of the units to drop for
        the linear transformation of the recurrent state.
      reset_after: GRU convention (whether to apply reset gate after or
        before matrix multiplication). False = "before" (default),
        True = "after" (cuDNN compatible).

    Call arguments:
      inputs: A 2D tensor.
      states: List of state tensors corresponding to the previous timestep.
      training: Python boolean indicating whether the layer should behave in
        training mode or in inference mode. Only relevant when `dropout` or
        `recurrent_dropout` is used.
    """

    def __init__(
        self,
        units,
        activation="tanh",
        recurrent_activation="hard_sigmoid",
        use_bias=True,
        kernel_initializer="glorot_uniform",
        recurrent_initializer="orthogonal",
        bias_initializer="zeros",
        kernel_regularizer=None,
        recurrent_regularizer=None,
        bias_regularizer=None,
        kernel_constraint=None,
        recurrent_constraint=None,
        bias_constraint=None,
        dropout=0.0,
        recurrent_dropout=0.0,
        reset_after=False,
        **kwargs
    ):
        super().__init__(
            units,
            activation=activation,
            recurrent_activation=recurrent_activation,
            use_bias=use_bias,
            kernel_initializer=kernel_initializer,
            recurrent_initializer=recurrent_initializer,
            bias_initializer=bias_initializer,
            kernel_regularizer=kernel_regularizer,
            recurrent_regularizer=recurrent_regularizer,
            bias_regularizer=bias_regularizer,
            kernel_constraint=kernel_constraint,
            recurrent_constraint=recurrent_constraint,
            bias_constraint=bias_constraint,
            dropout=dropout,
            recurrent_dropout=recurrent_dropout,
            implementation=kwargs.pop("implementation", 1),
            reset_after=reset_after,
            **kwargs
        )


@keras_export(v1=["keras.layers.GRU"])
class GRU(RNN):
    """Gated Recurrent Unit - Cho et al. 2014.

    There are two variants. The default one is based on 1406.1078v3 and
    has reset gate applied to hidden state before matrix multiplication. The
    other one is based on original 1406.1078v1 and has the order reversed.

    The second variant is compatible with CuDNNGRU (GPU-only) and allows
    inference on CPU. Thus it has separate biases for `kernel` and
    `recurrent_kernel`. Use `'reset_after'=True` and
    `recurrent_activation='sigmoid'`.

    Args:
      units: Positive integer, dimensionality of the output space.
      activation: Activation function to use.
        Default: hyperbolic tangent (`tanh`).
        If you pass `None`, no activation is applied
        (ie. "linear" activation: `a(x) = x`).
      recurrent_activation: Activation function to use
        for the recurrent step.
        Default: hard sigmoid (`hard_sigmoid`).
        If you pass `None`, no activation is applied
        (ie. "linear" activation: `a(x) = x`).
      use_bias: Boolean, whether the layer uses a bias vector.
      kernel_initializer: Initializer for the `kernel` weights matrix,
        used for the linear transformation of the inputs.
      recurrent_initializer: Initializer for the `recurrent_kernel` weights
        matrix, used for the linear transformation of the recurrent state.
      bias_initializer: Initializer for the bias vector.
      kernel_regularizer: Regularizer function applied to
        the `kernel` weights matrix.
      recurrent_regularizer: Regularizer function applied to
        the `recurrent_kernel` weights matrix.
      bias_regularizer: Regularizer function applied to the bias vector.
      activity_regularizer: Regularizer function applied to
        the output of the layer (its "activation")..
      kernel_constraint: Constraint function applied to
        the `kernel` weights matrix.
      recurrent_constraint: Constraint function applied to
        the `recurrent_kernel` weights matrix.
      bias_constraint: Constraint function applied to the bias vector.
      dropout: Float between 0 and 1.
        Fraction of the units to drop for
        the linear transformation of the inputs.
      recurrent_dropout: Float between 0 and 1.
        Fraction of the units to drop for
        the linear transformation of the recurrent state.
      return_sequences: Boolean. Whether to return the last output
        in the output sequence, or the full sequence.
      return_state: Boolean. Whether to return the last state
        in addition to the output.
      go_backwards: Boolean (default False).
        If True, process the input sequence backwards and return the
        reversed sequence.
      stateful: Boolean (default False). If True, the last state
        for each sample at index i in a batch will be used as initial
        state for the sample of index i in the following batch.
      unroll: Boolean (default False).
        If True, the network will be unrolled,
        else a symbolic loop will be used.
        Unrolling can speed-up a RNN,
        although it tends to be more memory-intensive.
        Unrolling is only suitable for short sequences.
      time_major: The shape format of the `inputs` and `outputs` tensors.
        If True, the inputs and outputs will be in shape
        `(timesteps, batch, ...)`, whereas in the False case, it will be
        `(batch, timesteps, ...)`. Using `time_major = True` is a bit more
        efficient because it avoids transposes at the beginning and end of the
        RNN calculation. However, most TensorFlow data is batch-major, so by
        default this function accepts input and emits output in batch-major
        form.
      reset_after: GRU convention (whether to apply reset gate after or
        before matrix multiplication). False = "before" (default),
        True = "after" (cuDNN compatible).

    Call arguments:
      inputs: A 3D tensor.
      mask: Binary tensor of shape `(samples, timesteps)` indicating whether
        a given timestep should be masked. An individual `True` entry indicates
        that the corresponding timestep should be utilized, while a `False`
        entry indicates that the corresponding timestep should be ignored.
      training: Python boolean indicating whether the layer should behave in
        training mode or in inference mode. This argument is passed to the cell
        when calling it. This is only relevant if `dropout` or
        `recurrent_dropout` is used.
      initial_state: List of initial state tensors to be passed to the first
        call of the cell.
    """

    def __init__(
        self,
        units,
        activation="tanh",
        recurrent_activation="hard_sigmoid",
        use_bias=True,
        kernel_initializer="glorot_uniform",
        recurrent_initializer="orthogonal",
        bias_initializer="zeros",
        kernel_regularizer=None,
        recurrent_regularizer=None,
        bias_regularizer=None,
        activity_regularizer=None,
        kernel_constraint=None,
        recurrent_constraint=None,
        bias_constraint=None,
        dropout=0.0,
        recurrent_dropout=0.0,
        return_sequences=False,
        return_state=False,
        go_backwards=False,
        stateful=False,
        unroll=False,
        reset_after=False,
        **kwargs
    ):
        implementation = kwargs.pop("implementation", 1)
        if implementation == 0:
            logging.warning(
                "`implementation=0` has been deprecated, "
                "and now defaults to `implementation=1`."
                "Please update your layer call."
            )
        if "enable_caching_device" in kwargs:
            cell_kwargs = {
                "enable_caching_device": kwargs.pop("enable_caching_device")
            }
        else:
            cell_kwargs = {}
        cell = GRUCell(
            units,
            activation=activation,
            recurrent_activation=recurrent_activation,
            use_bias=use_bias,
            kernel_initializer=kernel_initializer,
            recurrent_initializer=recurrent_initializer,
            bias_initializer=bias_initializer,
            kernel_regularizer=kernel_regularizer,
            recurrent_regularizer=recurrent_regularizer,
            bias_regularizer=bias_regularizer,
            kernel_constraint=kernel_constraint,
            recurrent_constraint=recurrent_constraint,
            bias_constraint=bias_constraint,
            dropout=dropout,
            recurrent_dropout=recurrent_dropout,
            implementation=implementation,
            reset_after=reset_after,
            dtype=kwargs.get("dtype"),
            trainable=kwargs.get("trainable", True),
            **cell_kwargs
        )
        super().__init__(
            cell,
            return_sequences=return_sequences,
            return_state=return_state,
            go_backwards=go_backwards,
            stateful=stateful,
            unroll=unroll,
            **kwargs
        )
        self.activity_regularizer = regularizers.get(activity_regularizer)
        self.input_spec = [InputSpec(ndim=3)]

    def call(self, inputs, mask=None, training=None, initial_state=None):
        return super().call(
            inputs, mask=mask, training=training, initial_state=initial_state
        )

    @property
    def units(self):
        return self.cell.units

    @property
    def activation(self):
        return self.cell.activation

    @property
    def recurrent_activation(self):
        return self.cell.recurrent_activation

    @property
    def use_bias(self):
        return self.cell.use_bias

    @property
    def kernel_initializer(self):
        return self.cell.kernel_initializer

    @property
    def recurrent_initializer(self):
        return self.cell.recurrent_initializer

    @property
    def bias_initializer(self):
        return self.cell.bias_initializer

    @property
    def kernel_regularizer(self):
        return self.cell.kernel_regularizer

    @property
    def recurrent_regularizer(self):
        return self.cell.recurrent_regularizer

    @property
    def bias_regularizer(self):
        return self.cell.bias_regularizer

    @property
    def kernel_constraint(self):
        return self.cell.kernel_constraint

    @property
    def recurrent_constraint(self):
        return self.cell.recurrent_constraint

    @property
    def bias_constraint(self):
        return self.cell.bias_constraint

    @property
    def dropout(self):
        return self.cell.dropout

    @property
    def recurrent_dropout(self):
        return self.cell.recurrent_dropout

    @property
    def implementation(self):
        return self.cell.implementation

    @property
    def reset_after(self):
        return self.cell.reset_after

    def get_config(self):
        config = {
            "units": self.units,
            "activation": activations.serialize(self.activation),
            "recurrent_activation": activations.serialize(
                self.recurrent_activation
            ),
            "use_bias": self.use_bias,
            "kernel_initializer": initializers.serialize(
                self.kernel_initializer
            ),
            "recurrent_initializer": initializers.serialize(
                self.recurrent_initializer
            ),
            "bias_initializer": initializers.serialize(self.bias_initializer),
            "kernel_regularizer": regularizers.serialize(
                self.kernel_regularizer
            ),
            "recurrent_regularizer": regularizers.serialize(
                self.recurrent_regularizer
            ),
            "bias_regularizer": regularizers.serialize(self.bias_regularizer),
            "activity_regularizer": regularizers.serialize(
                self.activity_regularizer
            ),
            "kernel_constraint": constraints.serialize(self.kernel_constraint),
            "recurrent_constraint": constraints.serialize(
                self.recurrent_constraint
            ),
            "bias_constraint": constraints.serialize(self.bias_constraint),
            "dropout": self.dropout,
            "recurrent_dropout": self.recurrent_dropout,
            "implementation": self.implementation,
            "reset_after": self.reset_after,
        }
        config.update(rnn_utils.config_for_enable_caching_device(self.cell))
        base_config = super().get_config()
        del base_config["cell"]
        return dict(list(base_config.items()) + list(config.items()))

    @classmethod
    def from_config(cls, config):
        if "implementation" in config and config["implementation"] == 0:
            config["implementation"] = 1
        return cls(**config)