# Copyright (c) OpenMMLab. All rights reserved.
from abc import ABCMeta, abstractmethod
from typing import Dict, Tuple, Union

import torch
from mmengine.model import BaseModel
from torch import Tensor

from mmocr.utils.typing_utils import (DetSampleList, OptConfigType,
                                      OptDetSampleList, OptMultiConfig)

ForwardResults = Union[Dict[str, torch.Tensor], DetSampleList,
                       Tuple[torch.Tensor], torch.Tensor]


class BaseTextDetector(BaseModel, metaclass=ABCMeta):
    """Base class for detectors.

    Args:
       data_preprocessor (dict or ConfigDict, optional): The pre-process
           config of :class:`BaseDataPreprocessor`.  it usually includes,
            ``pad_size_divisor``, ``pad_value``, ``mean`` and ``std``.
       init_cfg (dict or ConfigDict, optional): the config to control the
           initialization. Defaults to None.
    """

    def __init__(self,
                 data_preprocessor: OptConfigType = None,
                 init_cfg: OptMultiConfig = None):
        super().__init__(
            data_preprocessor=data_preprocessor, init_cfg=init_cfg)

    @property
    def with_neck(self) -> bool:
        """bool: whether the detector has a neck"""
        return hasattr(self, 'neck') and self.neck is not None

    def forward(self,
                inputs: torch.Tensor,
                data_samples: OptDetSampleList = None,
                mode: str = 'tensor') -> ForwardResults:
        """The unified entry for a forward process in both training and test.

        The method should accept three modes: "tensor", "predict" and "loss":

        - "tensor": Forward the whole network and return tensor or tuple of
        tensor without any post-processing, same as a common nn.Module.
        - "predict": Forward and return the predictions, which are fully
        processed to a list of :obj:`TextDetDataSample`.
        - "loss": Forward and return a dict of losses according to the given
        inputs and data samples.

        Note that this method doesn't handle either back propagation or
        parameter update, which are supposed to be done in :meth:`train_step`.

        Args:
            inputs (torch.Tensor): The input tensor with shape
                (N, C, ...) in general.
            data_samples (list[:obj:`TextDetDataSample`], optional): A batch of
                data samples that contain annotations and predictions.
                Defaults to None.
            mode (str): Return what kind of value. Defaults to 'tensor'.

        Returns:
            The return type depends on ``mode``.

            - If ``mode="tensor"``, return a tensor or a tuple of tensor.
            - If ``mode="predict"``, return a list of :obj:`TextDetDataSample`.
            - If ``mode="loss"``, return a dict of tensor.
        """
        if mode == 'loss':
            return self.loss(inputs, data_samples)
        elif mode == 'predict':
            return self.predict(inputs, data_samples)
        elif mode == 'tensor':
            return self._forward(inputs, data_samples)
        else:
            raise RuntimeError(f'Invalid mode "{mode}". '
                               'Only supports loss, predict and tensor mode')

    @abstractmethod
    def loss(self, inputs: Tensor,
             data_samples: DetSampleList) -> Union[dict, tuple]:
        """Calculate losses from a batch of inputs and data samples."""
        pass

    @abstractmethod
    def predict(self, inputs: Tensor,
                data_samples: DetSampleList) -> DetSampleList:
        """Predict results from a batch of inputs and data samples with post-
        processing."""
        pass

    @abstractmethod
    def _forward(self, inputs: Tensor, data_samples: OptDetSampleList = None):
        """Network forward process.

        Usually includes backbone, neck and head forward without any post-
        processing.
        """
        pass

    @abstractmethod
    def extract_feat(self, inputs: Tensor):
        """Extract features from images."""
        pass