# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

from typing import Optional, Tuple

import torch.nn.functional as F
from torch import Tensor

from mmdet.registry import MODELS
from .fpn import FPN


@MODELS.register_module()
class FPN_DropBlock(FPN):

    def __init__(self,
                 *args,
                 plugin: Optional[dict] = dict(
                     type='DropBlock',
                     drop_prob=0.3,
                     block_size=3,
                     warmup_iters=0),
                 **kwargs) -> None:
        super().__init__(*args, **kwargs)
        self.plugin = None
        if plugin is not None:
            self.plugin = MODELS.build(plugin)

    def forward(self, inputs: Tuple[Tensor]) -> tuple:
        """Forward function.

        Args:
            inputs (tuple[Tensor]): Features from the upstream network, each
                is a 4D-tensor.

        Returns:
            tuple: Feature maps, each is a 4D-tensor.
        """
        assert len(inputs) == len(self.in_channels)

        # build laterals
        laterals = [
            lateral_conv(inputs[i + self.start_level])
            for i, lateral_conv in enumerate(self.lateral_convs)
        ]

        # build top-down path
        used_backbone_levels = len(laterals)
        for i in range(used_backbone_levels - 1, 0, -1):
            # In some cases, fixing `scale factor` (e.g. 2) is preferred, but
            #  it cannot co-exist with `size` in `F.interpolate`.
            if 'scale_factor' in self.upsample_cfg:
                # fix runtime error of "+=" inplace operation in PyTorch 1.10
                laterals[i - 1] = laterals[i - 1] + F.interpolate(
                    laterals[i], **self.upsample_cfg)
            else:
                prev_shape = laterals[i - 1].shape[2:]
                laterals[i - 1] = laterals[i - 1] + F.interpolate(
                    laterals[i], size=prev_shape, **self.upsample_cfg)

            if self.plugin is not None:
                laterals[i - 1] = self.plugin(laterals[i - 1])

        # build outputs
        # part 1: from original levels
        outs = [
            self.fpn_convs[i](laterals[i]) for i in range(used_backbone_levels)
        ]
        # part 2: add extra levels
        if self.num_outs > len(outs):
            # use max pool to get more levels on top of outputs
            # (e.g., Faster R-CNN, Mask R-CNN)
            if not self.add_extra_convs:
                for i in range(self.num_outs - used_backbone_levels):
                    outs.append(F.max_pool2d(outs[-1], 1, stride=2))
            # add conv layers on top of original feature maps (RetinaNet)
            else:
                if self.add_extra_convs == 'on_input':
                    extra_source = inputs[self.backbone_end_level - 1]
                elif self.add_extra_convs == 'on_lateral':
                    extra_source = laterals[-1]
                elif self.add_extra_convs == 'on_output':
                    extra_source = outs[-1]
                else:
                    raise NotImplementedError
                outs.append(self.fpn_convs[used_backbone_levels](extra_source))
                for i in range(used_backbone_levels + 1, self.num_outs):
                    if self.relu_before_extra_convs:
                        outs.append(self.fpn_convs[i](F.relu(outs[-1])))
                    else:
                        outs.append(self.fpn_convs[i](outs[-1]))
        return tuple(outs)