# ------------------------------------------------------------------------
# Plain-DETR
# Copyright (c) 2023 Xi'an Jiaotong University & Microsoft Research Asia.
# Licensed under The MIT License [see LICENSE for details]
# ------------------------------------------------------------------------
# Deformable DETR
# Copyright (c) 2020 SenseTime. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Modified from DETR (https://github.com/facebookresearch/detr)
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
# ------------------------------------------------------------------------

"""
Modules to compute the matching cost and solve the corresponding LSAP.
"""
import torch
from scipy.optimize import linear_sum_assignment
from torch import nn

from utils.box_ops import box_cxcywh_to_xyxy, generalized_box_iou, bbox2delta


class HungarianMatcher(nn.Module):
    def __init__(self,
                 cost_class: float = 1,
                 cost_bbox:  float = 1,
                 cost_giou:  float = 1,
                 ):
        super().__init__()
        self.cost_class = cost_class
        self.cost_bbox = cost_bbox
        self.cost_giou = cost_giou
        assert (
            cost_class != 0 or cost_bbox != 0 or cost_giou != 0
        ), "all costs cant be 0"

    def forward(self, outputs, targets):
        """ Performs the matching

        Params:
            outputs: This is a dict that contains at least these entries:
                 "pred_logits": Tensor of dim [batch_size, num_queries, num_classes] with the classification logits
                 "pred_boxes": Tensor of dim [batch_size, num_queries, 4] with the predicted box coordinates

            targets: This is a list of targets (len(targets) = batch_size), where each target is a dict containing:
                 "labels": Tensor of dim [num_target_boxes] (where num_target_boxes is the number of ground-truth
                           objects in the target) containing the class labels
                 "boxes": Tensor of dim [num_target_boxes, 4] containing the target box coordinates

        Returns:
            A list of size batch_size, containing tuples of (index_i, index_j) where:
                - index_i is the indices of the selected predictions (in order)
                - index_j is the indices of the corresponding selected targets (in order)
            For each batch element, it holds:
                len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
        """
        with torch.no_grad():
            bs, num_queries = outputs["pred_logits"].shape[:2]

            # We flatten to compute the cost matrices in a batch
            out_prob = outputs["pred_logits"].flatten(0, 1).sigmoid()
            out_bbox = outputs["pred_boxes"].flatten(0, 1)

            # Also concat the target labels and boxes
            tgt_ids = torch.cat([v["labels"] for v in targets]).to(out_prob.device)
            tgt_bbox = torch.cat([v["boxes"] for v in targets]).to(out_prob.device)

            # Compute the classification cost.
            alpha = 0.25
            gamma = 2.0
            neg_cost_class = (1 - alpha) * (out_prob ** gamma) * (-(1 - out_prob + 1e-8).log())
            pos_cost_class = alpha * ((1 - out_prob) ** gamma) * (-(out_prob + 1e-8).log())
            cost_class = pos_cost_class[:, tgt_ids] - neg_cost_class[:, tgt_ids]

            # Compute the L1 cost between boxes
            out_delta = outputs["pred_deltas"].flatten(0, 1)
            out_bbox_old = outputs["pred_boxes_old"].flatten(0, 1)
            tgt_delta = bbox2delta(out_bbox_old, tgt_bbox)
            cost_bbox = torch.cdist(out_delta[:, None], tgt_delta, p=1).squeeze(1)

            # Compute the giou cost betwen boxes
            cost_giou = -generalized_box_iou(box_cxcywh_to_xyxy(out_bbox),
                                             box_cxcywh_to_xyxy(tgt_bbox)
            )

            # Final cost matrix
            C = self.cost_bbox  * cost_bbox + \
                self.cost_class * cost_class + \
                self.cost_giou  * cost_giou
            C = C.view(bs, num_queries, -1).cpu()

            sizes = [len(v["boxes"]) for v in targets]
            indices = [linear_sum_assignment(c[i]) for i, c in enumerate(C.split(sizes, -1))]
            
            return [(torch.as_tensor(i, dtype=torch.int64),  # batch index
                     torch.as_tensor(j, dtype=torch.int64))  # query index
                     for i, j in indices]