# ------------------------------------------------------------------------
# RF-DETR
# Copyright (c) 2025 Roboflow. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Extracted from lwdetr.py (Phase 10)
# Original copyrights: LW-DETR (Baidu), Conditional DETR (Microsoft),
# DETR (Facebook), Deformable DETR (SenseTime)
# ------------------------------------------------------------------------
"""Mathematical building blocks: MLP, inverse_sigmoid, accuracy, interpolate."""

from typing import List, Optional, Tuple

import torch
import torch.nn.functional as F  # noqa: N812
import torchvision
from torch import Tensor, nn

if float(torchvision.__version__.split(".")[1]) < 7.0:
    from torchvision.ops import _new_empty_tensor
    from torchvision.ops.misc import _output_size


@torch.no_grad()
def accuracy(output: torch.Tensor, target: torch.Tensor, topk: Tuple[int, ...] = (1,)) -> List[torch.Tensor]:
    """Computes the precision@k for the specified values of k."""
    if target.numel() == 0:
        return [torch.zeros([], device=output.device)]
    maxk = max(topk)
    batch_size = target.size(0)

    _, pred = output.topk(maxk, 1, True, True)
    pred = pred.t()
    correct = pred.eq(target.view(1, -1).expand_as(pred))

    res = []
    for k in topk:
        correct_k = correct[:k].view(-1).float().sum(0)
        res.append(correct_k.mul_(100.0 / batch_size))
    return res


def interpolate(
    input: Tensor,
    size: Optional[List[int]] = None,
    scale_factor: Optional[float] = None,
    mode: str = "nearest",
    align_corners: Optional[bool] = None,
) -> Tensor:
    """Equivalent to nn.functional.interpolate, but with support for empty batch sizes."""
    if float(torchvision.__version__.split(".")[1]) < 7.0:
        if input.numel() > 0:
            return torch.nn.functional.interpolate(input, size, scale_factor, mode, align_corners)

        output_shape = _output_size(2, input, size, scale_factor)
        output_shape = list(input.shape[:-2]) + list(output_shape)
        return _new_empty_tensor(input, output_shape)
    else:
        return torchvision.ops.misc.interpolate(input, size, scale_factor, mode, align_corners)


def inverse_sigmoid(x: torch.Tensor, eps: float = 1e-5) -> torch.Tensor:
    x = x.clamp(min=0, max=1)
    x1 = x.clamp(min=eps)
    x2 = (1 - x).clamp(min=eps)
    return torch.log(x1 / x2)


class MLP(nn.Module):
    """Very simple multi-layer perceptron (also called FFN)"""

    def __init__(self, input_dim, hidden_dim, output_dim, num_layers):
        super().__init__()
        self.num_layers = num_layers
        h = [hidden_dim] * (num_layers - 1)
        self.layers = nn.ModuleList(nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim]))

    def forward(self, x):
        for i, layer in enumerate(self.layers):
            x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
        return x