"""Cofiber Threshold V3: spatial-reg variant with 3x3 depthwise convolution on regression features.

Adds spatial context to box regression by letting each token see its 8 spatial
neighbors through a depthwise convolution. This directly addresses the
localization bottleneck in V2 (mAP@0.75 collapse) where each token predicts
box boundaries from its own features alone, with no access to neighboring tokens.

Architecture delta from V2 (box32_92k):
  - Add nn.Conv2d(32, 32, 3, padding=1, groups=32) after the regression hidden layer
  - +320 params (32 channels * 9 kernel values + 32 bias)
  - 91,960 total params (under NanoDet-m-0.5x head at 94K)

Results vs V2:
  - mAP@[0.5:0.95]: 5.9 -> 8.2 (+39%)
  - mAP@0.50: 21.4 -> 26.1 (+22%)
  - mAP@0.75: 1.3 -> 2.7 (+108%)
"""

import torch
import torch.nn as nn
import torch.nn.functional as F

NUM_CLASSES = 80


def cofiber_decompose(f, n_scales):
    cofibers = []
    residual = f
    for _ in range(n_scales - 1):
        omega = F.avg_pool2d(residual, 2)
        sigma_omega = F.interpolate(omega, size=residual.shape[2:], mode="bilinear", align_corners=False)
        cofibers.append(residual - sigma_omega)
        residual = omega
    cofibers.append(residual)
    return cofibers


class CofiberThresholdV3(nn.Module):
    """Cofiber decomposition + LayerNorm + prototype cls + spatial box regression. ~92K params."""
    name = "cofiber_threshold_spatialreg"
    needs_intermediates = False

    def __init__(self, feat_dim=768, num_classes=NUM_CLASSES, n_scales=3, reg_hidden=32):
        super().__init__()
        self.n_scales = n_scales
        self.scale_norms = nn.ModuleList([nn.LayerNorm(feat_dim) for _ in range(n_scales)])
        self.prototypes = nn.Parameter(torch.randn(num_classes, feat_dim) * 0.01)
        self.proto_bias = nn.Parameter(torch.zeros(num_classes))
        self.reg_hidden = nn.Linear(feat_dim, reg_hidden)
        self.reg_act = nn.GELU()
        # 3x3 depthwise conv: each token sees its 8 spatial neighbors
        self.reg_spatial = nn.Conv2d(reg_hidden, reg_hidden, 3, padding=1, groups=reg_hidden)
        self.reg_out = nn.Linear(reg_hidden, 4)
        self.ctr_weight = nn.Parameter(torch.randn(1, feat_dim) * 0.01)
        self.ctr_bias = nn.Parameter(torch.zeros(1))
        self.scale_params = nn.Parameter(torch.ones(n_scales))

    def forward(self, spatial, inter=None):
        cofibers = cofiber_decompose(spatial, self.n_scales)
        cls_l, reg_l, ctr_l = [], [], []
        for i, cof in enumerate(cofibers):
            B, C, H, W = cof.shape
            f = self.scale_norms[i](cof.permute(0, 2, 3, 1).reshape(-1, C))
            cls = (f @ self.prototypes.T + self.proto_bias).reshape(B, H, W, -1).permute(0, 3, 1, 2)
            # Regression with spatial context
            reg_h = self.reg_act(self.reg_hidden(f))
            reg_h_spatial = reg_h.reshape(B, H, W, -1).permute(0, 3, 1, 2)
            reg_h_spatial = self.reg_spatial(reg_h_spatial)
            reg_h = reg_h_spatial.permute(0, 2, 3, 1).reshape(-1, reg_h.shape[-1])
            reg_raw = (self.reg_out(reg_h) * self.scale_params[i]).clamp(-10, 10)
            reg = torch.exp(reg_raw).reshape(B, H, W, 4).permute(0, 3, 1, 2)
            ctr = (f @ self.ctr_weight.T + self.ctr_bias).reshape(B, H, W, 1).permute(0, 3, 1, 2)
            cls_l.append(cls)
            reg_l.append(reg)
            ctr_l.append(ctr)
        return cls_l, reg_l, ctr_l