import math

import torch
import torch.nn as nn

from .utils import to_cpu

# This new loss function is based on https://github.com/ultralytics/yolov3/blob/master/utils/loss.py

def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-9):
    # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
    box2 = box2.T

    # Get the coordinates of bounding boxes
    if x1y1x2y2:  # x1, y1, x2, y2 = box1
        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
    else:  # transform from xywh to xyxy
        b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
        b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
        b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
        b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2

    # Intersection area
    inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)

    # Union Area
    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
    union = w1 * h1 + w2 * h2 - inter + eps

    iou = inter / union
    if GIoU or DIoU or CIoU:
        cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) width
        ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1)  # convex height
        if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
            rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
                    (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center distance squared
            if DIoU:
                return iou - rho2 / c2  # DIoU
            elif CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
                v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
                with torch.no_grad():
                    alpha = v / ((1 + eps) - iou + v)
                return iou - (rho2 / c2 + v * alpha)  # CIoU
        else:  # GIoU https://arxiv.org/pdf/1902.09630.pdf
            c_area = cw * ch + eps  # convex area
            return iou - (c_area - union) / c_area  # GIoU
    else:
        return iou  # IoU


def smooth_BCE(eps=0.1):  # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
    # return positive, negative label smoothing BCE targets
    return 1.0 - 0.5 * eps, 0.5 * eps


class BCEBlurWithLogitsLoss(nn.Module):
    # BCEwithLogitLoss() with reduced missing label effects.
    def __init__(self, alpha=0.05):
        super(BCEBlurWithLogitsLoss, self).__init__()
        self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none')  # must be nn.BCEWithLogitsLoss()
        self.alpha = alpha

    def forward(self, pred, true):
        loss = self.loss_fcn(pred, true)
        pred = torch.sigmoid(pred)  # prob from logits
        dx = pred - true  # reduce only missing label effects
        # dx = (pred - true).abs()  # reduce missing label and false label effects
        alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4))
        loss *= alpha_factor
        return loss.mean()


class FocalLoss(nn.Module):
    # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
    def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
        super(FocalLoss, self).__init__()
        self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
        self.gamma = gamma
        self.alpha = alpha
        self.reduction = loss_fcn.reduction
        self.loss_fcn.reduction = 'none'  # required to apply FL to each element

    def forward(self, pred, true):
        loss = self.loss_fcn(pred, true)
        # p_t = torch.exp(-loss)
        # loss *= self.alpha * (1.000001 - p_t) ** self.gamma  # non-zero power for gradient stability

        # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
        pred_prob = torch.sigmoid(pred)  # prob from logits
        p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
        alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
        modulating_factor = (1.0 - p_t) ** self.gamma
        loss *= alpha_factor * modulating_factor

        if self.reduction == 'mean':
            return loss.mean()
        elif self.reduction == 'sum':
            return loss.sum()
        else:  # 'none'
            return loss


class QFocalLoss(nn.Module):
    # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
    def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
        super(QFocalLoss, self).__init__()
        self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
        self.gamma = gamma
        self.alpha = alpha
        self.reduction = loss_fcn.reduction
        self.loss_fcn.reduction = 'none'  # required to apply FL to each element

    def forward(self, pred, true):
        loss = self.loss_fcn(pred, true)

        pred_prob = torch.sigmoid(pred)  # prob from logits
        alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
        modulating_factor = torch.abs(true - pred_prob) ** self.gamma
        loss *= alpha_factor * modulating_factor

        if self.reduction == 'mean':
            return loss.mean()
        elif self.reduction == 'sum':
            return loss.sum()
        else:  # 'none'
            return loss


def compute_loss(predictions, targets, model):  # predictions, targets, model
    device = targets.device
    lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
    tcls, tbox, indices, anchors = build_targets(predictions, targets, model)  # targets
    hyperparams = model.hyperparams  # hyperparameters

    # Define criteria
    BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([1.0], device=device))
    BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([1.0], device=device))

    # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
    cp, cn = smooth_BCE(eps=0.0)

    # Focal loss
    gamma = 0 #hyperparams['fl_gamma']  # focal loss gamma
    if gamma > 0:
        BCEcls, BCEobj = FocalLoss(BCEcls, gamma), FocalLoss(BCEobj, gamma)

    # Losses
    balance = [4.0, 1.0, 0.4, 0.1]  # P3-P6
    for layer_index, layer_predictions in enumerate(predictions):  # layer index, layer predictions
        b, anchor, grid_j, grid_i = indices[layer_index]  # image, anchor, gridy, gridx
        tobj = torch.zeros_like(layer_predictions[..., 0], device=device)  # target obj

        num_targets = b.shape[0]  # number of targets
        if num_targets:
            ps = layer_predictions[b, anchor, grid_j, grid_i]  # prediction subset corresponding to targets

            # Regression
            pxy = ps[:, :2].sigmoid() * 2. - 0.5
            pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[layer_index]
            pbox = torch.cat((pxy, pwh), 1)  # predicted box
            iou = bbox_iou(pbox.T, tbox[layer_index], x1y1x2y2=False, CIoU=True)  # iou(prediction, target)
            lbox += (1.0 - iou).mean()  # iou loss

            model.gr = 1

            # Objectness
            tobj[b, anchor, grid_j, grid_i] = (1.0 - model.gr) + model.gr * iou.detach().clamp(0).type(tobj.dtype)  # iou ratio

            # Classification
            t = torch.full_like(ps[:, 5:], cn, device=device)  # targets
            t[range(num_targets), tcls[layer_index]] = cp
            lcls += BCEcls(ps[:, 5:], t)  # BCE

        lobj += BCEobj(layer_predictions[..., 4], tobj) * balance[layer_index]  # obj loss

    lbox *= 0.05 * (3. / 2)
    lobj *= (3. / 2)
    lcls *= 0.31
    batch_size = tobj.shape[0]  # batch size

    loss = lbox + lobj + lcls

    return loss * batch_size, to_cpu(torch.cat((lbox, lobj, lcls, loss)))


def build_targets(p, targets, model):
    # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
    na, nt = 3, targets.shape[0]  # number of anchors, targets #TODO
    tcls, tbox, indices, anch = [], [], [], []
    gain = torch.ones(7, device=targets.device)  # normalized to gridspace gain
    ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt)  # same as .repeat_interleave(nt)
    targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2)  # append anchor indices

    g = 0.5  # bias
    off = torch.tensor([[0, 0]], device=targets.device).float() * g  # offsets

    for i, yolo_layer in enumerate(model.yolo_layers):
        anchors = yolo_layer.anchors / yolo_layer.stride
        gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]]  # xyxy gain

        # Match targets to anchors
        t = targets * gain
        if nt:
            # Matches
            r = t[:, :, 4:6] / anchors[:, None]  # wh ratio
            j = torch.max(r, 1. / r).max(2)[0] < 4  # compare #TODO
            # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t']  # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
            t = t[j]  # filter
            # Offsets
            gxy = t[:, 2:4]  # grid xy
            gxi = gain[[2, 3]] - gxy  # inverse
            j, k = ((gxy % 1. < g) & (gxy > 1.)).T
            l, m = ((gxi % 1. < g) & (gxi > 1.)).T
            j = torch.stack((torch.ones_like(j),))
            t = t.repeat((off.shape[0], 1, 1))[j]
            offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]

        else:
            t = targets[0]
            offsets = 0

        # Define
        b, c = t[:, :2].long().T  # image, class
        gxy = t[:, 2:4]  # grid xy
        gwh = t[:, 4:6]  # grid wh
        gij = (gxy - offsets).long()
        gi, gj = gij.T  # grid xy indices

        # Append
        a = t[:, 6].long()  # anchor indices
        indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1)))  # image, anchor, grid indices
        tbox.append(torch.cat((gxy - gij, gwh), 1))  # box
        anch.append(anchors[a])  # anchors
        tcls.append(c)  # class

    return tcls, tbox, indices, anch