import torch
import torch.nn.functional as F


def calculate_adaptive_weight(recon_loss, g_loss, last_layer, disc_weight_max):
    recon_grads = torch.autograd.grad(
        recon_loss, last_layer, retain_graph=True)[0]
    g_grads = torch.autograd.grad(g_loss, last_layer, retain_graph=True)[0]

    d_weight = torch.norm(recon_grads) / (torch.norm(g_grads) + 1e-4)
    d_weight = torch.clamp(d_weight, 0.0, disc_weight_max).detach()
    return d_weight


def adopt_weight(weight, global_step, threshold=0, value=0.):
    if global_step < threshold:
        weight = value
    return weight


@torch.jit.script
def hinge_d_loss(logits_real, logits_fake):
    loss_real = torch.mean(F.relu(1. - logits_real))
    loss_fake = torch.mean(F.relu(1. + logits_fake))
    d_loss = 0.5 * (loss_real + loss_fake)
    return d_loss


def DiffAugment(x, policy='', channels_first=True):
    if policy:
        if not channels_first:
            x = x.permute(0, 3, 1, 2)
        for p in policy.split(','):
            for f in AUGMENT_FNS[p]:
                x = f(x)
        if not channels_first:
            x = x.permute(0, 2, 3, 1)
        x = x.contiguous()
    return x


def rand_brightness(x):
    x = x + (
        torch.rand(x.size(0), 1, 1, 1, dtype=x.dtype, device=x.device) - 0.5)
    return x


def rand_saturation(x):
    x_mean = x.mean(dim=1, keepdim=True)
    x = (x - x_mean) * (torch.rand(
        x.size(0), 1, 1, 1, dtype=x.dtype, device=x.device) * 2) + x_mean
    return x


def rand_contrast(x):
    x_mean = x.mean(dim=[1, 2, 3], keepdim=True)
    x = (x - x_mean) * (torch.rand(
        x.size(0), 1, 1, 1, dtype=x.dtype, device=x.device) + 0.5) + x_mean
    return x


def rand_translation(x, ratio=0.125):
    shift_x, shift_y = int(x.size(2) * ratio +
                           0.5), int(x.size(3) * ratio + 0.5)
    translation_x = torch.randint(
        -shift_x, shift_x + 1, size=[x.size(0), 1, 1], device=x.device)
    translation_y = torch.randint(
        -shift_y, shift_y + 1, size=[x.size(0), 1, 1], device=x.device)
    grid_batch, grid_x, grid_y = torch.meshgrid(
        torch.arange(x.size(0), dtype=torch.long, device=x.device),
        torch.arange(x.size(2), dtype=torch.long, device=x.device),
        torch.arange(x.size(3), dtype=torch.long, device=x.device),
    )
    grid_x = torch.clamp(grid_x + translation_x + 1, 0, x.size(2) + 1)
    grid_y = torch.clamp(grid_y + translation_y + 1, 0, x.size(3) + 1)
    x_pad = F.pad(x, [1, 1, 1, 1, 0, 0, 0, 0])
    x = x_pad.permute(0, 2, 3, 1).contiguous()[grid_batch, grid_x,
                                               grid_y].permute(0, 3, 1, 2)
    return x


def rand_cutout(x, ratio=0.5):
    cutout_size = int(x.size(2) * ratio + 0.5), int(x.size(3) * ratio + 0.5)
    offset_x = torch.randint(
        0,
        x.size(2) + (1 - cutout_size[0] % 2),
        size=[x.size(0), 1, 1],
        device=x.device)
    offset_y = torch.randint(
        0,
        x.size(3) + (1 - cutout_size[1] % 2),
        size=[x.size(0), 1, 1],
        device=x.device)
    grid_batch, grid_x, grid_y = torch.meshgrid(
        torch.arange(x.size(0), dtype=torch.long, device=x.device),
        torch.arange(cutout_size[0], dtype=torch.long, device=x.device),
        torch.arange(cutout_size[1], dtype=torch.long, device=x.device),
    )
    grid_x = torch.clamp(
        grid_x + offset_x - cutout_size[0] // 2, min=0, max=x.size(2) - 1)
    grid_y = torch.clamp(
        grid_y + offset_y - cutout_size[1] // 2, min=0, max=x.size(3) - 1)
    mask = torch.ones(
        x.size(0), x.size(2), x.size(3), dtype=x.dtype, device=x.device)
    mask[grid_batch, grid_x, grid_y] = 0
    x = x * mask.unsqueeze(1)
    return x


AUGMENT_FNS = {
    'color': [rand_brightness, rand_saturation, rand_contrast],
    'translation': [rand_translation],
    'cutout': [rand_cutout],
}