import torch
import torch.nn as nn
import torch.nn.functional as F
from contextlib import contextmanager
from einops import rearrange

from core.models.common.get_model import get_model, register

from .autokl_modules.diffusion_modules import Encoder, Decoder
from .autokl_modules.distributions import DiagonalGaussianDistribution


@register('autoencoderkl')
class AutoencoderKL(nn.Module):
    def __init__(self,
                 ddconfig,
                 lossconfig,
                 embed_dim,
                 ckpt_path=None,
                 ignore_keys=[],
                 image_key="image",
                 colorize_nlabels=None,
                 monitor=None,):
        super().__init__()
        self.image_key = image_key
        self.encoder = Encoder(**ddconfig)
        self.decoder = Decoder(**ddconfig)
        assert ddconfig["double_z"]
        self.quant_conv = torch.nn.Conv2d(2*ddconfig["z_channels"], 2*embed_dim, 1)
        self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)
        self.embed_dim = embed_dim
        if colorize_nlabels is not None:
            assert type(colorize_nlabels)==int
            self.register_buffer("colorize", torch.randn(3, colorize_nlabels, 1, 1))
        if monitor is not None:
            self.monitor = monitor

    def encode(self, x):
        if x.ndim == 5:
            is_video = True
            num_frames = x.shape[2]
            x = rearrange(x, 'b c f h w -> (b f) c h w')
        else:
            is_video = False
        if x.shape[1] == 1:
            x = torch.cat([x, x, x], dim=1)
            
        h = self.encoder(x)
        moments = self.quant_conv(h)
        if is_video:
            moments = rearrange(moments, '(b f) c h w -> b c f h w', f=num_frames)
        posterior = DiagonalGaussianDistribution(moments)
        return posterior

    def decode(self, z):
        if z.ndim == 5:
            is_video = True
            num_frames = z.shape[2]
            z = rearrange(z, 'b c f h w -> (b f) c h w')
        else:
            is_video = False
            num_frames = 1
            
        z = self.post_quant_conv(z)
        dec = self.decoder(z, num_frames=num_frames)
        
        if is_video:
            dec = rearrange(dec, '(b f) c h w -> b c f h w', f=num_frames)
        return dec

    def forward(self, input, sample_posterior=True):
        posterior = self.encode(input)
        if sample_posterior:
            z = posterior.sample().to(input.dtype)
        else:
            z = posterior.mode().to(input.dtype)
        dec = self.decode(z)
        return dec, posterior

    def get_input(self, batch, k):
        x = batch[k]
        if len(x.shape) == 3:
            x = x[..., None]
        x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format)
        return x

    def training_step(self, batch, batch_idx, optimizer_idx):
        inputs = self.get_input(batch, self.image_key)
        reconstructions, posterior = self(inputs)

        if optimizer_idx == 0:
            # train encoder+decoder+logvar
            aeloss, log_dict_ae = self.loss(inputs, reconstructions, posterior, optimizer_idx, self.global_step,
                                            last_layer=self.get_last_layer(), split="train")
            self.log("aeloss", aeloss, prog_bar=True, logger=True, on_step=True, on_epoch=True)
            self.log_dict(log_dict_ae, prog_bar=False, logger=True, on_step=True, on_epoch=False)
            return aeloss

        if optimizer_idx == 1:
            # train the discriminator
            discloss, log_dict_disc = self.loss(inputs, reconstructions, posterior, optimizer_idx, self.global_step,
                                                last_layer=self.get_last_layer(), split="train")

            self.log("discloss", discloss, prog_bar=True, logger=True, on_step=True, on_epoch=True)
            self.log_dict(log_dict_disc, prog_bar=False, logger=True, on_step=True, on_epoch=False)
            return discloss

    def validation_step(self, batch, batch_idx):
        inputs = self.get_input(batch, self.image_key)
        reconstructions, posterior = self(inputs)
        aeloss, log_dict_ae = self.loss(inputs, reconstructions, posterior, 0, self.global_step,
                                        last_layer=self.get_last_layer(), split="val")

        discloss, log_dict_disc = self.loss(inputs, reconstructions, posterior, 1, self.global_step,
                                            last_layer=self.get_last_layer(), split="val")

        self.log("val/rec_loss", log_dict_ae["val/rec_loss"])
        self.log_dict(log_dict_ae)
        self.log_dict(log_dict_disc)
        return self.log_dict

    def configure_optimizers(self):
        lr = self.learning_rate
        opt_ae = torch.optim.Adam(list(self.encoder.parameters())+
                                  list(self.decoder.parameters())+
                                  list(self.quant_conv.parameters())+
                                  list(self.post_quant_conv.parameters()),
                                  lr=lr, betas=(0.5, 0.9))
        opt_disc = torch.optim.Adam(self.loss.discriminator.parameters(),
                                    lr=lr, betas=(0.5, 0.9))
        return [opt_ae, opt_disc], []

    def get_last_layer(self):
        return self.decoder.conv_out.weight

    @torch.no_grad()
    def log_images(self, batch, only_inputs=False, **kwargs):
        log = dict()
        x = self.get_input(batch, self.image_key)
        x = x.to(self.device)
        if not only_inputs:
            xrec, posterior = self(x)
            if x.shape[1] > 3:
                # colorize with random projection
                assert xrec.shape[1] > 3
                x = self.to_rgb(x)
                xrec = self.to_rgb(xrec)
            log["samples"] = self.decode(torch.randn_like(posterior.sample()))
            log["reconstructions"] = xrec
        log["inputs"] = x
        return log

    def to_rgb(self, x):
        assert self.image_key == "segmentation"
        if not hasattr(self, "colorize"):
            self.register_buffer("colorize", torch.randn(3, x.shape[1], 1, 1).to(x))
        x = F.conv2d(x, weight=self.colorize)
        x = 2.*(x-x.min())/(x.max()-x.min()) - 1.
        return x


class IdentityFirstStage(nn.Module):
    def __init__(self, *args, vq_interface=False, **kwargs):
        self.vq_interface = vq_interface  # TODO: Should be true by default but check to not break older stuff
        super().__init__()

    def encode(self, x, *args, **kwargs):
        return x

    def decode(self, x, *args, **kwargs):
        return x

    def quantize(self, x, *args, **kwargs):
        if self.vq_interface:
            return x, None, [None, None, None]
        return x

    def forward(self, x, *args, **kwargs):
        return x