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

import cliport.utils.utils as utils
from cliport.models.resnet import IdentityBlock, ConvBlock
from cliport.models.core.unet import Up
from cliport.models.clip_lingunet_lat import CLIPLingUNetLat


class CLIPUNet(CLIPLingUNetLat):
    """ CLIP RN50 with U-Net skip connections without language """

    def __init__(self, input_shape, output_dim, cfg, device, preprocess):
        super().__init__(input_shape, output_dim, cfg, device, preprocess)

    def _build_decoder(self):
        self.conv1 = nn.Sequential(
            nn.Conv2d(self.input_dim, 1024, kernel_size=3, stride=1, padding=1, bias=False),
            nn.ReLU(True)
        )

        self.up1 = Up(2048, 1024 // self.up_factor, self.bilinear)

        self.up2 = Up(1024, 512 // self.up_factor, self.bilinear)

        self.up3 = Up(512, 256 // self.up_factor, self.bilinear)

        self.layer1 = nn.Sequential(
            ConvBlock(128, [64, 64, 64], kernel_size=3, stride=1, batchnorm=self.batchnorm),
            IdentityBlock(64, [64, 64, 64], kernel_size=3, stride=1, batchnorm=self.batchnorm),
            nn.UpsamplingBilinear2d(scale_factor=2),
        )

        self.layer2 = nn.Sequential(
            ConvBlock(64, [32, 32, 32], kernel_size=3, stride=1, batchnorm=self.batchnorm),
            IdentityBlock(32, [32, 32, 32], kernel_size=3, stride=1, batchnorm=self.batchnorm),
            nn.UpsamplingBilinear2d(scale_factor=2),
        )

        self.layer3 = nn.Sequential(
            ConvBlock(32, [16, 16, 16], kernel_size=3, stride=1, batchnorm=self.batchnorm),
            IdentityBlock(16, [16, 16, 16], kernel_size=3, stride=1, batchnorm=self.batchnorm),
            nn.UpsamplingBilinear2d(scale_factor=2),
        )

        self.conv2 = nn.Sequential(
            nn.Conv2d(16, self.output_dim, kernel_size=1)
        )

    def forward(self, x):
        x = self.preprocess(x, dist='clip')

        in_type = x.dtype
        in_shape = x.shape
        x = x[:,:3]  # select RGB
        x, im = self.encode_image(x)
        x = x.to(in_type)

        x = self.conv1(x)
        x = self.up1(x, im[-2])
        x = self.up2(x, im[-3])
        x = self.up3(x, im[-4])

        for layer in [self.layer1, self.layer2, self.layer3, self.conv2]:
            x = layer(x)

        x = F.interpolate(x, size=(in_shape[-2], in_shape[-1]), mode='bilinear')
        return x