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

from .base_model import BaseModel
from .blocks import (
    FeatureFusionBlock,
    FeatureFusionBlock_custom,
    Interpolate,
    _make_encoder,
    forward_vit,
)
from ..multi_task_head import MultitaskHead


def _make_fusion_block(features, use_bn):
    return FeatureFusionBlock_custom(
        features,
        nn.ReLU(False),
        deconv=False,
        bn=use_bn,
        expand=False,
        align_corners=True,
    )


class DPT(BaseModel):
    def __init__(
        self,
        head,
        features=256,
        backbone="vitb_rn50_384",
        readout="project",
        channels_last=False,
        use_bn=False,
        enable_attention_hooks=False,
        use_layer_scale=False,
    ):

        super(DPT, self).__init__()

        self.channels_last = channels_last

        hooks = {
            "vitb_rn50_384": [0, 1, 8, 11],
            "vitb16_384": [2, 5, 8, 11],
            "vitl16_384": [5, 11, 17, 23],
        }

        # Instantiate backbone and reassemble blocks
        self.pretrained, self.scratch = _make_encoder(
            backbone,
            features,
            False,  # Set to true of you want to train from scratch, uses ImageNet weights
            groups=1,
            expand=False,
            exportable=False,
            hooks=hooks[backbone],
            use_readout=readout,
            enable_attention_hooks=enable_attention_hooks,
            use_layer_scale=use_layer_scale,
        )

        self.scratch.refinenet1 = _make_fusion_block(features, use_bn)
        self.scratch.refinenet2 = _make_fusion_block(features, use_bn)
        self.scratch.refinenet3 = _make_fusion_block(features, use_bn)
        self.scratch.refinenet4 = _make_fusion_block(features, use_bn)

        self.scratch.output_conv = head

    def forward(self, x):
        if self.channels_last == True:
            x.contiguous(memory_format=torch.channels_last)
        
        layer_1, layer_2, layer_3, layer_4 = forward_vit(self.pretrained, x)

        layer_1_rn = self.scratch.layer1_rn(layer_1)
        layer_2_rn = self.scratch.layer2_rn(layer_2)
        layer_3_rn = self.scratch.layer3_rn(layer_3)
        layer_4_rn = self.scratch.layer4_rn(layer_4)

        path_4 = self.scratch.refinenet4(layer_4_rn)
        path_3 = self.scratch.refinenet3(path_4, layer_3_rn)
        path_2 = self.scratch.refinenet2(path_3, layer_2_rn)
        path_1 = self.scratch.refinenet1(path_2, layer_1_rn)
        
        out = self.scratch.output_conv(path_1)

        return out

class DPTFieldModel(DPT):
    def __init__(self, path=None, non_negative=True, head_size=[[3],[1],[1],[2],[2]], **kwargs):
        features = kwargs["features"] if "features" in kwargs else 256

        kwargs["use_bn"] = True

        num_class = sum(sum(head_size,[]))
        head = nn.Sequential(
            nn.Conv2d(features, features//2, kernel_size=3, stride=1, padding=1),
            # nn.BatchNorm2d(features//2),
            nn.ReLU(True),
            MultitaskHead(features//2, num_class, head_size=head_size),
        )

        super().__init__(head, **kwargs)

        self.stride = 2

    def forward(self, x):
        if x.shape[1] == 1:
            x = torch.cat([x,x,x], dim=1)
            
        out = super().forward(x)
        return out, None