# Copyright (2025) Bytedance Ltd. and/or its affiliates 

# Licensed under the Apache License, Version 2.0 (the "License"); 
# you may not use this file except in compliance with the License. 
# You may obtain a copy of the License at 

#     http://www.apache.org/licenses/LICENSE-2.0 

# Unless required by applicable law or agreed to in writing, software 
# distributed under the License is distributed on an "AS IS" BASIS, 
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 
# See the License for the specific language governing permissions and 
# limitations under the License. 
import torch
import torch.nn as nn
import torch.nn.functional as F

from .util.blocks import FeatureFusionBlock, _make_scratch


def _make_fusion_block(features, use_bn, size=None):
    return FeatureFusionBlock(
        features,
        nn.ReLU(False),
        deconv=False,
        bn=use_bn,
        expand=False,
        align_corners=True,
        size=size,
    )


class ConvBlock(nn.Module):
    def __init__(self, in_feature, out_feature):
        super().__init__()
        
        self.conv_block = nn.Sequential(
            nn.Conv2d(in_feature, out_feature, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(out_feature),
            nn.ReLU(True)
        )
    
    def forward(self, x):
        return self.conv_block(x)


class DPTHead(nn.Module):
    def __init__(
        self, 
        in_channels, 
        features=256, 
        use_bn=False, 
        out_channels=[256, 512, 1024, 1024], 
        use_clstoken=False
    ):
        super(DPTHead, self).__init__()
        
        self.use_clstoken = use_clstoken
        
        self.projects = nn.ModuleList([
            nn.Conv2d(
                in_channels=in_channels,
                out_channels=out_channel,
                kernel_size=1,
                stride=1,
                padding=0,
            ) for out_channel in out_channels
        ])
        
        self.resize_layers = nn.ModuleList([
            nn.ConvTranspose2d(
                in_channels=out_channels[0],
                out_channels=out_channels[0],
                kernel_size=4,
                stride=4,
                padding=0),
            nn.ConvTranspose2d(
                in_channels=out_channels[1],
                out_channels=out_channels[1],
                kernel_size=2,
                stride=2,
                padding=0),
            nn.Identity(),
            nn.Conv2d(
                in_channels=out_channels[3],
                out_channels=out_channels[3],
                kernel_size=3,
                stride=2,
                padding=1)
        ])
        
        if use_clstoken:
            self.readout_projects = nn.ModuleList()
            for _ in range(len(self.projects)):
                self.readout_projects.append(
                    nn.Sequential(
                        nn.Linear(2 * in_channels, in_channels),
                        nn.GELU()))
        
        self.scratch = _make_scratch(
            out_channels,
            features,
            groups=1,
            expand=False,
        )
        
        self.scratch.stem_transpose = None
        
        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)
        
        head_features_1 = features
        head_features_2 = 32
        
        self.scratch.output_conv1 = nn.Conv2d(head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1)
        self.scratch.output_conv2 = nn.Sequential(
            nn.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1),
            nn.ReLU(True),
            nn.Conv2d(head_features_2, 1, kernel_size=1, stride=1, padding=0),
            nn.ReLU(True),
            nn.Identity(),
        )
    
    def forward(self, out_features, patch_h, patch_w):
        out = []
        for i, x in enumerate(out_features):
            if self.use_clstoken:
                x, cls_token = x[0], x[1]
                readout = cls_token.unsqueeze(1).expand_as(x)
                x = self.readout_projects[i](torch.cat((x, readout), -1))
            else:
                x = x[0]
            
            x = x.permute(0, 2, 1).reshape((x.shape[0], x.shape[-1], patch_h, patch_w))
            
            x = self.projects[i](x)
            x = self.resize_layers[i](x)
            
            out.append(x)
        
        layer_1, layer_2, layer_3, layer_4 = out
        
        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, size=layer_3_rn.shape[2:])        
        path_3 = self.scratch.refinenet3(path_4, layer_3_rn, size=layer_2_rn.shape[2:])
        path_2 = self.scratch.refinenet2(path_3, layer_2_rn, size=layer_1_rn.shape[2:])
        path_1 = self.scratch.refinenet1(path_2, layer_1_rn)
        
        out = self.scratch.output_conv1(path_1)
        out = F.interpolate(out, (int(patch_h * 14), int(patch_w * 14)), mode="bilinear", align_corners=True)
        out = self.scratch.output_conv2(out)
        
        return out