import torch
import torch.nn as nn
from torchvision import transforms
from PIL import Image
from huggingface_hub import hf_hub_download
import io
import base64
import numpy as np

# --- Basic UNet Components ---
class DoubleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        return self.double_conv(x)

class Down(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.maxpool_conv = nn.Sequential(
            nn.MaxPool2d(2),
            DoubleConv(in_channels, out_channels)
        )

    def forward(self, x):
        return self.maxpool_conv(x)

class Up(nn.Module):
    def __init__(self, in_channels, out_channels, bilinear=True):
        super().__init__()
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
        else:
            self.up = nn.ConvTranspose2d(in_channels // 2, in_channels // 2, kernel_size=2, stride=2)
        self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        x1 = self.up(x1)
        diffY = x2.size()[2] - x1.size()[2]
        diffX = x2.size()[3] - x1.size()[3]
        x1 = nn.functional.pad(x1, [diffX // 2, diffX - diffX // 2,
                                    diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1)
        return self.conv(x)

class OutConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)

    def forward(self, x):
        return self.conv(x)

# --- Full UNet ---
class UNet(nn.Module):
    def __init__(self, n_channels=3, n_classes=1, bilinear=True):
        super().__init__()
        self.n_channels = n_channels
        self.n_classes = n_classes
        self.bilinear = bilinear

        self.inc = DoubleConv(n_channels, 64)
        self.down1 = Down(64, 128)
        self.down2 = Down(128, 256)
        self.down3 = Down(256, 512)
        factor = 2 if bilinear else 1
        self.down4 = Down(512, 1024 // factor)
        self.up1 = Up(1024, 512 // factor, bilinear)
        self.up2 = Up(512, 256 // factor, bilinear)
        self.up3 = Up(256, 128 // factor, bilinear)
        self.up4 = Up(128, 64, bilinear)
        self.outc = OutConv(64, n_classes)

    def forward(self, x):
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x3 = self.down2(x2)
        x4 = self.down3(x3)
        x5 = self.down4(x4)
        x = self.up1(x5, x4)
        x = self.up2(x, x3)
        x = self.up3(x, x2)
        x = self.up4(x, x1)
        logits = self.outc(x)
        return torch.sigmoid(logits)

# --- EndpointHandler for Hugging Face Inference Endpoint ---
class EndpointHandler:
    def __init__(self, path=""):
        model_path = hf_hub_download(repo_id="whitney0507/unet-model", filename="UNet_Model.pth")
        self.model = UNet()
        state_dict = torch.load(model_path, map_location=torch.device("cpu"))
        self.model.load_state_dict(state_dict)
        self.model.eval()
        self.transform = transforms.Compose([
            transforms.Resize((256, 256)),
            transforms.ToTensor()
        ])

    def __call__(self, data):
        image_bytes = base64.b64decode(data["inputs"])
        image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
        input_tensor = self.transform(image).unsqueeze(0)

        with torch.no_grad():
            output = self.model(input_tensor)
            mask = (output > 0.5).int().squeeze().cpu().numpy()

        # Ensure mask is in uint8 format for image encoding
        result_img = Image.fromarray((mask * 255).astype(np.uint8))
        buffer = io.BytesIO()
        result_img.save(buffer, format="PNG")
        encoded_output = base64.b64encode(buffer.getvalue()).decode("utf-8")
        return {"prediction": encoded_output}