import gradio as gr
import torch
import torch.nn as nn
import torchvision.transforms as transforms
from PIL import Image
import torch.nn.init as init

class Fire(nn.Module):
    def __init__(self, inplanes: int, squeeze_planes: int, expand1x1_planes: int, expand3x3_planes: int) -> None:
        super().__init__()
        self.inplanes = inplanes
        self.squeeze = nn.Conv2d(inplanes, squeeze_planes, kernel_size=1)
        self.squeeze_activation = nn.ReLU(inplace=True)
        self.expand1x1 = nn.Conv2d(squeeze_planes, expand1x1_planes, kernel_size=1)
        self.expand1x1_activation = nn.ReLU(inplace=True)
        self.expand3x3 = nn.Conv2d(squeeze_planes, expand3x3_planes, kernel_size=3, padding=1)
        self.expand3x3_activation = nn.ReLU(inplace=True)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.squeeze_activation(self.squeeze(x))
        return torch.cat(
            [self.expand1x1_activation(self.expand1x1(x)), self.expand3x3_activation(self.expand3x3(x))], 1
        )

class SqueezeNet(nn.Module):
    def __init__(self, version: str = "1_0", num_classes: int = 1000, dropout: float = 0.5) -> None:
        super().__init__()
        # _log_api_usage_once(self)
        self.num_classes = num_classes
        if version == "1_0":
            self.features = nn.Sequential(
                nn.Conv2d(3, 96, kernel_size=7, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(96, 16, 64, 64),
                Fire(128, 16, 64, 64),
                Fire(128, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 32, 128, 128),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(512, 64, 256, 256),
            )
        elif version == "middle":  # 0.78 mb
            self.features = nn.Sequential(
                nn.Conv2d(3, 32, kernel_size=3, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(32, 8, 32, 32),
                Fire(64, 8, 32, 32),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(64, 16, 64, 64),
                Fire(128, 16, 64, 64),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(128, 24, 96, 96),
                Fire(192, 24, 96, 96),
                Fire(192, 32, 128, 128),
                Fire(256, 32, 128, 128),
            )

        else:
            # FIXME: Is this needed? SqueezeNet should only be called from the
            # FIXME: squeezenet1_x() functions
            # FIXME: This checking is not done for the other models
            raise ValueError(f"Unsupported SqueezeNet version {version}: 1_0 or 1_1 expected")

        # Final convolution is initialized differently from the rest
        # 512
        final_conv = nn.Conv2d(256, self.num_classes, kernel_size=1)
        self.classifier = nn.Sequential(
            nn.Dropout(p=dropout), final_conv, nn.ReLU(inplace=True), nn.AdaptiveAvgPool2d((1, 1))
        )

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                if m is final_conv:
                    init.normal_(m.weight, mean=0.0, std=0.01)
                else:
                    init.kaiming_uniform_(m.weight)
                if m.bias is not None:
                    init.constant_(m.bias, 0)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.features(x)
        x = self.classifier(x)
        return torch.flatten(x, 1)


class SN(nn.Module):
    def __init__(self):
        super().__init__()
        self.model = SqueezeNet(version="middle", num_classes=2)

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


def predict(image):

    model = SN()
    model.load_state_dict(torch.load("./liveness_1M_model_0.8740054619288524 .ckpt", map_location=torch.device('cpu')))
    im = Image.open(image)
    transform1 = transforms.Compose([transforms.Resize((512, 512)),
                                     transforms.ToTensor()])
    img = transform1(im).unsqueeze(0)
    my_softmax = nn.Softmax(dim=1)
    with torch.no_grad():
        y_hat = model(img)
        liveness_score = float(my_softmax(y_hat)[0][1])

    res = {"fake": liveness_score, "real": 1 - liveness_score}
    return res


gr.Interface(
    predict,
    inputs=gr.inputs.Image(label="Upload an image", type="filepath"),
    outputs=gr.outputs.Label(num_top_classes=2),
    title="Real or Fake", examples=["./2022-10-12 16.52.56.jpg", "./2022-10-12 16.54.52.jpg", "./1724477482.jpeg"]
).launch()