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

class_labels = ['Dog', 'Horse', 'Elephant', 'Butterfly', 'Chicken', 'Cat', 'Cow', 'Sheep', 'Spider', 'Squirrel']

transform = transforms.Compose([
    transforms.Resize((128, 128)),
    transforms.ToTensor(),
])

class Animal(nn.Module):
    def __init__(self, num_classes=10):
        super(Animal, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(32)
        self.relu1 = nn.ReLU()
        self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)

        self.conv2 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(64)
        self.relu2 = nn.ReLU()
        self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)

        self.conv3 = nn.Conv2d(64, 128, kernel_size=3, padding=1)
        self.bn3 = nn.BatchNorm2d(128)
        self.relu3 = nn.ReLU()
        self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)

        self.fc1 = nn.Linear(128 * 16 * 16, 512)
        self.relu4 = nn.ReLU()
        self.dropout = nn.Dropout(0.5)
        self.fc2 = nn.Linear(512, num_classes)

    def forward(self, x):
        x = self.pool1(self.relu1(self.bn1(self.conv1(x))))
        x = self.pool2(self.relu2(self.bn2(self.conv2(x))))
        x = self.pool3(self.relu3(self.bn3(self.conv3(x))))
        x = x.view(x.size(0), -1)
        x = self.relu4(self.fc1(x))
        x = self.dropout(x)
        x = self.fc2(x)
        return x

model = Animal()
model.load_state_dict(torch.load('model.pth', map_location=torch.device('cpu')))
model.eval()

def predict_class_with_confidence(input_image):
    input_image = Image.fromarray(input_image)
    input_image = transform(input_image).unsqueeze(0)

    with torch.no_grad():
        output = model(input_image)

    _, predicted_class = torch.max(output.data, 1)
    predicted_label = class_labels[predicted_class.item()]

    return predicted_label

app = gr.Interface(
    fn=predict_class_with_confidence,
    inputs=gr.inputs.Image(),
    outputs="text",
    live=True,
    capture_session=True,
    title="Animal Classification App", 
    description="Upload an image of an animal to classify it",
)

if __name__ == '__main__':
    app.launch(share=True)