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


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# Load the trained model (make sure the Net class definition is available)
net = Net()
net.load_state_dict(torch.load('model.pth', map_location=torch.device('cpu')))
net.eval()

def predict(image):
    transform = transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor(),
        transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

     # Convert the NumPy array to a PIL Image and apply the transformations
    image = Image.fromarray(image.astype('uint8'), 'RGB')
    image = transform(image).unsqueeze(0)
    
    with torch.no_grad():
        outputs = net(image)
        _, predicted = torch.max(outputs, 1)
        classes = ('plane', 'car', 'bird', 'cat', 'deer', 
                   'dog', 'frog', 'horse', 'ship', 'truck')
        return classes[predicted[0]]

iface = gr.Interface(fn=predict, inputs="image", outputs="text", 
                     description="Upload an image to classify it into one of the CIFAR-10 classes.")
iface.launch()