app.py

import gradio as gr
import torch
from torch import nn
from torchvision import models, transforms
from PIL import Image

# Load the ResNet50 model
model = models.resnet50(pretrained=False)  # Don't load pre-trained weights here
model.fc = nn.Linear(model.fc.in_features, 11)  # Adjust the output layer to match your number of classes

# Load the saved model weights (food_classification_model.pth)
model.load_state_dict(torch.load('food_classification_model.pth'))  # Load from the local file
model.eval()  # Set the model to evaluation mode

# Define the same preprocessing used during training
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])

# Define the prediction function
def classify_image(img):
    # Preprocess the image
    img = transform(img).unsqueeze(0)  # Add batch dimension
    
    # Make prediction
    with torch.no_grad():
        outputs = model(img)
        probs = torch.softmax(outputs, dim=-1)
    
    # Get the label with the highest probability
    top_label = probs.argmax().item()  # Get the index of the highest probability
    return top_label

# Create the Gradio interface
iface = gr.Interface(
    fn=classify_image,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Food Image Classification",
    description="Upload an image to classify if it’s an apple pie, etc."
)

# Launch the app
iface.launch()