import gradio as gr

import torch
import torch.nn.functional as F
from torchvision import transforms

# load model
model = torch.jit.load("food_classifier.ptl")

# Transformations that will be applied
the_transform = transforms.Compose([
        transforms.Resize((224,224)),
        transforms.CenterCrop((224,224)),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485,0.456,0.406],std=[0.229,0.224,0.225])
])

# Classes 
class_names = ['Apple Pie','Bibimbap','Cannoli','Edamame','Falafel','French Toast','Ice Cream','Ramen','Sushi','Tiramisu']

# Returns transformed image
def transform_img(img):
    return the_transform(img) 
    
# Returns string with class and probability
def classify_img(img):
    # Applying transformation to the image
    model_img = transform_img(img)
    model_img = model_img.view(1,3,224,224)
    
    # Running image through the model
    model.eval()
    with torch.no_grad():
        result = model(model_img)
    
    # Converting values to softmax values 
    result = F.softmax(result,dim=1)
    probability = round(result[0][result.argmax()].item() * 100, 2)
    
    # Returning class name and probability
    return f'{class_names[result.argmax()]} : {probability}% confident'
    
demo = gr.Interface(classify_img,
                        inputs = gr.inputs.Image(type="pil"), 
                        outputs = "text", 
                        description="Insert food image you would like to classify! <br> Categories: Apple Pie, Bibimbap, Cannoli, Edamame, Falafel, French Toast, Ice Cream, Ramen, Sushi, Tiramisu")

demo.launch(inline=False)