File size: 2,864 Bytes
04f475a
a27e928
04f475a
7b63336
 
a27e928
 
ff3533c
f825898
04f475a
f825898
800f4d4
 
 
04f475a
 
f825898
 
a27e928
 
 
 
 
 
 
 
 
 
 
 
 
 
800f4d4
a27e928
800f4d4
4bfa63a
 
a27e928
 
4bfa63a
 
f825898
7b63336
ff3533c
94c304e
7b63336
 
800f4d4
 
ff3533c
800f4d4
a27e928
94c304e
04f475a
 
 
 
 
 
 
 
800f4d4
04f475a
f825898
800f4d4
f825898
 
94c304e
800f4d4
f825898
 
 
a27e928
f825898
 
7b63336
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
import streamlit as st
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
from PIL import Image
import os

# Hugging Face token login (add this as a secret in Hugging Face Spaces)
os.environ["HF_TOKEN"] = st.secrets["HF_TOKEN"]

# Load the image classification pipeline
@st.cache_resource
def load_image_classification_pipeline():
    """
    Load the image classification pipeline using a pretrained model.
    """
    return pipeline("image-classification", model="Shresthadev403/food-image-classification")

pipe_classification = load_image_classification_pipeline()

# Load the Llama model for ingredient generation
@st.cache_resource
def load_llama_pipeline():
    """
    Load the Llama model for ingredient generation.
    """
    tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct", use_auth_token=os.environ["HF_TOKEN"])
    model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct", use_auth_token=os.environ["HF_TOKEN"])
    return pipeline("text-generation", model=model, tokenizer=tokenizer)

pipe_llama = load_llama_pipeline()

# Function to generate ingredients using the Llama model
def get_ingredients_llama(food_name):
    """
    Generate a list of ingredients for the given food item using the Llama model.
    """
    prompt = f"List the main ingredients typically used to prepare {food_name}."
    try:
        response = pipe_llama(prompt, max_length=50, num_return_sequences=1)
        return response[0]["generated_text"].strip()
    except Exception as e:
        return f"Error generating ingredients: {e}"

# Streamlit app setup
st.title("Food Image Recognition with Ingredients")

# Add banner image
st.image("IR_IMAGE.png", caption="Food Recognition Model", use_column_width=True)

# Sidebar for model information
st.sidebar.title("Model Information")
st.sidebar.write("**Image Classification Model**: Shresthadev403/food-image-classification")
st.sidebar.write("**LLM for Ingredients**: meta-llama/Llama-3.2-3B-Instruct")

# Upload image
uploaded_file = st.file_uploader("Choose a food image...", type=["jpg", "png", "jpeg"])

if uploaded_file is not None:
    # Display the uploaded image
    image = Image.open(uploaded_file)
    st.image(image, caption="Uploaded Image", use_column_width=True)
    st.write("Classifying...")

    # Make predictions
    predictions = pipe_classification(image)

    # Display only the top prediction
    top_food = predictions[0]['label']
    st.header(f"Food: {top_food}")

    # Generate and display ingredients for the top prediction
    st.subheader("Ingredients")
    try:
        ingredients = get_ingredients_llama(top_food)
        st.write(ingredients)
    except Exception as e:
        st.error(f"Error generating ingredients: {e}")

# Footer
st.sidebar.markdown("Created with ❤️ using Streamlit and Hugging Face.")