app.py

import streamlit as st
import os
from PIL import Image
import numpy as np
import pickle
import tensorflow
import pandas as pd
from tensorflow.keras.preprocessing import image
from tensorflow.keras.layers import GlobalMaxPooling2D
from tensorflow.keras.applications.resnet50 import ResNet50,preprocess_input
from sklearn.neighbors import NearestNeighbors
from numpy.linalg import norm        

feature_list = np.array(pickle.load(open('embedding_large.pkl','rb')))
# print(feature_list)
filenames = pd.read_pickle('filenames_large.pkl')

# print(filenames)

feature_list_myntra = np.array(pickle.load(open('embedding_myntra.pkl','rb')))
# print(feature_list)
filenames_myntra = pd.read_pickle('filenames_myntra.pkl')




    


model = ResNet50(weights='imagenet',include_top=False,input_shape=(224,224,3))
model.trainable = False

model = tensorflow.keras.Sequential([
    model,
    GlobalMaxPooling2D()
])

st.title('Fashion Recommender System')

def save_uploaded_file(uploaded_file):
    try:
        with open(os.path.join('uploads',uploaded_file.name),'wb') as f:
            f.write(uploaded_file.getbuffer())
        return 1
    except:
        return 0

def feature_extraction(img_path,model):
    img = image.load_img(img_path, target_size=(224, 224))
    img_array = image.img_to_array(img)
    expanded_img_array = np.expand_dims(img_array, axis=0)
    preprocessed_img = preprocess_input(expanded_img_array)
    result = model.predict(preprocessed_img).flatten()
    normalized_result = result / norm(result)

    return normalized_result

def recommend(features,feature_list):
    neighbors = NearestNeighbors(n_neighbors=6, algorithm='brute', metric='euclidean')
    neighbors.fit(feature_list)

    distances, indices = neighbors.kneighbors([features])
    print(distances,indices)

    


    return indices


def recommend_myntra(features,feature_list):
    neighbors = NearestNeighbors(n_neighbors=6, algorithm='brute', metric='euclidean')
    neighbors.fit(feature_list_myntra)

    distances, indices = neighbors.kneighbors([features])
    print(distances,indices)

    


    return indices

#

menu = ['FR','FRM','AB']
option = st.sidebar.selectbox("Select your model",menu)

if option=='FR':
    uploaded_file = st.file_uploader("Choose an image")
    if uploaded_file is not None:
        if save_uploaded_file(uploaded_file):
            display_image = Image.open(uploaded_file)
            st.image(display_image) 
            # feature extract
            features = feature_extraction(os.path.join("uploads",uploaded_file.name),model)
            # recommendention
            indices = recommend(features,feature_list)
            # show
            st.header("Recommend For You....")
            st.text("")
            col1,col2,col3,col4,col5 = st.columns(5)
            with col1:
                st.image(filenames[indices[0][1]])
            with col2:
                st.image(filenames[indices[0][2]])
            with col3:
                st.image(filenames[indices[0][3]])
            with col4:
                st.image(filenames[indices[0][4]])
            with col5:
                st.image(filenames[indices[0][5]])
        else:
            st.header("Some error occured in file upload")


elif option=='FRM':
    uploaded_file = st.file_uploader("Choose an image")
    if uploaded_file is not None:
        if save_uploaded_file(uploaded_file):
            display_image = Image.open(uploaded_file)
            st.image(display_image) 
            # feature extract
            features = feature_extraction(os.path.join("uploads",uploaded_file.name),model)
            # recommendention
            indices = recommend_myntra(features,feature_list)
            # show
            st.header("Recommend For You....")
            st.text("")
            col1,col2,col3,col4,col5 = st.columns(5)
            with col1:
                st.image(filenames_myntra[indices[0][1]])
            with col2:
                st.image(filenames_myntra[indices[0][2]])
            with col3:
                st.image(filenames_myntra[indices[0][3]])
            with col4:
                st.image(filenames_myntra[indices[0][4]])
            with col5:
                st.image(filenames_myntra[indices[0][5]])
        else:
            st.header("Some error occured in file upload")


elif option=="AB":
    st.markdown("FR: First Model Only Recommend Women Fashion Dresses...")
    st.markdown("FRM: Second Model Recommend Men Women include also footwears and clothes.")
    st.title("Product Recommendation Engine V-2.0")
    st.markdown("This Engine Developed by <a href='https://github.com/datamind321'>DataMind Platform</a>",unsafe_allow_html=True)
    st.subheader("if you have any query Contact us on : [email protected]") 
    st.markdown("More on : ")
    
    
    st.markdown("[![Linkedin](https://content.linkedin.com/content/dam/me/business/en-us/amp/brand-site/v2/bg/LI-Bug.svg.original.svg)](https://www.linkedin.com/in/rahul-rathour-402408231/)",unsafe_allow_html=True)
    

    st.markdown("[![Instagram](https://img.icons8.com/color/1x/instagram-new.png)](https://instagram.com/_technical__mind?igshid=YmMyMTA2M2Y=)")