Add files via upload

app.py

@@ -0,0 +1,55 @@
+import numpy as np
+import tensorflow
+
+from tensorflow.keras.preprocessing import image
+from tensorflow.keras.layers import GlobalMaxPooling2D
+from tensorflow.keras.applications.resnet50 import ResNet50,preprocess_input
+from numpy.linalg import norm
+import os
+from tqdm import tqdm
+import pickle
+
+model = ResNet50(weights="imagenet", include_top=False,input_shape=(224,224,3))
+model.trainable=False
+
+model1 = tensorflow.keras.Sequential([
+    model,
+    GlobalMaxPooling2D()
+])
+
+def  extract_features(img_path,model):
+    img=image.load_img(img_path,target_size = (224,224))
+    image_array = image.img_to_array(img)
+    expanded_image_array = np.expand_dims(image_array,axis=0)
+    processed_image = preprocess_input(expanded_image_array)
+    result = model.predict(processed_image).flatten()
+    normalized_result=result/norm(result)
+    return  normalized_result
+
+filenames =[]
+
+for file in os.listdir('set0'):
+    filenames.append(os.path.join('set0',file))
+
+for file in os.listdir('set1'):
+    filenames.append(os.path.join('set1',file))
+
+for file in os.listdir('set2'):
+    filenames.append(os.path.join('set2',file))
+
+for file in os.listdir('set3'):
+    filenames.append(os.path.join('set3',file))
+
+for file in os.listdir('set4'):
+    filenames.append(os.path.join('set4',file))
+
+feature_list = []
+
+for i in tqdm(filenames):
+    feature_list.append(extract_features(i,model1))
+
+print(np.array(feature_list).shape)
+
+import pickle
+pickle.dump(feature_list,open('embeddings2.pkl','wb'))
+pickle.dump(filenames,open('filenames2.pkl','wb'))

main.py

@@ -0,0 +1,74 @@
+import streamlit as st
+import os
+from PIL import Image
+import pickle
+import tensorflow
+import numpy as np
+from numpy.linalg import norm
+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
+
+feature_list = np.array(pickle.load(open('embeddings2.pkl', 'rb')))
+filenames = pickle.load(open('filenames2.pkl', 'rb'))
+
+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 extract_features(img_path, model):
+    img = image.load_img(img_path, target_size=(224, 224))
+    image_array = image.img_to_array(img)
+    expanded_image_array = np.expand_dims(image_array, axis=0)
+    processed_image = preprocess_input(expanded_image_array)
+    result = model.predict(processed_image).flatten()
+    normalized_result = result / norm(result)
+    return normalized_result
+
+def recommend(features,feature_list):
+    neighbors = NearestNeighbors(n_neighbors=5, algorithm='brute', metric='euclidean')
+    neighbors.fit(feature_list)
+
+    distances, indices = neighbors.kneighbors([features])
+    return indices
+
+
+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
+
+
+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)
+        features = extract_features(os.path.join("uploads",uploaded_file.name),model)
+        #st.text(features)
+        indices = recommend(features,feature_list)
+        col1,col2,col3,col4,col5 = st.columns(5)
+        with col1:
+            st.image(filenames[indices[0][0]])
+        with col2:
+            st.image(filenames[indices[0][1]])
+        with col3:
+            st.image(filenames[indices[0][2]])
+        with col4:
+            st.image(filenames[indices[0][3]])
+        with col5:
+            st.image(filenames[indices[0][4]])
+    else:
+        st.header("Some error has occured while uploading file")

test.py

@@ -0,0 +1,43 @@
+import pickle
+import tensorflow
+import numpy as np
+from numpy.linalg import norm
+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
+import cv2
+
+feature_list = np.array(pickle.load(open('embeddings.pkl','rb')))
+filenames = pickle.load(open('filenames.pkl','rb'))
+
+model = ResNet50(weights='imagenet',include_top=False,input_shape=(224,224,3))
+model.trainable = False
+
+model = tensorflow.keras.Sequential([
+    model,
+    GlobalMaxPooling2D()
+])
+
+img = image.load_img('sample/i4.jpg',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)
+
+neighbors = NearestNeighbors(n_neighbors=5,algorithm='brute',metric='euclidean')
+neighbors.fit(feature_list)
+
+distances,indices = neighbors.kneighbors([normalized_result])
+
+print(indices)
+
+for file in indices[0][0:5]:
+    temp_img = cv2.imread(filenames[file])
+    cv2.imshow('output',cv2.resize(temp_img,(512,512)))
+    cv2.waitKey(0)
+
+distances,indices = neighbors.kneighbors([normalized_result])
+
+print(indices)