Create app.py

app.py

@@ -0,0 +1,64 @@
+import streamlit as s
+from transformers import AutoTokenizer, TFAutoModelForSequenceClassification, pipeline
+
+!wget http://vis-www.cs.umass.edu/lfw/lfw.tgz
+!tar -xvf /content/lfw.tgz
+
+!pip install tensorflow
+!pip install tqdm
+
+import os
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.applications import ResNet50
+from tensorflow.keras.applications.resnet import preprocess_input
+from tensorflow.keras.preprocessing import image
+from PIL import Image
+from tqdm import tqdm
+
+resnet50_model = ResNet50(weights='imagenet', include_top=False, pooling='avg')
+
+def get_image_features(img_path):
+    loaded_img = image.load_img(img_path, target_size=(224, 224))
+    img_array = image.img_to_array(loaded_img)
+    expanded_array = np.expand_dims(img_array, axis=0)
+    preprocessed_img = preprocess_input(expanded_array)
+    features = resnet50_model.predict(preprocessed_img)
+    return features.flatten()
+
+extracted_features = {}
+
+lfw_dir = '/content/lfw'
+all_files = []
+
+for root_dir, subdir_list, file_list in os.walk(lfw_dir):
+    for file_name in file_list:
+        if file_name.endswith('.jpg'):
+            img_path = os.path.join(root_dir, file_name)
+            all_files.append(img_path)
+
+for file_path in tqdm(all_files, desc="Processing images"):
+    img_features = get_image_features(file_path)
+    file_name = os.path.basename(file_path)
+    extracted_features[file_name] = img_features
+
+from sklearn.neighbors import NearestNeighbors
+
+def find_similar_images(target_image, feature_dictionary, num_neighbors=10):
+    img_names = list(feature_dictionary.keys())
+    features_list = np.array([feature_dictionary[name] for name in img_names])
+    neighbors_model = NearestNeighbors(n_neighbors=num_neighbors, algorithm='auto', metric='euclidean')
+    neighbors_model.fit(features_list)
+    target_image_feature = feature_dictionary[target_image].reshape(1, -1)
+    _, img_indices = neighbors_model.kneighbors(target_image_feature)
+    retrieved_images = [img_names[index] for index in img_indices.flatten()]
+    return retrieved_images
+
+query_img = 'Francis_Ricciardone_0001.jpg'
+similar_imgs = find_similar_images(query_img, extracted_features, num_neighbors=11)
+
+print(f"Images similar to {query_img}:")
+for count, img_name in enumerate(similar_imgs[1:], start=1):
+    print(f"{count}: {img_name}")
+
+