File size: 4,622 Bytes
6a4d9dc
 
 
 
 
 
 
 
 
 
 
61e280c
6a4d9dc
 
 
 
 
6ef5a6e
6a4d9dc
 
 
 
 
 
 
61e280c
6a4d9dc
 
 
 
 
 
 
61e280c
6a4d9dc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2d4593d
 
 
 
 
 
 
 
 
6a4d9dc
61e280c
 
98d3e8a
 
 
 
61e280c
 
 
 
98d3e8a
6a4d9dc
61e280c
6a4d9dc
61e280c
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
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
import os
import requests
from tqdm import tqdm
from datasets import load_dataset
import numpy as np
from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.preprocessing import image
from sklearn.neighbors import NearestNeighbors
import joblib
from PIL import UnidentifiedImageError, Image
import matplotlib.pyplot as plt
import gradio as gr

# Load the dataset
dataset = load_dataset("thefcraft/civitai-stable-diffusion-337k")

# Take a subset of the dataset
subset_size = 50
dataset_subset = dataset['train'].shuffle(seed=42).select(range(subset_size))

# Directory to save images
image_dir = 'civitai_images'
os.makedirs(image_dir, exist_ok=True)

# Load the ResNet50 model pretrained on ImageNet
model = ResNet50(weights='imagenet', include_top=False, pooling='avg')

# Function to extract features
def extract_features(img_path, model):
    img = image.load_img(img_path, target_size=(224, 224))
    img_array = image.img_to_array(img)
    img_array = np.expand_dims(img_array, axis=0)
    img_array = preprocess_input(img_array)
    features = model.predict(img_array)
    return features.flatten()

# Extract features for a sample of images
features = []
image_paths = []
model_names = []

for sample in tqdm(dataset_subset):
    img_url = sample['url']  # Adjust based on the correct column name
    model_name = sample['Model']  # Adjust based on the correct column name
    img_path = os.path.join(image_dir, os.path.basename(img_url))

    # Download the image
    try:
        response = requests.get(img_url)
        response.raise_for_status()  # Check if the download was successful

        if 'image' not in response.headers['Content-Type']:
            raise ValueError("URL does not contain an image")

        with open(img_path, 'wb') as f:
            f.write(response.content)

        # Extract features
        try:
            img_features = extract_features(img_path, model)
            features.append(img_features)
            image_paths.append(img_path)
            model_names.append(model_name)
        except UnidentifiedImageError:
            print(f"UnidentifiedImageError: Skipping file {img_path}")
            os.remove(img_path)

    except requests.exceptions.RequestException as e:
        print(f"RequestException: Failed to download {img_url} - {e}")

# Convert features to numpy array
features = np.array(features)

# Build the NearestNeighbors model
nbrs = NearestNeighbors(n_neighbors=5, algorithm='ball_tree').fit(features)

# Save the model and features
joblib.dump(nbrs, 'nearest_neighbors_model.pkl')
np.save('image_features.npy', features)
np.save('image_paths.npy', image_paths)
np.save('model_names.npy', model_names)

# Load the NearestNeighbors model and features
nbrs = joblib.load('nearest_neighbors_model.pkl')
features = np.load('image_features.npy')
image_paths = np.load('image_paths.npy', allow_pickle=True)
model_names = np.load('model_names.npy', allow_pickle=True)

# Function to get recommendations
def get_recommendations(img_path, model, nbrs, image_paths, model_names, n_neighbors=5):
    img_features = extract_features(img_path, model)
    distances, indices = nbrs.kneighbors([img_features])

    recommended_images = [image_paths[idx] for idx in indices.flatten()]
    recommended_model_names = [model_names[idx] for idx in indices.flatten()]
    recommended_distances = distances.flatten()

    return recommended_images, recommended_model_names, recommended_distances

def display_images(image_paths, model_names, distances):
    plt.figure(figsize=(20, 10))
    for i, (img_path, model_name, distance) in enumerate(zip(image_paths, model_names, distances)):
        img = Image.open(img_path)
        plt.subplot(1, len(image_paths), i+1)
        plt.imshow(img)
        plt.title(f'{model_name}\nDistance: {distance:.2f}', fontsize=12)
        plt.axis('off')
    plt.show()

def recommend_images(img):
  recommended_images, recommended_model_names, recommended_distances = get_recommendations(img, model, nbrs, image_paths, model_names)
  recommendations = []
  for i in range(len(recommended_images)):
    recommendations.append(f"Rekomendasi {i+1}:\nGambar: {Image.open(recommended_images[i])}\nModel: {recommended_model_names[i]}\nEuclidian Distance: {recommended_distances[i]:.2f}")
  return recommendations

iface = gr.Interface(
    fn=recommend_images,
    inputs=gr.Image(label="Upload an image"),
    outputs=gr.Textbox(label="Rekomendasi", lines=10),
    title="Image Recommendation System",
    description="Upload an image and get recommendations based on similarity."
)
iface.launch()