Spaces:
Runtime error
Runtime error
sonuprasad
commited on
Commit
•
8085865
1
Parent(s):
e2b9b7e
Upload app.py with huggingface_hub
Browse files
app.py
CHANGED
@@ -1,76 +1,76 @@
|
|
1 |
-
from flask import Flask, request, jsonify, render_template, send_from_directory
|
2 |
-
from tensorflow.keras.models import load_model
|
3 |
-
from PIL import Image
|
4 |
-
import numpy as np
|
5 |
-
import os
|
6 |
-
|
7 |
-
app = Flask(__name__)
|
8 |
-
|
9 |
-
# Loading the trained model
|
10 |
-
try:
|
11 |
-
model = load_model('
|
12 |
-
except Exception as e:
|
13 |
-
print("Error loading the model:", e)
|
14 |
-
|
15 |
-
def detect_image(image_path):
|
16 |
-
try:
|
17 |
-
# Function to detect image
|
18 |
-
img = Image.open(image_path).resize((256, 256)) # Resizing image
|
19 |
-
img_array = np.array(img) / 255.0 # Normalizing pixel values
|
20 |
-
img_array = np.expand_dims(img_array, axis=0) # Adding batch dimension
|
21 |
-
|
22 |
-
prediction = model.predict(img_array)[0][0]
|
23 |
-
probability_real = prediction * 100 # Converting prediction to percentage
|
24 |
-
probability_ai = (1 - prediction) * 100
|
25 |
-
|
26 |
-
# Determine the final output
|
27 |
-
if probability_real > probability_ai:
|
28 |
-
result = 'Input Image is Real'
|
29 |
-
confidence = probability_real
|
30 |
-
else:
|
31 |
-
result = 'Input Image is AI Generated'
|
32 |
-
confidence = probability_ai
|
33 |
-
|
34 |
-
return result, confidence
|
35 |
-
except Exception as e:
|
36 |
-
print("Error detecting image:", e)
|
37 |
-
return "Error detecting image", 0
|
38 |
-
|
39 |
-
@app.route('/')
|
40 |
-
def index():
|
41 |
-
return render_template('home.html')
|
42 |
-
|
43 |
-
@app.route('/detect', methods=['POST'])
|
44 |
-
def detect():
|
45 |
-
try:
|
46 |
-
if 'file' not in request.files:
|
47 |
-
return jsonify({'error': 'No file provided'})
|
48 |
-
|
49 |
-
file = request.files['file']
|
50 |
-
if file.filename.split('.')[-1].lower() not in ['jpg', 'jpeg', 'png']:
|
51 |
-
return jsonify({'error': 'Unsupported file type. Please provide an image in JPG, JPEG, or PNG format.'})
|
52 |
-
|
53 |
-
file_path = 'DetectionImage/' + file.filename # Specifying the directory where images will be saved
|
54 |
-
file.save(file_path)
|
55 |
-
|
56 |
-
result, confidence = detect_image(file_path)
|
57 |
-
|
58 |
-
response = {
|
59 |
-
'result': result,
|
60 |
-
'confidence': confidence,
|
61 |
-
'image_path': file_path
|
62 |
-
}
|
63 |
-
|
64 |
-
return jsonify(response)
|
65 |
-
except Exception as e:
|
66 |
-
print("Error processing request:", e)
|
67 |
-
return jsonify({'error': 'Error processing request'})
|
68 |
-
|
69 |
-
@app.route('/DetectionImage/<path:filename>')
|
70 |
-
def serve_image(filename):
|
71 |
-
return send_from_directory('DetectionImage', filename)
|
72 |
-
|
73 |
-
if __name__ == '__main__':
|
74 |
-
if not os.path.exists('DetectionImage'):
|
75 |
-
os.makedirs('DetectionImage')
|
76 |
-
app.run(debug=True)
|
|
|
1 |
+
from flask import Flask, request, jsonify, render_template, send_from_directory
|
2 |
+
from tensorflow.keras.models import load_model
|
3 |
+
from PIL import Image
|
4 |
+
import numpy as np
|
5 |
+
import os
|
6 |
+
|
7 |
+
app = Flask(__name__)
|
8 |
+
|
9 |
+
# Loading the trained model
|
10 |
+
try:
|
11 |
+
model = load_model('model.h5') # Replacing with the path to your saved model
|
12 |
+
except Exception as e:
|
13 |
+
print("Error loading the model:", e)
|
14 |
+
|
15 |
+
def detect_image(image_path):
|
16 |
+
try:
|
17 |
+
# Function to detect image
|
18 |
+
img = Image.open(image_path).resize((256, 256)) # Resizing image
|
19 |
+
img_array = np.array(img) / 255.0 # Normalizing pixel values
|
20 |
+
img_array = np.expand_dims(img_array, axis=0) # Adding batch dimension
|
21 |
+
|
22 |
+
prediction = model.predict(img_array)[0][0]
|
23 |
+
probability_real = prediction * 100 # Converting prediction to percentage
|
24 |
+
probability_ai = (1 - prediction) * 100
|
25 |
+
|
26 |
+
# Determine the final output
|
27 |
+
if probability_real > probability_ai:
|
28 |
+
result = 'Input Image is Real'
|
29 |
+
confidence = probability_real
|
30 |
+
else:
|
31 |
+
result = 'Input Image is AI Generated'
|
32 |
+
confidence = probability_ai
|
33 |
+
|
34 |
+
return result, confidence
|
35 |
+
except Exception as e:
|
36 |
+
print("Error detecting image:", e)
|
37 |
+
return "Error detecting image", 0
|
38 |
+
|
39 |
+
@app.route('/')
|
40 |
+
def index():
|
41 |
+
return render_template('home.html')
|
42 |
+
|
43 |
+
@app.route('/detect', methods=['POST'])
|
44 |
+
def detect():
|
45 |
+
try:
|
46 |
+
if 'file' not in request.files:
|
47 |
+
return jsonify({'error': 'No file provided'})
|
48 |
+
|
49 |
+
file = request.files['file']
|
50 |
+
if file.filename.split('.')[-1].lower() not in ['jpg', 'jpeg', 'png']:
|
51 |
+
return jsonify({'error': 'Unsupported file type. Please provide an image in JPG, JPEG, or PNG format.'})
|
52 |
+
|
53 |
+
file_path = 'DetectionImage/' + file.filename # Specifying the directory where images will be saved
|
54 |
+
file.save(file_path)
|
55 |
+
|
56 |
+
result, confidence = detect_image(file_path)
|
57 |
+
|
58 |
+
response = {
|
59 |
+
'result': result,
|
60 |
+
'confidence': confidence,
|
61 |
+
'image_path': file_path
|
62 |
+
}
|
63 |
+
|
64 |
+
return jsonify(response)
|
65 |
+
except Exception as e:
|
66 |
+
print("Error processing request:", e)
|
67 |
+
return jsonify({'error': 'Error processing request'})
|
68 |
+
|
69 |
+
@app.route('/DetectionImage/<path:filename>')
|
70 |
+
def serve_image(filename):
|
71 |
+
return send_from_directory('DetectionImage', filename)
|
72 |
+
|
73 |
+
if __name__ == '__main__':
|
74 |
+
if not os.path.exists('DetectionImage'):
|
75 |
+
os.makedirs('DetectionImage')
|
76 |
+
app.run(debug=True)
|