nisharg nargund
commited on
Commit
•
378363a
1
Parent(s):
08b991c
Upload 4 files
Browse files- app.py +44 -0
- bone.ipynb +294 -0
- bone_frac.zip +3 -0
- bone_model.h5 +3 -0
app.py
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
from flask import Flask, request, render_template
|
3 |
+
from tensorflow.keras.models import load_model
|
4 |
+
from tensorflow.keras.preprocessing import image
|
5 |
+
import numpy as np
|
6 |
+
|
7 |
+
app = Flask(__name__)
|
8 |
+
|
9 |
+
# Load the trained model
|
10 |
+
model = load_model('bone_fracture/bone_model.h5') # Update with your model's file path
|
11 |
+
|
12 |
+
# Define class labels
|
13 |
+
class_labels = ['Not Fractured', 'Fractured']
|
14 |
+
|
15 |
+
@app.route('/', methods=['GET', 'POST'])
|
16 |
+
def index():
|
17 |
+
if request.method == 'POST':
|
18 |
+
# Get the uploaded file from the form
|
19 |
+
file = request.files['file']
|
20 |
+
if file:
|
21 |
+
# Save the file temporarily
|
22 |
+
temp_path = 'temp.jpg'
|
23 |
+
file.save(temp_path)
|
24 |
+
|
25 |
+
# Load and preprocess the image
|
26 |
+
img = image.load_img(temp_path, target_size=(224, 224))
|
27 |
+
img_array = image.img_to_array(img)
|
28 |
+
img_array = np.expand_dims(img_array, axis=0)
|
29 |
+
img_array /= 255.0
|
30 |
+
|
31 |
+
# Make a prediction
|
32 |
+
prediction = model.predict(img_array)
|
33 |
+
predicted_class = int(np.round(prediction)[0][0])
|
34 |
+
predicted_label = class_labels[predicted_class]
|
35 |
+
|
36 |
+
# Delete the temporary file
|
37 |
+
os.remove(temp_path)
|
38 |
+
|
39 |
+
return render_template('result.html', prediction=predicted_label)
|
40 |
+
|
41 |
+
return render_template('index.html')
|
42 |
+
|
43 |
+
if __name__ == '__main__':
|
44 |
+
app.run(debug=True)
|
bone.ipynb
ADDED
@@ -0,0 +1,294 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 13,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [],
|
8 |
+
"source": [
|
9 |
+
"import tensorflow as tf\n",
|
10 |
+
"from tensorflow import keras\n",
|
11 |
+
"from keras.layers import Conv2D,MaxPooling2D,Dense,Flatten,Dropout\n",
|
12 |
+
"from keras import Sequential\n",
|
13 |
+
"import numpy as np\n",
|
14 |
+
"import pandas as pd\n",
|
15 |
+
"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
|
16 |
+
"from tensorflow.keras.preprocessing import image"
|
17 |
+
]
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"cell_type": "code",
|
21 |
+
"execution_count": 2,
|
22 |
+
"metadata": {},
|
23 |
+
"outputs": [
|
24 |
+
{
|
25 |
+
"name": "stdout",
|
26 |
+
"output_type": "stream",
|
27 |
+
"text": [
|
28 |
+
"Zip file extracted successfully.\n"
|
29 |
+
]
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"source": [
|
33 |
+
"from zipfile import ZipFile\n",
|
34 |
+
"\n",
|
35 |
+
"zip_file_path = 'bone_frac.zip'\n",
|
36 |
+
"\n",
|
37 |
+
"with ZipFile(zip_file_path, 'r') as zip_ref:\n",
|
38 |
+
" zip_ref.extractall()\n",
|
39 |
+
"\n",
|
40 |
+
"print(\"Zip file extracted successfully.\")\n"
|
41 |
+
]
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"cell_type": "code",
|
45 |
+
"execution_count": 3,
|
46 |
+
"metadata": {},
|
47 |
+
"outputs": [],
|
48 |
+
"source": [
|
49 |
+
"Training = 'archive (6)/train'\n",
|
50 |
+
"Validation = 'archive (6)/val'"
|
51 |
+
]
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"cell_type": "code",
|
55 |
+
"execution_count": 4,
|
56 |
+
"metadata": {},
|
57 |
+
"outputs": [],
|
58 |
+
"source": [
|
59 |
+
"img_width, img_height = 224, 224\n",
|
60 |
+
"batch_size = 32"
|
61 |
+
]
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"cell_type": "code",
|
65 |
+
"execution_count": 7,
|
66 |
+
"metadata": {},
|
67 |
+
"outputs": [
|
68 |
+
{
|
69 |
+
"name": "stdout",
|
70 |
+
"output_type": "stream",
|
71 |
+
"text": [
|
72 |
+
"Found 8863 images belonging to 2 classes.\n",
|
73 |
+
"Found 600 images belonging to 2 classes.\n"
|
74 |
+
]
|
75 |
+
}
|
76 |
+
],
|
77 |
+
"source": [
|
78 |
+
"#Data Augmentation\n",
|
79 |
+
"\n",
|
80 |
+
"train_datagen = ImageDataGenerator(\n",
|
81 |
+
" rescale=1.0/255,\n",
|
82 |
+
" rotation_range=20,\n",
|
83 |
+
" width_shift_range=0.2,\n",
|
84 |
+
" height_shift_range=0.2,\n",
|
85 |
+
" shear_range=0.2,\n",
|
86 |
+
" zoom_range=0.2,\n",
|
87 |
+
" horizontal_flip=True,\n",
|
88 |
+
" fill_mode='nearest'\n",
|
89 |
+
")\n",
|
90 |
+
"\n",
|
91 |
+
"#Rescale validation images \n",
|
92 |
+
"validation_datagen = ImageDataGenerator(rescale=1.0/255)\n",
|
93 |
+
"\n",
|
94 |
+
"#loading train n val data:\n",
|
95 |
+
"\n",
|
96 |
+
"train_generator = train_datagen.flow_from_directory(\n",
|
97 |
+
" Training,\n",
|
98 |
+
" target_size=(img_width, img_height),\n",
|
99 |
+
" batch_size=batch_size,\n",
|
100 |
+
" class_mode='binary'\n",
|
101 |
+
")\n",
|
102 |
+
"\n",
|
103 |
+
"validation_generator = validation_datagen.flow_from_directory(\n",
|
104 |
+
" Validation,\n",
|
105 |
+
" target_size=(img_width, img_height),\n",
|
106 |
+
" batch_size=batch_size,\n",
|
107 |
+
" class_mode='binary'\n",
|
108 |
+
")"
|
109 |
+
]
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"cell_type": "code",
|
113 |
+
"execution_count": 8,
|
114 |
+
"metadata": {},
|
115 |
+
"outputs": [],
|
116 |
+
"source": [
|
117 |
+
"#building CNN model\n",
|
118 |
+
"\n",
|
119 |
+
"model = Sequential()\n",
|
120 |
+
"\n",
|
121 |
+
"model.add(Conv2D(32, (3,3), activation='relu', input_shape=(img_width, img_height, 3)))\n",
|
122 |
+
"model.add(MaxPooling2D((2,2)))\n",
|
123 |
+
"\n",
|
124 |
+
"model.add(Conv2D(64, (3,3), activation='relu'))\n",
|
125 |
+
"model.add(MaxPooling2D((2,2)))\n",
|
126 |
+
"\n",
|
127 |
+
"model.add(Conv2D(128, (3,3), activation='relu'))\n",
|
128 |
+
"model.add(MaxPooling2D((2,2)))\n",
|
129 |
+
"\n",
|
130 |
+
"model.add(Flatten())\n",
|
131 |
+
"\n",
|
132 |
+
"model.add(Dense(128, activation='relu'))\n",
|
133 |
+
"model.add(Dropout(0.5))\n",
|
134 |
+
"\n",
|
135 |
+
"model.add(Dense(1, activation='sigmoid'))\n",
|
136 |
+
"\n"
|
137 |
+
]
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"cell_type": "code",
|
141 |
+
"execution_count": 9,
|
142 |
+
"metadata": {},
|
143 |
+
"outputs": [],
|
144 |
+
"source": [
|
145 |
+
"model.compile(optimizer='Adam', loss='binary_crossentropy', metrics=['accuracy'])"
|
146 |
+
]
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"cell_type": "code",
|
150 |
+
"execution_count": 11,
|
151 |
+
"metadata": {},
|
152 |
+
"outputs": [
|
153 |
+
{
|
154 |
+
"name": "stdout",
|
155 |
+
"output_type": "stream",
|
156 |
+
"text": [
|
157 |
+
"Epoch 1/5\n",
|
158 |
+
"276/276 [==============================] - 450s 2s/step - loss: 0.6812 - accuracy: 0.5570 - val_loss: 0.6559 - val_accuracy: 0.5533\n",
|
159 |
+
"Epoch 2/5\n",
|
160 |
+
"276/276 [==============================] - 457s 2s/step - loss: 0.6691 - accuracy: 0.5919 - val_loss: 0.6212 - val_accuracy: 0.6000\n",
|
161 |
+
"Epoch 3/5\n",
|
162 |
+
"276/276 [==============================] - 301s 1s/step - loss: 0.6513 - accuracy: 0.5942 - val_loss: 0.5682 - val_accuracy: 0.6800\n",
|
163 |
+
"Epoch 4/5\n",
|
164 |
+
"276/276 [==============================] - 302s 1s/step - loss: 0.6283 - accuracy: 0.6159 - val_loss: 0.6609 - val_accuracy: 0.5000\n",
|
165 |
+
"Epoch 5/5\n",
|
166 |
+
"276/276 [==============================] - 303s 1s/step - loss: 0.6163 - accuracy: 0.6440 - val_loss: 0.5883 - val_accuracy: 0.6767\n"
|
167 |
+
]
|
168 |
+
}
|
169 |
+
],
|
170 |
+
"source": [
|
171 |
+
"history = model.fit(\n",
|
172 |
+
" train_generator,\n",
|
173 |
+
" steps_per_epoch=train_generator.samples / batch_size,\n",
|
174 |
+
" validation_data=validation_generator,\n",
|
175 |
+
" validation_steps=(validation_generator.samples / batch_size),\n",
|
176 |
+
" epochs=5)"
|
177 |
+
]
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"cell_type": "code",
|
181 |
+
"execution_count": 12,
|
182 |
+
"metadata": {},
|
183 |
+
"outputs": [
|
184 |
+
{
|
185 |
+
"name": "stdout",
|
186 |
+
"output_type": "stream",
|
187 |
+
"text": [
|
188 |
+
"19/19 [==============================] - 4s 203ms/step - loss: 0.5883 - accuracy: 0.6767\n",
|
189 |
+
"Test accuracy: 67.67%\n"
|
190 |
+
]
|
191 |
+
}
|
192 |
+
],
|
193 |
+
"source": [
|
194 |
+
"test_loss, test_acc = model.evaluate(validation_generator)\n",
|
195 |
+
"print(f'Test accuracy: {test_acc * 100: .2f}%') #.2f means float no. upto 2 decimals"
|
196 |
+
]
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"cell_type": "code",
|
200 |
+
"execution_count": 14,
|
201 |
+
"metadata": {},
|
202 |
+
"outputs": [],
|
203 |
+
"source": [
|
204 |
+
"model.save('bone_model.h5')"
|
205 |
+
]
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"cell_type": "code",
|
209 |
+
"execution_count": 30,
|
210 |
+
"metadata": {},
|
211 |
+
"outputs": [],
|
212 |
+
"source": [
|
213 |
+
"model = tf.keras.models.load_model('bone_model.h5')\n",
|
214 |
+
"\n",
|
215 |
+
"img_path = 'archive (6)/val/fractured\\9.jpg'\n",
|
216 |
+
"img = image.load_img(img_path, target_size=(224,224))\n",
|
217 |
+
"img_array = image.img_to_array(img)\n",
|
218 |
+
"img_array = np.expand_dims(img_array, axis=0)\n",
|
219 |
+
"img_array /= 255.0"
|
220 |
+
]
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"cell_type": "code",
|
224 |
+
"execution_count": 31,
|
225 |
+
"metadata": {},
|
226 |
+
"outputs": [
|
227 |
+
{
|
228 |
+
"name": "stdout",
|
229 |
+
"output_type": "stream",
|
230 |
+
"text": [
|
231 |
+
"1/1 [==============================] - 0s 76ms/step\n"
|
232 |
+
]
|
233 |
+
}
|
234 |
+
],
|
235 |
+
"source": [
|
236 |
+
"#making prediction\n",
|
237 |
+
"\n",
|
238 |
+
"prediction = model.predict(img_array)\n",
|
239 |
+
"predicted_class=int(np.round(prediction)[0][0]) #[0][0]\n",
|
240 |
+
"\n",
|
241 |
+
"class_labels = ['Not Fractured', 'Fractured']\n",
|
242 |
+
"\n",
|
243 |
+
"\n",
|
244 |
+
"\n"
|
245 |
+
]
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"cell_type": "code",
|
249 |
+
"execution_count": 35,
|
250 |
+
"metadata": {},
|
251 |
+
"outputs": [
|
252 |
+
{
|
253 |
+
"name": "stdout",
|
254 |
+
"output_type": "stream",
|
255 |
+
"text": [
|
256 |
+
"Predicted class: Fractured (Confidence: 57.78%)\n"
|
257 |
+
]
|
258 |
+
}
|
259 |
+
],
|
260 |
+
"source": [
|
261 |
+
"print(f\"Predicted class: {class_labels[predicted_class]} (Confidence: {prediction[0][0] * 100:.2f}%)\")"
|
262 |
+
]
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"cell_type": "code",
|
266 |
+
"execution_count": null,
|
267 |
+
"metadata": {},
|
268 |
+
"outputs": [],
|
269 |
+
"source": []
|
270 |
+
}
|
271 |
+
],
|
272 |
+
"metadata": {
|
273 |
+
"kernelspec": {
|
274 |
+
"display_name": "Python 3",
|
275 |
+
"language": "python",
|
276 |
+
"name": "python3"
|
277 |
+
},
|
278 |
+
"language_info": {
|
279 |
+
"codemirror_mode": {
|
280 |
+
"name": "ipython",
|
281 |
+
"version": 3
|
282 |
+
},
|
283 |
+
"file_extension": ".py",
|
284 |
+
"mimetype": "text/x-python",
|
285 |
+
"name": "python",
|
286 |
+
"nbconvert_exporter": "python",
|
287 |
+
"pygments_lexer": "ipython3",
|
288 |
+
"version": "3.10.7"
|
289 |
+
},
|
290 |
+
"orig_nbformat": 4
|
291 |
+
},
|
292 |
+
"nbformat": 4,
|
293 |
+
"nbformat_minor": 2
|
294 |
+
}
|
bone_frac.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3904d875f3e408293142724a4150819c0b6fce1da77d70211dfae9b780c859f
|
3 |
+
size 180678817
|
bone_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81fbc842860855112b3ea1eaacb1d46f0062956637377056d35b592b76df1541
|
3 |
+
size 134080488
|