Skip to content

Commit d136a78

Browse files
jayanttikmanijayanttikmani
committed
Initial Commit
1 parent bb8ee37 commit d136a78

20 files changed

+87552
-0
lines changed

‎ConvolutionalNeuralNetworksUsing-TensorFlow_Keras.ipynb

+165
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,165 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {},
6+
"source": [
7+
"#### Convolutional Neural Networks Using - TensorFlow, Theano, Keras"
8+
]
9+
},
10+
{
11+
"cell_type": "code",
12+
"execution_count": 1,
13+
"metadata": {
14+
"collapsed": true
15+
},
16+
"outputs": [],
17+
"source": [
18+
"# Convolutional Neural Network\n",
19+
"\n",
20+
"# Installing Theano\n",
21+
"# pip install --upgrade --no-deps git+git://github.com/Theano/Theano.git\n",
22+
"\n",
23+
"# Installing Tensorflow\n",
24+
"# Install Tensorflow from the website: https://www.tensorflow.org/versions/r0.12/get_started/os_setup.html\n",
25+
"\n",
26+
"# Installing Keras\n",
27+
"# pip install --upgrade keras"
28+
]
29+
},
30+
{
31+
"cell_type": "markdown",
32+
"metadata": {},
33+
"source": [
34+
"#### Dataset Problem Statement - It is an image classification problem where the dataset consists of images for dogs and cats. We will train a convolutional neural network to predict if an image is a photo of a dog or a cat. Even though classifying cats and dogs isn't very important, the primary goal is to build a model, which can later be used for any important image classification problem (ex. medical imaging, tumor detection)"
35+
]
36+
},
37+
{
38+
"cell_type": "code",
39+
"execution_count": 2,
40+
"metadata": {},
41+
"outputs": [
42+
{
43+
"name": "stderr",
44+
"output_type": "stream",
45+
"text": [
46+
"Using TensorFlow backend.\n"
47+
]
48+
}
49+
],
50+
"source": [
51+
"# Part 1 - Building the CNN\n",
52+
"\n",
53+
"# Importing the Keras libraries and packages\n",
54+
"from keras.models import Sequential\n",
55+
"from keras.layers import Convolution2D\n",
56+
"from keras.layers import MaxPooling2D\n",
57+
"from keras.layers import Flatten\n",
58+
"from keras.layers import Dense"
59+
]
60+
},
61+
{
62+
"cell_type": "code",
63+
"execution_count": 3,
64+
"metadata": {},
65+
"outputs": [
66+
{
67+
"name": "stderr",
68+
"output_type": "stream",
69+
"text": [
70+
"C:\\Users\\Jayant\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:5: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (3, 3), input_shape=(64, 64, 3..., activation=\"relu\")`\n",
71+
" \"\"\"\n",
72+
"C:\\Users\\Jayant\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:11: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (3, 3), activation=\"relu\")`\n",
73+
" # This is added back by InteractiveShellApp.init_path()\n",
74+
"C:\\Users\\Jayant\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:18: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(activation=\"relu\", units=128)`\n",
75+
"C:\\Users\\Jayant\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:19: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(activation=\"sigmoid\", units=1)`\n"
76+
]
77+
}
78+
],
79+
"source": [
80+
"# Initialising the CNN\n",
81+
"classifier = Sequential()\n",
82+
"\n",
83+
"# Step 1 - Convolution\n",
84+
"classifier.add(Convolution2D(32, 3, 3, input_shape = (64, 64, 3), activation = 'relu'))\n",
85+
"\n",
86+
"# Step 2 - Pooling\n",
87+
"classifier.add(MaxPooling2D(pool_size = (2, 2)))\n",
88+
"\n",
89+
"# Adding a second convolutional layer\n",
90+
"classifier.add(Convolution2D(32, 3, 3, activation = 'relu'))\n",
91+
"classifier.add(MaxPooling2D(pool_size = (2, 2)))\n",
92+
"\n",
93+
"# Step 3 - Flattening\n",
94+
"classifier.add(Flatten())\n",
95+
"\n",
96+
"# Step 4 - Full connection\n",
97+
"classifier.add(Dense(output_dim = 128, activation = 'relu'))\n",
98+
"classifier.add(Dense(output_dim = 1, activation = 'sigmoid'))\n",
99+
"\n",
100+
"# Compiling the CNN\n",
101+
"classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])"
102+
]
103+
},
104+
{
105+
"cell_type": "code",
106+
"execution_count": null,
107+
"metadata": {
108+
"collapsed": true
109+
},
110+
"outputs": [],
111+
"source": [
112+
"# Part 2 - Fitting the CNN to the images\n",
113+
"\n",
114+
"from keras.preprocessing.image import ImageDataGenerator\n",
115+
"\n",
116+
"train_datagen = ImageDataGenerator(rescale = 1./255,\n",
117+
" shear_range = 0.2,\n",
118+
" zoom_range = 0.2,\n",
119+
" horizontal_flip = True)\n",
120+
"\n",
121+
"test_datagen = ImageDataGenerator(rescale = 1./255)"
122+
]
123+
},
124+
{
125+
"cell_type": "code",
126+
"execution_count": null,
127+
"metadata": {
128+
"collapsed": true
129+
},
130+
"outputs": [],
131+
"source": [
132+
"training_set = train_datagen.flow_from_directory('dataset/training_set',\n",
133+
" target_size = (64, 64),\n",
134+
" batch_size = 32,\n",
135+
" class_mode = 'binary')\n",
136+
"\n",
137+
"test_set = test_datagen.flow_from_directory('dataset/test_set',\n",
138+
" target_size = (64, 64),\n",
139+
" batch_size = 32,\n",
140+
" class_mode = 'binary')"
141+
]
142+
}
143+
],
144+
"metadata": {
145+
"kernelspec": {
146+
"display_name": "Python 3",
147+
"language": "python",
148+
"name": "python3"
149+
},
150+
"language_info": {
151+
"codemirror_mode": {
152+
"name": "ipython",
153+
"version": 3
154+
},
155+
"file_extension": ".py",
156+
"mimetype": "text/x-python",
157+
"name": "python",
158+
"nbconvert_exporter": "python",
159+
"pygments_lexer": "ipython3",
160+
"version": "3.6.1"
161+
}
162+
},
163+
"nbformat": 4,
164+
"nbformat_minor": 2
165+
}

0 commit comments

Comments
 (0)