Skip to content

Commit b986b8a

Browse files
beachdwellerbeachdweller
committed
Merge branch 'keras-example'
2 parents a362166 + e6f6175 commit b986b8a

File tree

2 files changed

+654
-0
lines changed

2 files changed

+654
-0
lines changed

‎15_optimization/035_colab_mnist_keras_example.ipynb‎

Lines changed: 316 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,316 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {
6+
"id": "view-in-github",
7+
"colab_type": "text"
8+
},
9+
"source": [
10+
"<a href=\"https://colab.research.google.com/github/kangwonlee/nmisp/blob/main/15_optimization/035_colab_mnist_keras_example.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n"
11+
]
12+
},
13+
{
14+
"cell_type": "markdown",
15+
"metadata": {},
16+
"source": [
17+
"## 2.1 A first look at a neural network\n",
18+
"\n",
19+
"* from : F. Chollet, Deep Learning with Python, ISBN 9781617294433, 2017\n",
20+
"* https://github.com/fchollet/deep-learning-with-python-notebooks\n",
21+
"* https://www.manning.com/books/deep-learning-with-python\n",
22+
"\n"
23+
]
24+
},
25+
{
26+
"cell_type": "code",
27+
"execution_count": null,
28+
"metadata": {},
29+
"outputs": [],
30+
"source": [
31+
"import os\n",
32+
"import pathlib\n",
33+
"\n",
34+
"import numpy as np\n",
35+
"import pandas as pd\n",
36+
"import tensorflow as tf\n",
37+
"\n"
38+
]
39+
},
40+
{
41+
"cell_type": "markdown",
42+
"metadata": {},
43+
"source": [
44+
"### Listing 2.1 Loading the MNIST dataset in Keras\n",
45+
"\n"
46+
]
47+
},
48+
{
49+
"cell_type": "code",
50+
"execution_count": null,
51+
"metadata": {},
52+
"outputs": [],
53+
"source": [
54+
"try:\n",
55+
" data_folder = pathlib.Path('sample_data')\n",
56+
" assert data_folder.exists()\n",
57+
" assert data_folder.is_dir()\n",
58+
"\n",
59+
" def read_data(data_path):\n",
60+
" df = pd.read_csv(\n",
61+
" data_path,\n",
62+
" header=None\n",
63+
" )\n",
64+
" labels = np.array(df.iloc[:, 0])\n",
65+
" images = np.array(df.iloc[:, 1:])\n",
66+
"\n",
67+
" return images, labels\n",
68+
"\n",
69+
"\n",
70+
" train_images, train_labels = read_data(data_folder / 'mnist_train_small.csv')\n",
71+
" test_images, test_labels = read_data(data_folder / 'mnist_test.csv')\n",
72+
"\n",
73+
"except AssertionError:\n",
74+
" (train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data()\n",
75+
"\n"
76+
]
77+
},
78+
{
79+
"cell_type": "markdown",
80+
"metadata": {},
81+
"source": [
82+
"### Listing 2.2 The training data\n"
83+
]
84+
},
85+
{
86+
"cell_type": "code",
87+
"execution_count": null,
88+
"metadata": {},
89+
"outputs": [],
90+
"source": [
91+
"train_images.shape\n",
92+
"\n"
93+
]
94+
},
95+
{
96+
"cell_type": "code",
97+
"execution_count": null,
98+
"metadata": {},
99+
"outputs": [],
100+
"source": [
101+
"n_train = len(train_labels)\n",
102+
"\n"
103+
]
104+
},
105+
{
106+
"cell_type": "code",
107+
"execution_count": null,
108+
"metadata": {},
109+
"outputs": [],
110+
"source": [
111+
"train_labels\n",
112+
"\n"
113+
]
114+
},
115+
{
116+
"cell_type": "markdown",
117+
"metadata": {},
118+
"source": [
119+
"### Listing 2.3 The test data\n"
120+
]
121+
},
122+
{
123+
"cell_type": "code",
124+
"execution_count": null,
125+
"metadata": {},
126+
"outputs": [],
127+
"source": [
128+
"test_images.shape\n"
129+
]
130+
},
131+
{
132+
"cell_type": "code",
133+
"execution_count": null,
134+
"metadata": {},
135+
"outputs": [],
136+
"source": [
137+
"n_test = len(test_labels)\n",
138+
"\n"
139+
]
140+
},
141+
{
142+
"cell_type": "code",
143+
"execution_count": null,
144+
"metadata": {},
145+
"outputs": [],
146+
"source": [
147+
"test_labels\n"
148+
]
149+
},
150+
{
151+
"cell_type": "markdown",
152+
"metadata": {},
153+
"source": [
154+
"### Listing 2.4 The network architecture\n",
155+
"\n"
156+
]
157+
},
158+
{
159+
"cell_type": "code",
160+
"execution_count": null,
161+
"metadata": {},
162+
"outputs": [],
163+
"source": [
164+
"import keras\n",
165+
"\n",
166+
"network = keras.models.Sequential()\n",
167+
"network.add(keras.layers.Input(shape=(28 * 28,))) # Define input shape using Input layer\n",
168+
"network.add(keras.layers.Dense(512, activation='relu'))\n",
169+
"network.add(keras.layers.Dense(10, activation='softmax'))\n",
170+
"\n"
171+
]
172+
},
173+
{
174+
"cell_type": "markdown",
175+
"metadata": {},
176+
"source": [
177+
"### 2.5 The compilation step\n",
178+
"\n"
179+
]
180+
},
181+
{
182+
"cell_type": "code",
183+
"execution_count": null,
184+
"metadata": {},
185+
"outputs": [],
186+
"source": [
187+
"network.compile(\n",
188+
" optimizer='rmsprop',\n",
189+
" loss='categorical_crossentropy',\n",
190+
" metrics=['accuracy']\n",
191+
")\n",
192+
"\n"
193+
]
194+
},
195+
{
196+
"cell_type": "markdown",
197+
"metadata": {},
198+
"source": [
199+
"### 2.6 Preparing the image data\n",
200+
"\n"
201+
]
202+
},
203+
{
204+
"cell_type": "code",
205+
"execution_count": null,
206+
"metadata": {},
207+
"outputs": [],
208+
"source": [
209+
"train_images = np.array(train_images).reshape((n_train, 28 * 28))\n",
210+
"train_images = np.array(train_images).astype('float32') / 255\n",
211+
"\n",
212+
"test_images = np.array(test_images).reshape((n_test, 28 * 28))\n",
213+
"test_images = np.array(test_images).astype('float32') / 255\n",
214+
"\n"
215+
]
216+
},
217+
{
218+
"cell_type": "markdown",
219+
"metadata": {},
220+
"source": [
221+
"### 2.7 Preparing the labels\n",
222+
"\n"
223+
]
224+
},
225+
{
226+
"cell_type": "code",
227+
"execution_count": null,
228+
"metadata": {},
229+
"outputs": [],
230+
"source": [
231+
"train_labels = keras.utils.to_categorical(train_labels)\n",
232+
"test_labels = keras.utils.to_categorical(test_labels)\n",
233+
"\n"
234+
]
235+
},
236+
{
237+
"cell_type": "markdown",
238+
"metadata": {},
239+
"source": [
240+
"### 2.8 Training the network\n",
241+
"\n"
242+
]
243+
},
244+
{
245+
"cell_type": "code",
246+
"execution_count": null,
247+
"metadata": {},
248+
"outputs": [],
249+
"source": [
250+
"n_epoch = 1 if os.getenv('GITHUB_ACTIONS', False) else 5\n",
251+
"\n"
252+
]
253+
},
254+
{
255+
"cell_type": "code",
256+
"execution_count": null,
257+
"metadata": {},
258+
"outputs": [],
259+
"source": [
260+
"%%time\n",
261+
"network.fit(train_images, train_labels, epochs=n_epoch, batch_size=128)\n",
262+
"\n"
263+
]
264+
},
265+
{
266+
"cell_type": "markdown",
267+
"metadata": {},
268+
"source": [
269+
"### 2.9 Evaluating the network\n",
270+
"\n"
271+
]
272+
},
273+
{
274+
"cell_type": "code",
275+
"execution_count": null,
276+
"metadata": {},
277+
"outputs": [],
278+
"source": [
279+
"test_loss, test_acc = network.evaluate(test_images, test_labels)\n",
280+
"print('test_acc:', test_acc)\n",
281+
"\n"
282+
]
283+
},
284+
{
285+
"cell_type": "code",
286+
"execution_count": null,
287+
"metadata": {},
288+
"outputs": [],
289+
"source": []
290+
}
291+
],
292+
"metadata": {
293+
"colab": {
294+
"provenance": []
295+
},
296+
"kernelspec": {
297+
"display_name": "Python 3 (ipykernel)",
298+
"language": "python",
299+
"name": "python3"
300+
},
301+
"language_info": {
302+
"codemirror_mode": {
303+
"name": "ipython",
304+
"version": 3
305+
},
306+
"file_extension": ".py",
307+
"mimetype": "text/x-python",
308+
"name": "python",
309+
"nbconvert_exporter": "python",
310+
"pygments_lexer": "ipython3",
311+
"version": "3.10.0"
312+
}
313+
},
314+
"nbformat": 4,
315+
"nbformat_minor": 4
316+
}

0 commit comments

Comments
 (0)