Skip to content

Commit 274bfb8

Browse files
TarrySinghTarrySingh
committed
More Keras Tutorials
1 parent 4106f52 commit 274bfb8

12 files changed

+50456
-0
lines changed

‎deep-learning/Keras Tutorials/Apples Classification.ipynb

+95
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,95 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"metadata": {
7+
"collapsed": true
8+
},
9+
"outputs": [],
10+
"source": [
11+
"import sys\n",
12+
"import os\n",
13+
"import shutil\n",
14+
"import unicodedata\n",
15+
"from collections import defaultdict"
16+
]
17+
},
18+
{
19+
"cell_type": "code",
20+
"execution_count": 2,
21+
"metadata": {
22+
"collapsed": true
23+
},
24+
"outputs": [],
25+
"source": [
26+
"UNKNOWN = \"unknown\"\n",
27+
"\n",
28+
"def remove_accents(input_unicode):\n",
29+
" nfkd_form = unicodedata.normalize('NFKD', input_unicode)\n",
30+
" return u\"\".join([c for c in nfkd_form if not unicodedata.combining(c)])\n",
31+
"\n",
32+
"def normalized(p):\n",
33+
" p = p.replace(\"/\", \"-\")\n",
34+
" p = p.replace(\" \", \"-\")\n",
35+
" return remove_accents(p.decode(\"utf-8\")).encode(\"ascii\")"
36+
]
37+
},
38+
{
39+
"cell_type": "code",
40+
"execution_count": 4,
41+
"metadata": {},
42+
"outputs": [
43+
{
44+
"ename": "ValueError",
45+
"evalue": "not enough values to unpack (expected 4, got 2)",
46+
"output_type": "error",
47+
"traceback": [
48+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
49+
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
50+
"\u001b[0;32m<ipython-input-4-735b4af72066>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mfiles_filename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfaces_filename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moutput_dir\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msys\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margv\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mfiles\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0ml\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstrip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"\\t\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0ml\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mfile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfiles_filename\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mfaces\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0ml\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstrip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"\\t\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0ml\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mfile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfaces_filename\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mpersons\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ml\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0ml\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mfaces\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32massert\u001b[0m \u001b[0mUNKNOWN\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mpersons\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
51+
"\u001b[0;31mValueError\u001b[0m: not enough values to unpack (expected 4, got 2)"
52+
]
53+
}
54+
],
55+
"source": [
56+
"files_filename, faces_filename, input_dir, output_dir = sys.argv[1:]\n",
57+
"files = [l.strip().split(\"\\t\") for l in file(files_filename)]\n",
58+
"faces = [l.strip().split(\"\\t\") for l in file(faces_filename)]\n",
59+
"persons = set(l[2] for l in faces)\n",
60+
"assert UNKNOWN not in persons\n",
61+
"print(len(files), \"files found\")"
62+
]
63+
},
64+
{
65+
"cell_type": "code",
66+
"execution_count": null,
67+
"metadata": {
68+
"collapsed": true
69+
},
70+
"outputs": [],
71+
"source": []
72+
}
73+
],
74+
"metadata": {
75+
"kernelspec": {
76+
"display_name": "Python 3",
77+
"language": "python",
78+
"name": "python3"
79+
},
80+
"language_info": {
81+
"codemirror_mode": {
82+
"name": "ipython",
83+
"version": 3
84+
},
85+
"file_extension": ".py",
86+
"mimetype": "text/x-python",
87+
"name": "python",
88+
"nbconvert_exporter": "python",
89+
"pygments_lexer": "ipython3",
90+
"version": "3.6.1"
91+
}
92+
},
93+
"nbformat": 4,
94+
"nbformat_minor": 2
95+
}

‎deep-learning/Keras Tutorials/Fashion MNIST in Keras.ipynb

+84
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"metadata": {},
7+
"outputs": [
8+
{
9+
"name": "stderr",
10+
"output_type": "stream",
11+
"text": [
12+
"Using TensorFlow backend.\n"
13+
]
14+
}
15+
],
16+
"source": [
17+
"from utils.mnist_loader import load_mnist\n",
18+
"from keras.layers import Dense, MaxPool2D, Conv2D, Dropout\n",
19+
"from keras.layers import Flatten, InputLayer\n",
20+
"from keras.layers.normalization import BatchNormalization\n",
21+
"from keras.models import Sequential\n",
22+
"from keras.utils import np_utils\n",
23+
"from keras.initializers import Constant"
24+
]
25+
},
26+
{
27+
"cell_type": "code",
28+
"execution_count": 5,
29+
"metadata": {},
30+
"outputs": [
31+
{
32+
"ename": "FileNotFoundError",
33+
"evalue": "[Errno 2] No such file or directory: './data/train-labels-idx1-ubyte.gz'",
34+
"output_type": "error",
35+
"traceback": [
36+
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
37+
"\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
38+
"\u001b[0;32m<ipython-input-5-006d3f2b0e9f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Load data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;31m# Function load_minst is available in git.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_mnist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'./data'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkind\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'train'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 4\u001b[0m \u001b[0mX_test\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_test\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_mnist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'./data'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkind\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m't10k'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
39+
"\u001b[0;32m~/Projects/Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials/deep-learning/Keras Tutorials/utils/mnist_loader.py\u001b[0m in \u001b[0;36mload_mnist\u001b[0;34m(path, kind)\u001b[0m\n\u001b[1;32m 12\u001b[0m % kind)\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0;32mwith\u001b[0m \u001b[0mgzip\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlabels_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'rb'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mlbpath\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 15\u001b[0m labels = np.frombuffer(lbpath.read(), dtype=np.uint8,\n\u001b[1;32m 16\u001b[0m offset=8)\n",
40+
"\u001b[0;32m~/anaconda/lib/python3.6/gzip.py\u001b[0m in \u001b[0;36mopen\u001b[0;34m(filename, mode, compresslevel, encoding, errors, newline)\u001b[0m\n\u001b[1;32m 51\u001b[0m \u001b[0mgz_mode\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreplace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"t\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 52\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbytes\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mPathLike\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 53\u001b[0;31m \u001b[0mbinary_file\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mGzipFile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgz_mode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcompresslevel\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 54\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"read\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"write\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 55\u001b[0m \u001b[0mbinary_file\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mGzipFile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgz_mode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcompresslevel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
41+
"\u001b[0;32m~/anaconda/lib/python3.6/gzip.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, filename, mode, compresslevel, fileobj, mtime)\u001b[0m\n\u001b[1;32m 161\u001b[0m \u001b[0mmode\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;34m'b'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 162\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mfileobj\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 163\u001b[0;31m \u001b[0mfileobj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmyfileobj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbuiltins\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0;34m'rb'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 164\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mfilename\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 165\u001b[0m \u001b[0mfilename\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfileobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'name'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m''\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
42+
"\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: './data/train-labels-idx1-ubyte.gz'"
43+
]
44+
}
45+
],
46+
"source": [
47+
"# Load data\n",
48+
"# Function load_minst is available in git.\n",
49+
"X_train, y_train = load_mnist('./data', kind='train')\n",
50+
"X_test, y_test = load_mnist('./data', kind='t10k')"
51+
]
52+
},
53+
{
54+
"cell_type": "code",
55+
"execution_count": null,
56+
"metadata": {
57+
"collapsed": true
58+
},
59+
"outputs": [],
60+
"source": []
61+
}
62+
],
63+
"metadata": {
64+
"kernelspec": {
65+
"display_name": "Python 3",
66+
"language": "python",
67+
"name": "python3"
68+
},
69+
"language_info": {
70+
"codemirror_mode": {
71+
"name": "ipython",
72+
"version": 3
73+
},
74+
"file_extension": ".py",
75+
"mimetype": "text/x-python",
76+
"name": "python",
77+
"nbconvert_exporter": "python",
78+
"pygments_lexer": "ipython3",
79+
"version": "3.6.1"
80+
}
81+
},
82+
"nbformat": 4,
83+
"nbformat_minor": 2
84+
}

‎deep-learning/Keras Tutorials/utils/mnist_loader.py

+22
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,22 @@
1+
def load_mnist(path, kind='train'):
2+
import os
3+
import gzip
4+
import numpy as np
5+
6+
"""Load MNIST data from `path`"""
7+
labels_path = os.path.join(path,
8+
'%s-labels-idx1-ubyte.gz'
9+
% kind)
10+
images_path = os.path.join(path,
11+
'%s-images-idx3-ubyte.gz'
12+
% kind)
13+
14+
with gzip.open(labels_path, 'rb') as lbpath:
15+
labels = np.frombuffer(lbpath.read(), dtype=np.uint8,
16+
offset=8)
17+
18+
with gzip.open(images_path, 'rb') as imgpath:
19+
images = np.frombuffer(imgpath.read(), dtype=np.uint8,
20+
offset=16).reshape(len(labels), 784)
21+
22+
return images, labels

0 commit comments

Comments
 (0)