添加了静态的 HTML 文件

Former-commit-id: 0a23739
Former-commit-id: 55b028e60f58b3a6392368d07043b9bcfbb7fd68 [formerly 4baf6faa3ae671afb70f35853a5faebcd3f9eede] [formerly 92c269f18c65fd8820f17b0d94da4fc61756090a [formerly 6769512c4e98fbce459b74b4dccc0717644b2765]] [formerly fe368abc29479ea6d7975d6704b839b4c071476a [formerly 226a6650f0ee2381d5742c50594637ef5e9d4529] [formerly 7e6255d4645dbf80370506037ef820127ef7eedf [formerly 2763b4d9464dba961543883a04826c2a6b66fd52]]] [formerly 786d447ca560591734ab28752439ddb1246ed08c [formerly 0930ade9abbff8c847d7badbeef317fa0fa6f448] [formerly a60308d9ac38d495118b041a1cfea97a68289528 [formerly 12959f28936571a44e9d83caaf2bf4da5f0254ee]] [formerly 4072a382edeb1651a37c1528c2f8d6850aae14df [formerly 680dffec4bf302c36dc008abb625b829c3185aff] [formerly 9f9667d8193ee1af7f3bd48b3514577fcccf6890 [formerly 15cb732]]]]
Former-commit-id: 953c9aa46269cb8c7076c4df77238cdd90c5e194 [formerly 5604ec0b6b1842f20f0d2f848acff9a59cbda33a] [formerly b533893d3ca0844452f149906a147100861b6c98 [formerly 4ad0d80c131e6cb43af669857a8d4bcedd33d8ac]] [formerly 3431118edec5e6df516465e6edb634469d4f008b [formerly 8b09659abc746ef4b2d3afc3f10544bf13b718aa] [formerly a0f4db2410d20522682eb52cf2e03f9fd5e425ae [formerly 00165d191fc0eb236806d4ef38100a7e1ec0984a]]]
Former-commit-id: d8deb71db2014f8e3cc4d4e28e514dea1b7ec1ad [formerly ba8d2d60dfd47a7ade5b3d99b22e2c5a242981cf] [formerly 742896aea232e7d2ac5e0a326c0406697d858f07 [formerly aec35cb2acf1163e35e21d10c0217f862eca3698]]
Former-commit-id: b88ad491302356538321e50ba94c42986a3384af [formerly aa67ef41dacb0a2fe1fa7f73ab43ea4f05053812]
Former-commit-id: 4f30b96efbef636a0f0bdcb44492df6e01f45b71

03. numpy/03.04 array types.ipynb.REMOVED.git-id

@@ -1 +1 @@
-713ccb0c837d616e4f75cc49a117c2297179862b
+8b3a5b7d7391ea7f4735ef7a7f28a6bb4197e215

09. theano/09.01 introduction and installation.ipynb

@@ -0,0 +1,206 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Theano 简介及其安装"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 简介"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`Theano` 是一个 `Python` 科学计算库，允许我们进行符号运算，并在 `CPU` 和 `GPU` 上执行。\n",
+    "\n",
+    "它最初由 `Montreal` 大学的机器学习研究者们所开发，用来进行机器学习的计算。\n",
+    "\n",
+    "按照[官网](http://deeplearning.net/software/theano/)上的说明，它拥有以下几个方面的特点：\n",
+    "\n",
+    "- 与 **Numpy, Scipy** 的紧密结合\n",
+    "- **GPU** 加速\n",
+    "- 高效的符号计算\n",
+    "- 速度和稳定性\n",
+    "- 动态生成 **C** 代码"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 使用 anaconda 安装 theano"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`windows` 下，使用 `anaconda` 安装 `theano` 的命令为：\n",
+    "\n",
+    "    conda install mingw libpython\n",
+    "    pip install theano\n",
+    "    \n",
+    "`linux` 下，使用 `anaconda` 安装的命令为\n",
+    "    \n",
+    "    conda install theano\n",
+    "\n",
+    "安装好之后，还需要安装 `Cuda` 并进行 `GPU` 环境的配置，否则是不能利用 `GPU` 进行计算的，推荐使用 `linux/mac` 进行配置，具体方法可以参考[官网](http://deeplearning.net/software/theano/)上的配置说明。\n",
+    "\n",
+    "查看安装的版本："
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false,
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'0.7.0.dev-54186290a97186b9c6b76317e007844529a352f4'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import theano\n",
+    "\n",
+    "theano.__version__"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "查看当前使用的 device："
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'cpu'"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "theano.config.device"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "运行测试："
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/usr/local/lib/python2.7/dist-packages/theano/misc/pycuda_init.py:34: UserWarning: PyCUDA import failed in theano.misc.pycuda_init\n",
+      "  warnings.warn(\"PyCUDA import failed in theano.misc.pycuda_init\")\n",
+      "....................S..............."
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Theano version 0.7.0.dev-54186290a97186b9c6b76317e007844529a352f4\n",
+      "theano is installed in /usr/local/lib/python2.7/dist-packages/theano\n",
+      "NumPy version 1.10.1\n",
+      "NumPy relaxed strides checking option: True\n",
+      "NumPy is installed in /usr/lib/python2.7/dist-packages/numpy\n",
+      "Python version 2.7.6 (default, Jun 22 2015, 17:58:13) [GCC 4.8.2]\n",
+      "nose version 1.3.7\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "----------------------------------------------------------------------\n",
+      "Ran 37 tests in 37.919s\n",
+      "\n",
+      "OK (SKIP=1)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<nose.result.TextTestResult run=37 errors=0 failures=0>"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "theano.test()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "这里我已经在本地 `Windows` 配好了 `GPU` 的设置，如果没有配好，显示的结果可能不一样。\n",
+    "\n",
+    "`Windows` 下第一次运行可能会显示 `DEBUG: nvcc STDOUT` 等内容，**`Just ignore it!`**"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

09. theano/09.02 theano basics.ipynb.REMOVED.git-id

@@ -1 +1 @@
-df42578b7bd3c7a9cea6ab49118537b543a60ec8
+c724d58f499a3332c788a91db5a4bc7888924179

09. theano/09.03 gpu on windows.ipynb.REMOVED.git-id

@@ -1 +1 @@
-d00aaf25f64be888e5ce70962a07e9372126f5ba
+c5f58238f46e59e2c4256b9b0ad3c55eb3509cba

09. theano/09.07 softmax on mnist.ipynb.REMOVED.git-id

@@ -1 +1 @@
-e742f36bb55ffc69bcd84b3a7e8cb4d486a918a4
+b700b87c50e114ba229377e6248a2ba7591b9a11

09. theano/09.08 net.ipynb.REMOVED.git-id

@@ -0,0 +1 @@
+2a207a309f728f12e5f45faadafde766be259372

09. theano/download_mnist.py

@@ -1,20 +1,20 @@
-import os
-import os.path
-import urllib
-import gzip
-import shutil
-
-if not os.path.exists('mnist'):
-    os.mkdir('mnist')
-
-def download_and_gzip(name):
-    if not os.path.exists(name + '.gz'):
-        urllib.urlretrieve('http://yann.lecun.com/exdb/' + name + '.gz', name + '.gz')
-    if not os.path.exists(name):
-        with gzip.open(name + '.gz', 'rb') as f_in, open(name, 'wb') as f_out:
-            shutil.copyfileobj(f_in, f_out)
-
-download_and_gzip('mnist/train-images-idx3-ubyte')
-download_and_gzip('mnist/train-labels-idx1-ubyte')
-download_and_gzip('mnist/t10k-images-idx3-ubyte')
+import os
+import os.path
+import urllib
+import gzip
+import shutil
+
+if not os.path.exists('mnist'):
+    os.mkdir('mnist')
+
+def download_and_gzip(name):
+    if not os.path.exists(name + '.gz'):
+        urllib.urlretrieve('http://yann.lecun.com/exdb/' + name + '.gz', name + '.gz')
+    if not os.path.exists(name):
+        with gzip.open(name + '.gz', 'rb') as f_in, open(name, 'wb') as f_out:
+            shutil.copyfileobj(f_in, f_out)
+
+download_and_gzip('mnist/train-images-idx3-ubyte')
+download_and_gzip('mnist/train-labels-idx1-ubyte')
+download_and_gzip('mnist/t10k-images-idx3-ubyte')
 download_and_gzip('mnist/t10k-labels-idx1-ubyte')

09. theano/load.py

@@ -1,48 +1,48 @@
-import numpy as np
-import os
-
-datasets_dir = './'
-
-def one_hot(x,n):
-	if type(x) == list:
-		x = np.array(x)
-	x = x.flatten()
-	o_h = np.zeros((len(x),n))
-	o_h[np.arange(len(x)),x] = 1
-	return o_h
-
-def mnist(ntrain=60000,ntest=10000,onehot=True):
-	data_dir = os.path.join(datasets_dir,'mnist/')
-	fd = open(os.path.join(data_dir,'train-images-idx3-ubyte'))
-	loaded = np.fromfile(file=fd,dtype=np.uint8)
-	trX = loaded[16:].reshape((60000,28*28)).astype(float)
-
-	fd = open(os.path.join(data_dir,'train-labels-idx1-ubyte'))
-	loaded = np.fromfile(file=fd,dtype=np.uint8)
-	trY = loaded[8:].reshape((60000))
-
-	fd = open(os.path.join(data_dir,'t10k-images-idx3-ubyte'))
-	loaded = np.fromfile(file=fd,dtype=np.uint8)
-	teX = loaded[16:].reshape((10000,28*28)).astype(float)
-
-	fd = open(os.path.join(data_dir,'t10k-labels-idx1-ubyte'))
-	loaded = np.fromfile(file=fd,dtype=np.uint8)
-	teY = loaded[8:].reshape((10000))
-
-	trX = trX/255.
-	teX = teX/255.
-
-	trX = trX[:ntrain]
-	trY = trY[:ntrain]
-
-	teX = teX[:ntest]
-	teY = teY[:ntest]
-
-	if onehot:
-		trY = one_hot(trY, 10)
-		teY = one_hot(teY, 10)
-	else:
-		trY = np.asarray(trY)
-		teY = np.asarray(teY)
-
+import numpy as np
+import os
+
+datasets_dir = './'
+
+def one_hot(x,n):
+	if type(x) == list:
+		x = np.array(x)
+	x = x.flatten()
+	o_h = np.zeros((len(x),n))
+	o_h[np.arange(len(x)),x] = 1
+	return o_h
+
+def mnist(ntrain=60000,ntest=10000,onehot=True):
+	data_dir = os.path.join(datasets_dir,'mnist/')
+	fd = open(os.path.join(data_dir,'train-images-idx3-ubyte'))
+	loaded = np.fromfile(file=fd,dtype=np.uint8)
+	trX = loaded[16:].reshape((60000,28*28)).astype(float)
+
+	fd = open(os.path.join(data_dir,'train-labels-idx1-ubyte'))
+	loaded = np.fromfile(file=fd,dtype=np.uint8)
+	trY = loaded[8:].reshape((60000))
+
+	fd = open(os.path.join(data_dir,'t10k-images-idx3-ubyte'))
+	loaded = np.fromfile(file=fd,dtype=np.uint8)
+	teX = loaded[16:].reshape((10000,28*28)).astype(float)
+
+	fd = open(os.path.join(data_dir,'t10k-labels-idx1-ubyte'))
+	loaded = np.fromfile(file=fd,dtype=np.uint8)
+	teY = loaded[8:].reshape((10000))
+
+	trX = trX/255.
+	teX = teX/255.
+
+	trX = trX[:ntrain]
+	trY = trY[:ntrain]
+
+	teX = teX[:ntest]
+	teY = teY[:ntest]
+
+	if onehot:
+		trY = one_hot(trY, 10)
+		teY = one_hot(teY, 10)
+	else:
+		trY = np.asarray(trY)
+		teY = np.asarray(teY)
+
 	return trX,teX,trY,teY