556 lines
36 KiB
Plaintext
556 lines
36 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"collapsed": true
|
||
},
|
||
"source": [
|
||
"## 安装库\n",
|
||
"本例使用pycharm\n",
|
||
"\n",
|
||
"- 安装notebook\n",
|
||
"\n",
|
||
"```python\n",
|
||
"pip install notebook\n",
|
||
"```\n",
|
||
"\n",
|
||
"- 安装tensorflow\n",
|
||
"\n",
|
||
"本例使用了**tf-nightly**\n",
|
||
"\n",
|
||
"```python\n",
|
||
"pip install tf-nightly\n",
|
||
"```"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"C:\\ProgramData\\Anaconda3\\lib\\site-packages\\h5py\\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n",
|
||
" from ._conv import register_converters as _register_converters\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#导入keras\n",
|
||
"import tensorflow.keras as keras"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"1.12.0-dev20180926\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"#导入tensorflow\n",
|
||
"import tensorflow as tf\n",
|
||
"print(tf.__version__)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"## 下载mnist数据\n",
|
||
"keras默认从(https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz)下载，但国内很难连上，\n",
|
||
"可以参考(http://www.cnblogs.com/shinny/p/9283372.html)。手动下载mnist.npz，然后修改mnist.py中的引用路径。\n",
|
||
"如果找不到mnist.py，可以用everthing搜索。\n",
|
||
"\n",
|
||
"mnist.npz已上传到datasets文件夹，可从[这里]()下载。"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[[ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 3 18 18 18 126 136\n",
|
||
" 175 26 166 255 247 127 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 30 36 94 154 170 253 253 253 253 253\n",
|
||
" 225 172 253 242 195 64 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 49 238 253 253 253 253 253 253 253 253 251\n",
|
||
" 93 82 82 56 39 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 18 219 253 253 253 253 253 198 182 247 241\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 80 156 107 253 253 205 11 0 43 154\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 14 1 154 253 90 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 139 253 190 2 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 11 190 253 70 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 35 241 225 160 108 1\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 81 240 253 253 119\n",
|
||
" 25 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 45 186 253 253\n",
|
||
" 150 27 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 16 93 252\n",
|
||
" 253 187 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 249\n",
|
||
" 253 249 64 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 46 130 183 253\n",
|
||
" 253 207 2 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 39 148 229 253 253 253\n",
|
||
" 250 182 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 24 114 221 253 253 253 253 201\n",
|
||
" 78 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 23 66 213 253 253 253 253 198 81 2\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 18 171 219 253 253 253 253 195 80 9 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 55 172 226 253 253 253 253 244 133 11 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 136 253 253 253 212 135 132 16 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]\n",
|
||
" [ 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
||
" 0 0 0 0 0 0 0 0 0 0]]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"mnist = tf.keras.datasets.mnist\n",
|
||
"(x_train, y_train),(x_test, y_test) = mnist.load_data()\n",
|
||
"print(x_train[0])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAADmtJREFUeJzt3W+sVPWdx/HPFwT/UFQIV3ulKF00ZgmJYEbYhI2iRLSbKvCgBmIQTQM+ANkmEBfhATxwE6PbdlVMk4slQFJpGyorJGYtGo1L3BgGJQiLbNVc6V0QLqFYqw9Q+O6De2hu8c5vhpkzc+byfb8ScmfO9/zmfDPczz0z85uZn7m7AMQzpOgGABSD8ANBEX4gKMIPBEX4gaAIPxAU4QeCIvxAUIQfCOqSVh5szJgxPn78+FYeEgilu7tbJ06csFr2bSj8ZnavpGclDZX0ors/ldp//PjxKpfLjRwSQEKpVKp537of9pvZUEkvSPqBpImS5pvZxHpvD0BrNfKcf6qkj9z9E3c/LenXkmbn0xaAZmsk/GMl/bHf9Z5s298ws8VmVjazcm9vbwOHA5CnRsI/0IsK3/p8sLt3uXvJ3UsdHR0NHA5AnhoJf4+kcf2uf0/SkcbaAdAqjYR/t6SbzOz7ZjZc0jxJ2/NpC0Cz1T3V5+7fmNlSSa+pb6pvg7sfyK0zAE3V0Dy/u78q6dWcegHQQry9FwiK8ANBEX4gKMIPBEX4gaAIPxAU4QeCIvxAUIQfCIrwA0ERfiAowg8ERfiBoAg/EBThB4Ii/EBQhB8IivADQRF+ICjCDwRF+IGgCD8QFOEHgiL8QFCEHwiK8ANBEX4gKMIPBEX4gaAaWqXXzLolfSHpjKRv3L2UR1PIz5kzZ5L1zz//vKnHX7duXcXaV199lRx76NChZP2FF15I1lesWFGxtmXLluTYyy67LFlfuXJlsr5mzZpkvR00FP7Mne5+IofbAdBCPOwHgmo0/C7p92a2x8wW59EQgNZo9GH/dHc/YmbXSNppZh+6+9v9d8j+KCyWpOuvv77BwwHIS0Nnfnc/kv08LmmbpKkD7NPl7iV3L3V0dDRyOAA5qjv8ZjbCzEaeuyxplqT9eTUGoLkaedh/raRtZnbudl5y9//MpSsATVd3+N39E0m35NjLRevw4cPJ+unTp5P1d955J1nftWtXxdqpU6eSY7du3ZqsF2ncuHHJ+mOPPZasb9u2rWJt5MiRybG33JL+1b7jjjuS9cGAqT4gKMIPBEX4gaAIPxAU4QeCIvxAUHl8qi+8999/P1m/6667kvVmf6y2XQ0dOjRZf/LJJ5P1ESNGJOsPPvhgxdp1112XHDtq1Khk/eabb07WBwPO/EBQhB8IivADQRF+ICjCDwRF+IGgCD8QFPP8ObjhhhuS9TFjxiTr7TzPP23atGS92nz4m2++WbE2fPjw5NgFCxYk62gMZ34gKMIPBEX4gaAIPxAU4QeCIvxAUIQfCIp5/hyMHj06WX/mmWeS9R07diTrU6ZMSdaXLVuWrKdMnjw5WX/99deT9Wqfqd+/v/I6Ls8991xyLJqLMz8QFOEHgiL8QFCEHwiK8ANBEX4gKMIPBFV1nt/MNkj6oaTj7j4p2zZa0m8kjZfULekBd/9T89oc3ObMmZOsV/te/2rLSe/bt69i7cUXX0yOXbFiRbJebR6/mkmTJlWsdXV1NXTbaEwtZ/6Nku49b9tKSW+4+02S3siuAxhEqobf3d+WdPK8zbMlbcoub5KUPrUBaDv1Pue/1t2PSlL285r8WgLQCk1/wc/MFptZ2czKvb29zT4cgBrVG/5jZtYpSdnP45V2dPcudy+5e6mjo6POwwHIW73h3y5pYXZ5oaRX8mkHQKtUDb+ZbZH035JuNrMeM/uxpKck3W1mf5B0d3YdwCBSdZ7f3edXKM3MuZewrrzyyobGX3XVVXWPrfY+gHnz5iXrQ4bwPrHBiv85ICjCDwRF+IGgCD8QFOEHgiL8QFB8dfdFYO3atRVre/bsSY596623kvVqX909a9asZB3tizM/EBThB4Ii/EBQhB8IivADQRF+ICjCDwTFPP9FIPX12uvXr0+OvfXWW5P1RYsWJet33nlnsl4qlSrWlixZkhxrZsk6GsOZHwiK8ANBEX4gKMIPBEX4gaAIPxAU4QeCYp7/IjdhwoRkfePGjcn6I488kqxv3ry57vqXX36ZHPvQQw8l652dnck60jjzA0ERfiAowg8ERfiBoAg/EBThB4Ii/EBQVef5zWyDpB9KOu7uk7JtayUtktSb7bbK3V9tVpNonrlz5ybrN954Y7K+fPnyZD31vf9PPPFEcuynn36arK9evTpZHzt2bLIeXS1n/o2S7h1g+8/dfXL2j+ADg0zV8Lv725JOtqAXAC3UyHP+pWa2z8w2mNmo3DoC0BL1hv8XkiZImizpqKSfVtrRzBabWdnMyr29vZV2A9BidYXf3Y+5+xl3PytpvaSpiX273L3k7qWOjo56+wSQs7rCb2b9P041V9L+fNoB0Cq1TPVtkTRD0hgz65G0RtIMM5ssySV1S3q0iT0CaAJz95YdrFQqeblcbtnx0HynTp1K1nfs2FGx9vDDDyfHVvvdnDlzZrK+c+fOZP1iVCqVVC6Xa1rwgHf4AUERfiAowg8ERfiBoAg/EBThB4Jiqg+FufTSS5P1r7/+OlkfNmxYsv7aa69VrM2YMSM5drBiqg9AVYQfCIrwA0ERfiAowg8ERfiBoAg/EBRLdCNp3759yfrWrVuT9d27d1esVZvHr2bixInJ+u23397Q7V/sOPMDQRF+ICjCDwRF+IGgCD8QFOEHgiL8QFDM81/kDh06lKw///zzyfrLL7+crH/22WcX3FOtLrkk/evZ2dmZrA8ZwrkthXsHCIrwA0ERfiAowg8ERfiBoAg/EBThB4KqOs9vZuMkbZb0XUlnJXW5+7NmNlrSbySNl9Qt6QF3/1PzWo2r2lz6Sy+9VLG2bt265Nju7u56WsrFbbfdlqyvXr06Wb///vvzbCecWs7830ha7u5/L+kfJC0xs4mSVkp6w91vkvRGdh3AIFE1/O5+1N3fyy5/IemgpLGSZkvalO22SdKcZjUJIH8X9JzfzMZLmiLpXUnXuvtRqe8PhKRr8m4OQPPUHH4z+46k30n6ibv/+QLGLTazspmVe3t76+kRQBPUFH4zG6a+4P/K3c990uOYmXVm9U5Jxwca6+5d7l5y91JHR0cePQPIQdXwm5lJ+qWkg+7+s36l7ZIWZpcXSnol//YANEstH+mdLmmBpA/MbG+2bZWkpyT91sx+LOmwpB81p8XB79ixY8n6gQMHkvWlS5cm6x9++OEF95SXadOmJeuPP/54xdrs2bOTY/lIbnNVDb+775JUab3vmfm2A6BV+NMKBEX4gaAIPxAU4QeCIvxAUIQfCIqv7q7RyZMnK9YeffTR5Ni9e/cm6x9//HFdPeVh+vTpyfry5cuT9XvuuSdZv/zyyy+4J7QGZ34gKMIPBEX4gaAIPxAU4QeCIvxAUIQfCCrMPP+7776brD/99NPJ+u7duyvWenp66uopL1dccUXF2rJly5Jjq3099ogRI+rqCe2PMz8QFOEHgiL8QFCEHwiK8ANBEX4gKMIPBBVmnn/btm0N1RsxceLEZP2+++5L1ocOHZqsr1ixomLt6quvTo5FXJz5gaAIPxAU4QeCIvxAUIQfCIrwA0ERfiAoc/f0DmbjJG2W9F1JZyV1ufuzZrZW0iJJvdmuq9z91dRtlUolL5fLDTcNYGClUknlctlq2beWN/l8I2m5u79nZiMl7TGznVnt5+7+b/U2CqA4VcPv7kclHc0uf2FmByWNbXZjAJrrgp7zm9l4SVMknftOrKVmts/MNpjZqApjFptZ2czKvb29A+0CoAA1h9/MviPpd5J+4u5/lvQLSRMkTVbfI4OfDjTO3bvcveTupY6OjhxaBpCHmsJvZsPUF/xfufvLkuTux9z9jLuflbRe0tTmtQkgb1XDb2Ym6ZeSDrr7z/pt7+y321xJ+/NvD0Cz1PJq/3RJCyR9YGbn1ppeJWm+mU2W5JK6JaXXqQbQVmp5tX+XpIHmDZNz+gDaG+/wA4Ii/EBQhB8IivADQRF+ICjCDwRF+IGgCD8QFOEHgiL8QFCEHwiK8ANBEX4gKMIPBFX1q7tzPZhZr6RP+20aI+lEyxq4MO3aW7v2JdFbvfLs7QZ3r+n78loa/m8d3Kzs7qXCGkho197atS+J3upVVG887AeCIvxAUEWHv6vg46e0a2/t2pdEb/UqpLdCn/MDKE7RZ34ABSkk/GZ2r5kdMrOPzGxlET1UYmbdZvaBme01s0KXFM6WQTtuZvv7bRttZjvN7A/ZzwGXSSuot7Vm9n/ZfbfXzP6poN7GmdmbZnbQzA6Y2T9n2wu97xJ9FXK/tfxhv5kNlfS/ku6W1CNpt6T57v4/LW2kAjPrllRy98LnhM3sdkl/kbTZ3Sdl256WdNLdn8r+cI5y939pk97WSvpL0Ss3ZwvKdPZfWVrSHEkPq8D7LtHXAyrgfivizD9V0kfu/om7n5b0a0mzC+ij7bn725JOnrd5tqRN2eVN6vvlabkKvbUFdz/q7u9ll7+QdG5l6ULvu0RfhSgi/GMl/bHf9R6115LfLun3ZrbHzBYX3cwArs2WTT+3fPo1BfdzvqorN7fSeStLt819V8+K13krIvwDrf7TTlMO0939Vkk/kLQke3iL2tS0cnOrDLCydFuod8XrvBUR/h5J4/pd/56kIwX0MSB3P5L9PC5pm9pv9eFj5xZJzX4eL7ifv2qnlZsHWllabXDftdOK10WEf7ekm8zs+2Y2XNI8SdsL6ONbzGxE9kKMzGyEpFlqv9WHt0tamF1eKOmVAnv5G+2ycnOllaVV8H3XbiteF/Imn2wq498lDZW0wd3/teVNDMDM/k59Z3upbxHTl4rszcy2SJqhvk99HZO0RtJ/SPqtpOslHZb0I3dv+QtvFXqbob6Hrn9dufncc+wW9/aPkv5L0geSzmabV6nv+XVh912ir/kq4H7jHX5AULzDDwiK8ANBEX4gKMIPBEX4gaAIPxAU4QeCIvxAUP8Pt/ALPExulGgAAAAASUVORK5CYII=\n",
|
||
"text/plain": [
|
||
"<Figure size 432x288 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"import matplotlib.pyplot as plt\n",
|
||
"%matplotlib inline\n",
|
||
"plt.imshow(x_train[0],cmap=plt.cm.binary)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"5\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(y_train[0])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[[0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0.00393124 0.02332955 0.02620568 0.02625207 0.17420356 0.17566281\n",
|
||
" 0.28629534 0.05664824 0.51877786 0.71632322 0.77892406 0.89301644\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0.05780486 0.06524513 0.16128198 0.22713296\n",
|
||
" 0.22277047 0.32790981 0.36833534 0.3689874 0.34978968 0.32678448\n",
|
||
" 0.368094 0.3747499 0.79066747 0.67980478 0.61494005 0.45002403\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0.12250613 0.45858525 0.45852825 0.43408872 0.37314701\n",
|
||
" 0.33153488 0.32790981 0.36833534 0.3689874 0.34978968 0.32420121\n",
|
||
" 0.15214552 0.17865984 0.25626376 0.1573102 0.12298801 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0.04500225 0.4219755 0.45852825 0.43408872 0.37314701\n",
|
||
" 0.33153488 0.32790981 0.28826244 0.26543758 0.34149427 0.31128482\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0.1541463 0.28272888 0.18358693 0.37314701\n",
|
||
" 0.33153488 0.26569767 0.01601458 0. 0.05945042 0.19891229\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0.0253731 0.00171577 0.22713296\n",
|
||
" 0.33153488 0.11664776 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.20500962\n",
|
||
" 0.33153488 0.24625638 0.00291174 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.01622378\n",
|
||
" 0.24897876 0.32790981 0.10191096 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0.04586451 0.31235677 0.32757096 0.23335172 0.14931733 0.00129164\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0.10498298 0.34940902 0.3689874 0.34978968 0.15370495\n",
|
||
" 0.04089933 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0.06551419 0.27127137 0.34978968 0.32678448\n",
|
||
" 0.245396 0.05882702 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0.02333517 0.12857881 0.32549285\n",
|
||
" 0.41390126 0.40743158 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.32161793\n",
|
||
" 0.41390126 0.54251585 0.20001074 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0.06697006 0.18959827 0.25300993 0.32678448\n",
|
||
" 0.41390126 0.45100715 0.00625034 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0.05110617 0.19182076 0.33339444 0.3689874 0.34978968 0.32678448\n",
|
||
" 0.40899334 0.39653769 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0.04117838 0.16813739\n",
|
||
" 0.28960162 0.32790981 0.36833534 0.3689874 0.34978968 0.25961929\n",
|
||
" 0.12760592 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0.04431706 0.11961607 0.36545809 0.37314701\n",
|
||
" 0.33153488 0.32790981 0.36833534 0.28877275 0.111988 0.00258328\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0.05298497 0.42752138 0.4219755 0.45852825 0.43408872 0.37314701\n",
|
||
" 0.33153488 0.25273681 0.11646967 0.01312603 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0.37491383 0.56222061\n",
|
||
" 0.66525569 0.63253163 0.48748768 0.45852825 0.43408872 0.359873\n",
|
||
" 0.17428513 0.01425695 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0.92705966 0.82698729\n",
|
||
" 0.74473314 0.63253163 0.4084877 0.24466922 0.22648107 0.02359823\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]\n",
|
||
" [0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. 0. 0.\n",
|
||
" 0. 0. 0. 0. ]]\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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\n",
|
||
"text/plain": [
|
||
"<Figure size 432x288 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"x_train = tf.keras.utils.normalize(x_train, axis=1)\n",
|
||
"x_test = tf.keras.utils.normalize(x_test, axis=1)\n",
|
||
"\n",
|
||
"print(x_train[0])\n",
|
||
"\n",
|
||
"plt.imshow(x_train[0],cmap=plt.cm.binary)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Epoch 1/3\n",
|
||
"60000/60000 [==============================] - 15s 254us/step - loss: 0.2563 - acc: 0.9248\n",
|
||
"Epoch 2/3\n",
|
||
"60000/60000 [==============================] - 6s 107us/step - loss: 0.1081 - acc: 0.9665\n",
|
||
"Epoch 3/3\n",
|
||
"60000/60000 [==============================] - 7s 109us/step - loss: 0.0737 - acc: 0.9777\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<tensorflow.python.keras.callbacks.History at 0xee9a547c50>"
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"model = tf.keras.models.Sequential()\n",
|
||
"model.add(tf.keras.layers.Flatten(input_shape=(28,28)))\n",
|
||
"model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))\n",
|
||
"model.add(tf.keras.layers.Dense(128, activation=tf.nn.relu))\n",
|
||
"model.add(tf.keras.layers.Dense(10, activation=tf.nn.softmax))\n",
|
||
"model.compile(optimizer='adam',\n",
|
||
" loss='sparse_categorical_crossentropy',\n",
|
||
" metrics=['accuracy'])\n",
|
||
"model.fit(x_train, y_train, epochs=3)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"10000/10000 [==============================] - 0s 46us/step\n",
|
||
"0.09269746929686516\n",
|
||
"0.9708\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"val_loss, val_acc = model.evaluate(x_test, y_test)\n",
|
||
"print(val_loss)\n",
|
||
"print(val_acc)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[[8.8540384e-09 1.2010514e-08 8.4797415e-07 ... 9.9985945e-01\n",
|
||
" 4.4095773e-07 6.2582812e-06]\n",
|
||
" [9.7641809e-08 8.4762014e-03 9.9100375e-01 ... 8.4532692e-09\n",
|
||
" 1.1629361e-05 9.1832054e-12]\n",
|
||
" [1.9781417e-09 9.9992287e-01 1.9637739e-05 ... 2.6759613e-05\n",
|
||
" 2.1188511e-05 3.5105760e-08]\n",
|
||
" ...\n",
|
||
" [8.3089546e-10 7.8291782e-07 2.2996884e-08 ... 3.0950861e-04\n",
|
||
" 3.1089010e-06 1.6785970e-04]\n",
|
||
" [3.2990449e-08 2.2628739e-05 9.8154613e-09 ... 2.6752227e-06\n",
|
||
" 1.8036989e-03 5.3969260e-09]\n",
|
||
" [1.1823743e-06 7.2185024e-08 2.2751304e-07 ... 1.0656525e-10\n",
|
||
" 3.2980407e-07 6.6678885e-09]]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"predictions = model.predict(x_test)\n",
|
||
"print(predictions)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"7\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"\n",
|
||
"print(np.argmax(predictions[0]))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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\n",
|
||
"text/plain": [
|
||
"<Figure size 432x288 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.imshow(x_test[0],cmap=plt.cm.binary)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 保存模型\n",
|
||
"model.save('epic_num_reader.model')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# 加载保存的模型\n",
|
||
"new_model = tf.keras.models.load_model('epic_num_reader.model')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"7\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# 测试保存的模型\n",
|
||
"predictions = new_model.predict(x_test)\n",
|
||
"print(np.argmax(predictions[0]))"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.6.5"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 1
|
||
}
|