{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/jannes/anaconda/lib/python3.5/site-packages/h5py/__init__.py:34: 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",
      "Using TensorFlow backend.\n",
      "/Users/jannes/anaconda/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: compiletime version 3.6 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.5\n",
      "  return f(*args, **kwds)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Couldn't import dot_parser, loading of dot files will not be possible.\n"
     ]
    }
   ],
   "source": [
    "from keras.datasets import mnist\n",
    "\n",
    "(x_train, y_train), (x_test, y_test) = mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import Sequential\n",
    "from keras.layers import Dense"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train.shape = (60000, 28 * 28)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_test.shape = (10000, 28 * 28)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = x_train / 255\n",
    "x_test = x_test / 255"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Sequential()\n",
    "model.add(Dense(512,activation='relu',input_dim= 28*28))\n",
    "model.add(Dense(512,activation='relu'))\n",
    "model.add(Dense(512,activation='relu'))\n",
    "model.add(Dense(10,activation='softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(loss='sparse_categorical_crossentropy',optimizer='adam',metrics=['acc'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.callbacks import TensorBoard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow.python import debug as tf_debug\n",
    "import keras\n",
    "\n",
    "keras.backend.set_session(\n",
    "    tf_debug.TensorBoardDebugWrapperSession(tf.Session(), \"localhost:2018\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "tb = TensorBoard(log_dir='./logs/test2', \n",
    "                 histogram_freq=1, \n",
    "                 batch_size=32, \n",
    "                 write_graph=True, \n",
    "                 write_grads=True, \n",
    "                 write_images=True, \n",
    "                 embeddings_freq=0, \n",
    "                 embeddings_layer_names=None, \n",
    "                 embeddings_metadata=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 60000 samples, validate on 10000 samples\n",
      "Epoch 1/5\n",
      "60000/60000 [==============================] - 9s 149us/step - loss: 13.4057 - acc: 0.1680 - val_loss: 14.2823 - val_acc: 0.1139\n",
      "Epoch 2/5\n",
      "60000/60000 [==============================] - 9s 144us/step - loss: 12.8723 - acc: 0.2014 - val_loss: 12.7043 - val_acc: 0.2118\n",
      "Epoch 3/5\n",
      "60000/60000 [==============================] - 8s 136us/step - loss: 12.7616 - acc: 0.2082 - val_loss: 12.7011 - val_acc: 0.2120\n",
      "Epoch 4/5\n",
      "60000/60000 [==============================] - 9s 150us/step - loss: 12.7532 - acc: 0.2088 - val_loss: 12.7011 - val_acc: 0.2120\n",
      "Epoch 5/5\n",
      "60000/60000 [==============================] - 9s 143us/step - loss: 13.8286 - acc: 0.1420 - val_loss: 14.2887 - val_acc: 0.1135\n"
     ]
    }
   ],
   "source": [
    "hist = model.fit(x_train*255,y_train,\n",
    "                 batch_size=128,\n",
    "                 epochs=5,callbacks=[tb],\n",
    "                 validation_data=(x_test*255,y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [default]",
   "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": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}