tflearn vs tensorflow

mnist_dnn.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting mnist/train-images-idx3-ubyte.gz\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/Cellar/python/2.7.12/Frameworks/Python.framework/Versions/2.7/lib/python2.7/gzip.py:275: VisibleDeprecationWarning: converting an array with ndim > 0 to an index will result in an error in the future\n",
      "  chunk = self.extrabuf[offset: offset + size]\n",
      "/usr/local/lib/python2.7/site-packages/tflearn/datasets/mnist.py:52: VisibleDeprecationWarning: converting an array with ndim > 0 to an index will result in an error in the future\n",
      "  data = data.reshape(num_images, rows, cols, 1)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting mnist/train-labels-idx1-ubyte.gz\n",
      "Extracting mnist/t10k-images-idx3-ubyte.gz\n",
      "Extracting mnist/t10k-labels-idx1-ubyte.gz\n"
     ]
    }
   ],
   "source": [
    "import tflearn\n",
    "import tflearn.datasets.mnist as mnist\n",
    "X, Y, testX, testY = mnist.load_data(one_hot=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Step: 6880  | total loss: \u001b[1m\u001b[32m0.29894\u001b[0m\u001b[0m\n",
      "| RMSProp | epoch: 016 | loss: 0.29894 - acc: 0.9752 | val_loss: 0.06902 - val_acc: 0.9801 -- iter: 55000/55000\n",
      "Training Step: 6880  | total loss: \u001b[1m\u001b[32m0.29894\u001b[0m\u001b[0m\n",
      "| RMSProp | epoch: 016 | loss: 0.29894 - acc: 0.9752 | val_loss: 0.06902 - val_acc: 0.9801 -- iter: 55000/55000\n",
      "--\n"
     ]
    }
   ],
   "source": [
    "input_layer = tflearn.input_data(shape=[None, 784])\n",
    "dense1 = tflearn.fully_connected(input_layer, 512, activation='tanh')\n",
    "dropout1 = tflearn.dropout(dense1, 0.8)\n",
    "dense2 = tflearn.fully_connected(dropout1, 512, activation='tanh')\n",
    "dropout2 = tflearn.dropout(dense2, 0.8)\n",
    "softmax = tflearn.fully_connected(dropout2, 10, activation='softmax')\n",
    "\n",
    "net = tflearn.regression(softmax, optimizer=tflearn.RMSProp(), loss='categorical_crossentropy')\n",
    "\n",
    "# Training\n",
    "model = tflearn.DNN(net, tensorboard_verbose=0)\n",
    "model.fit(X, Y, n_epoch=16, batch_size=128, validation_set=(testX, testY), \n",
    "          show_metric=True, shuffle=True, run_id=\"dense_model\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}

mnist_mlp.ipynb