{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "##### 교재 페이지 (298-300) #####" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "9) MNIST 99% with CNN" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:From :6: read_data_sets (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Please use alternatives such as official/mnist/dataset.py from tensorflow/models.\n", "WARNING:tensorflow:From C:\\Users\\jsdata00010\\Anaconda3\\lib\\site-packages\\tensorflow\\contrib\\learn\\python\\learn\\datasets\\mnist.py:260: maybe_download (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Please write your own downloading logic.\n", "WARNING:tensorflow:From C:\\Users\\jsdata00010\\Anaconda3\\lib\\site-packages\\tensorflow\\contrib\\learn\\python\\learn\\datasets\\mnist.py:262: extract_images (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Please use tf.data to implement this functionality.\n", "Extracting ./mnist/data/train-images-idx3-ubyte.gz\n", "WARNING:tensorflow:From C:\\Users\\jsdata00010\\Anaconda3\\lib\\site-packages\\tensorflow\\contrib\\learn\\python\\learn\\datasets\\mnist.py:267: extract_labels (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Please use tf.data to implement this functionality.\n", "Extracting ./mnist/data/train-labels-idx1-ubyte.gz\n", "WARNING:tensorflow:From C:\\Users\\jsdata00010\\Anaconda3\\lib\\site-packages\\tensorflow\\contrib\\learn\\python\\learn\\datasets\\mnist.py:110: dense_to_one_hot (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Please use tf.one_hot on tensors.\n", "Extracting ./mnist/data/t10k-images-idx3-ubyte.gz\n", "Extracting ./mnist/data/t10k-labels-idx1-ubyte.gz\n", "WARNING:tensorflow:From C:\\Users\\jsdata00010\\Anaconda3\\lib\\site-packages\\tensorflow\\contrib\\learn\\python\\learn\\datasets\\mnist.py:290: DataSet.__init__ (from tensorflow.contrib.learn.python.learn.datasets.mnist) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Please use alternatives such as official/mnist/dataset.py from tensorflow/models.\n" ] } ], "source": [ "import tensorflow as tf\n", "import numpy as np\n", "\n", "#mnist 데이터 불러오기\n", "from tensorflow.examples.tutorials.mnist import input_data\n", "mnist= input_data.read_data_sets(\"./mnist/data/\",one_hot=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Conv layer1" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:From C:\\Users\\jsdata00010\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Colocations handled automatically by placer.\n" ] } ], "source": [ "#입력데이터 플레이스홀더\n", "X = tf.placeholder(tf.float32,[None,784])\n", "X_img = tf.reshape(X,[-1,28,28,1])\n", "Y = tf.placeholder(tf.float32,[None,10])\n", "\n", "#Layer1(합성곱층+풀링층)\n", "W1 = tf.Variable(tf.random_normal([3,3,1,32],stddev=0.01))\n", "L1 = tf.nn.conv2d(X_img,W1,strides=[1,1,1,1],padding='SAME')\n", "L1 = tf.nn.relu(L1)\n", "L1 = tf.nn.max_pool(L1,ksize=[1,2,2,1],\n", " strides=[1,2,2,1],padding='SAME')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Conv layer2" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "#Layer2(합성곱층+풀링층)\n", "W2 = tf.Variable(tf.random_normal([3,3,32,64],stddev=0.01))\n", "L2 = tf.nn.conv2d(L1,W2,strides=[1,1,1,1],padding='SAME')\n", "L2 = tf.nn.relu(L2)\n", "L2 = tf.nn.max_pool(L2,ksize=[1,2,2,1],\n", " strides=[1,2,2,1],padding='SAME')\n", "L2 = tf.reshape(L2,[-1,7*7*64])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Fully Connecter(FC,Dense) layer" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "L2 = tf.reshape(L2,[-1,7*7*64])\n", "\n", "#전출력층\n", "W3 = tf.get_variable(\"W3\",shape=[7*7*64,10],\n", " initializer=tf.contrib.layers.xavier_initializer())\n", "b = tf.Variable(tf.random_normal([10]))\n", "hypo = tf.matmul(L2,W3) + b\n", "\n", "learning_rate = 0.001\n", "cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=hypo,\n", " labels=Y))\n", "optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Training and Evaluation" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "epoch: 0005 Avg.cost= 0.052819\n", "epoch: 0010 Avg.cost= 0.028132\n", "epoch: 0015 Avg.cost= 0.015315\n", "epoch: 0020 Avg.cost= 0.008689\n", "epoch: 0025 Avg.cost= 0.005381\n", "epoch: 0030 Avg.cost= 0.004462\n", "Learning Finished!\n" ] } ], "source": [ "#신경망 모델 학습\n", "init=tf.global_variables_initializer()\n", "sess=tf.Session()\n", "\n", "sess.run(init)\n", "\n", "\n", "batch_size=100\n", "total_batch=int(mnist.train.num_examples/batch_size)\n", "\n", "for epoch in range(30):\n", " total_cost=0\n", " \n", " for i in range(total_batch):\n", " batch_xs,batch_ys=mnist.train.next_batch(batch_size)\n", " \n", " _,cost_val=sess.run([optimizer,cost],feed_dict={X:batch_xs,Y:batch_ys\n", " })\n", " total_cost += cost_val\n", " \n", " if(epoch%5==4): \n", " print('epoch:','%04d'%(epoch+1),\n", " 'Avg.cost=','{:3f}'.format(total_cost/total_batch))\n", "\n", "print(\"Learning Finished!\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Training and Evaluation" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "정확도: 0.9879\n" ] } ], "source": [ "#정확도\n", "is_correct=tf.equal(tf.argmax(hypo,1),tf.argmax(Y,1))\n", "accuracy=tf.reduce_mean(tf.cast(is_correct,tf.float32))\n", "print('정확도:',sess.run(accuracy,feed_dict={X:mnist.test.images,\n", " Y:mnist.test.labels\n", " }))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "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": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }