{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "##### 교재 페이지 (148-149) #####" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "6-2) matrix" ] }, { "cell_type": "code", "execution_count": 1, "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", "0 Cost: 15320.755 \n", "Prediction:\n", " [[-42.37143 ]\n", " [-49.9997 ]\n", " [-51.354637]\n", " [-55.203167]\n", " [-57.852077]\n", " [-74.300415]\n", " [-75.81849 ]\n", " [-68.26634 ]\n", " [-89.54002 ]]\n", "10000 Cost: 16.23153 \n", "Prediction:\n", " [[35.26634 ]\n", " [40.94182 ]\n", " [45.52548 ]\n", " [49.496647]\n", " [51.258404]\n", " [69.95748 ]\n", " [71.77668 ]\n", " [63.04966 ]\n", " [87.43705 ]]\n", "20000 Cost: 13.404957 \n", "Prediction:\n", " [[34.873634]\n", " [41.90531 ]\n", " [44.972748]\n", " [49.36367 ]\n", " [51.43707 ]\n", " [70.12926 ]\n", " [71.6353 ]\n", " [63.042015]\n", " [87.37891 ]]\n", "30000 Cost: 11.16961 \n", "Prediction:\n", " [[34.52546 ]\n", " [42.76284 ]\n", " [44.481853]\n", " [49.245743]\n", " [51.596294]\n", " [70.28148 ]\n", " [71.50909 ]\n", " [63.035088]\n", " [87.32593 ]]\n", "40000 Cost: 9.401882 \n", "Prediction:\n", " [[34.215824]\n", " [43.525368]\n", " [44.045315]\n", " [49.14087 ]\n", " [51.73787 ]\n", " [70.416855]\n", " [71.39686 ]\n", " [63.028942]\n", " [87.278854]]\n", "50000 Cost: 8.00386 \n", "Prediction:\n", " [[33.9405 ]\n", " [44.203514]\n", " [43.65713 ]\n", " [49.047634]\n", " [51.8638 ]\n", " [70.537254]\n", " [71.29707 ]\n", " [63.023483]\n", " [87.236984]]\n", "60000 Cost: 6.89825 \n", "Prediction:\n", " [[33.6957 ]\n", " [44.806602]\n", " [43.31197 ]\n", " [48.96476 ]\n", " [51.975822]\n", " [70.644356]\n", " [71.20837 ]\n", " [63.01867 ]\n", " [87.19979 ]]\n", "70000 Cost: 6.023898 \n", "Prediction:\n", " [[33.477913]\n", " [45.3428 ]\n", " [43.004932]\n", " [48.890972]\n", " [52.07533 ]\n", " [70.739494]\n", " [71.12937 ]\n", " [63.014282]\n", " [87.16661 ]]\n", "80000 Cost: 5.332395 \n", "Prediction:\n", " [[33.284317]\n", " [45.819706]\n", " [42.731945]\n", " [48.825397]\n", " [52.163876]\n", " [70.824135]\n", " [71.05914 ]\n", " [63.01041 ]\n", " [87.13711 ]]\n", "90000 Cost: 4.7856045 \n", "Prediction:\n", " [[33.112003]\n", " [46.24361 ]\n", " [42.489117]\n", " [48.76704 ]\n", " [52.242542]\n", " [70.89944 ]\n", " [70.996765]\n", " [63.00697 ]\n", " [87.11104 ]]\n", "100000 Cost: 4.353171 \n", "Prediction:\n", " [[32.958973]\n", " [46.62072 ]\n", " [42.273323]\n", " [48.71525 ]\n", " [52.312607]\n", " [70.96642 ]\n", " [70.94131 ]\n", " [63.003967]\n", " [87.08778 ]]\n", "110000 Cost: 4.0110664 \n", "Prediction:\n", " [[32.823093]\n", " [46.95635 ]\n", " [42.081554]\n", " [48.669308]\n", " [52.375057]\n", " [71.02598 ]\n", " [70.89196 ]\n", " [63.00136 ]\n", " [87.06697 ]]\n", "120000 Cost: 3.7407138 \n", "Prediction:\n", " [[32.702038]\n", " [47.254303]\n", " [41.910892]\n", " [48.62829 ]\n", " [52.43032 ]\n", " [71.078835]\n", " [70.84803 ]\n", " [62.998886]\n", " [87.04851 ]]\n", "130000 Cost: 3.5270166 \n", "Prediction:\n", " [[32.594433]\n", " [47.519093]\n", " [41.75925 ]\n", " [48.591877]\n", " [52.47949 ]\n", " [71.12594 ]\n", " [70.80913 ]\n", " [62.996777]\n", " [87.03231 ]]\n", "140000 Cost: 3.3580005 \n", "Prediction:\n", " [[32.498867]\n", " [47.754536]\n", " [41.62445 ]\n", " [48.559467]\n", " [52.52316 ]\n", " [71.1676 ]\n", " [70.77432 ]\n", " [62.99477 ]\n", " [87.01757 ]]\n", "150000 Cost: 3.2241697 \n", "Prediction:\n", " [[32.41367 ]\n", " [47.96407 ]\n", " [41.50442 ]\n", " [48.53065 ]\n", " [52.562054]\n", " [71.204895]\n", " [70.74354 ]\n", " [62.9931 ]\n", " [87.004776]]\n", "160000 Cost: 3.1181645 \n", "Prediction:\n", " [[32.337746]\n", " [48.150616]\n", " [41.397507]\n", " [48.504993]\n", " [52.59669 ]\n", " [71.23818 ]\n", " [70.71621 ]\n", " [62.99165 ]\n", " [86.993546]]\n", "170000 Cost: 3.0342064 \n", "Prediction:\n", " [[32.270657]\n", " [48.317078]\n", " [41.30261 ]\n", " [48.482285]\n", " [52.627686]\n", " [71.26753 ]\n", " [70.69159 ]\n", " [62.990288]\n", " [86.98288 ]]\n", "180000 Cost: 2.9679677 \n", "Prediction:\n", " [[32.211304]\n", " [48.46487 ]\n", " [41.218563]\n", " [48.46226 ]\n", " [52.655285]\n", " [71.2936 ]\n", " [70.66981 ]\n", " [62.98915 ]\n", " [86.9734 ]]\n", "190000 Cost: 2.9156418 \n", "Prediction:\n", " [[32.15726 ]\n", " [48.595116]\n", " [41.14301 ]\n", " [48.443886]\n", " [52.679176]\n", " [71.31704 ]\n", " [70.650665]\n", " [62.987972]\n", " [86.966 ]]\n", "200000 Cost: 2.8743722 \n", "Prediction:\n", " [[32.1107 ]\n", " [48.711536]\n", " [41.07696 ]\n", " [48.42818 ]\n", " [52.700962]\n", " [71.33752 ]\n", " [70.63346 ]\n", " [62.98708 ]\n", " [86.9584 ]]\n" ] } ], "source": [ "import tensorflow as tf\n", "x_data = [[19., 16.6, 13.], [23., 18.4, 10.], [26., 17.1, 12.],\n", " [29., 17.1, 10.], [30., 18.2, 10.], [43.,18.8, 7.],\n", " [44., 19.2, 8.], [38., 18.9, 9.], [55., 19.5, 5.]]\n", "y_data = [[33.], [51.], [40.], [49.], [50.], [69.], [70.], \n", " [64.], [89.]] \n", "\n", "# placeholders for a tensor that will be always fed.\n", "X = tf.placeholder(tf.float32, shape=[None, 3])\n", "Y = tf.placeholder(tf.float32, shape=[None, 1])\n", "\n", "W = tf.Variable(tf.random_normal([3, 1]), name='weight')\n", "b = tf.Variable(tf.random_normal([1]), name='bias')\n", "\n", "# Hypothesis\n", "hypothesis = tf.matmul(X, W) + b\n", "\n", "# Simplified cost/loss function\n", "cost = tf.reduce_mean(tf.square(hypothesis - Y))\n", "\n", "# Minimize\n", "optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)\n", "train = optimizer.minimize(cost)\n", "\n", "# Launch the graph in a session.\n", "sess = tf.Session()\n", "\n", "# Initializes global variables in the graph.\n", "sess.run(tf.global_variables_initializer())\n", "for step in range(200001):\n", " cost_val, hy_val, _ = sess.run([cost, hypothesis, train],\n", " feed_dict={X: x_data, Y: y_data})\n", " if step % 10000 == 0:\n", " print(step, \"Cost: \", cost_val, \"\\nPrediction:\\n\", hy_val)" ] } ], "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 }