StutiJain_Task1 (#66)

* Top90.txt Phase 1: Top90 words #32 * SutiJain_Task1 * Delete Top90.txt
oss2019 · Jul 25, 2019 · e9c8a1a · e9c8a1a
1 parent 7fb4872
commit e9c8a1a
Showing 1 changed file with 187 additions and 0 deletions.
diff --git a/Framework/Keras/Keras Assingment/StutiJain_Task1/StutiJain_ModelwithLogs.ipynb b/Framework/Keras/Keras Assingment/StutiJain_Task1/StutiJain_ModelwithLogs.ipynb
@@ -0,0 +1,187 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import tensorflow as tf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mnist = tf.keras.datasets.mnist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(x_train, y_train),(x_test, y_test) = mnist.load_data()\n",
+    "x_train = tf.keras.utils.normalize(x_train, axis=1)\n",
+    "x_test = tf.keras.utils.normalize(x_test, axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(60000, 28, 28)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(x_train.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = tf.keras.models.Sequential()\n",
+    "model.add(tf.keras.layers.Flatten())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/5\n",
+      "60000/60000 [==============================] - 13s 220us/sample - loss: 0.1988 - acc: 0.9397\n",
+      "Epoch 2/5\n",
+      "60000/60000 [==============================] - 13s 220us/sample - loss: 0.0810 - acc: 0.9751\n",
+      "Epoch 3/5\n",
+      "60000/60000 [==============================] - 13s 221us/sample - loss: 0.0522 - acc: 0.9832\n",
+      "Epoch 4/5\n",
+      "60000/60000 [==============================] - 13s 214us/sample - loss: 0.0386 - acc: 0.9873\n",
+      "Epoch 5/5\n",
+      "60000/60000 [==============================] - 13s 211us/sample - loss: 0.0287 - acc: 0.9905\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<tensorflow.python.keras.callbacks.History at 0x1c81ea137b8>"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.add(tf.keras.layers.Dense(512 ,activation=tf.nn.relu))\n",
+    "model.add(tf.keras.layers.Dense(512, 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=5)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<function matplotlib.pyplot.show(*args, **kw)>"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.imshow(x_train[0], cmap = plt.cm.binary)\n",
+    "plt.show"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "10000/10000 [==============================] - 1s 85us/sample - loss: 0.0844 - acc: 0.9782\n",
+      "Loss is 0.08439339621820836\n",
+      "Accuracy is 0.9782\n"
+     ]
+    }
+   ],
+   "source": [
+    "val_loss, val_acc = model.evaluate(x_test, y_test)\n",
+    "print(\"Loss is\", val_loss)\n",
+    "print(\"Accuracy is\",val_acc)"
+   ]
+  },
+  {
+   "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": "3.7.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}