abcd

Framework/Keras/Keras Assingment/Harsh_Task1/harsh.ipynb

@@ -0,0 +1,233 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from keras.utils.np_utils import to_categorical"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from keras.datasets import mnist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from keras.layers import Dense"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from keras.models import Sequential"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from keras.callbacks import CSVLogger"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "(X_train, Y_train),(X_test, Y_test) = mnist.load_data()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Sequential()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = X_train.reshape(X_train.shape[0],784)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test = X_test.reshape(X_test.shape[0], 784)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = X_train / 255\n",
+    "X_test = X_test / 255"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y_train = to_categorical(Y_train)\n",
+    "Y_test = to_categorical(Y_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.add(Dense(512,input_dim = 784 ,activation = 'relu'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.add(Dense(10,activation = 'softmax'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.compile(optimizer = 'adam',loss = 'categorical_crossentropy', metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train on 60000 samples, validate on 10000 samples\n",
+      "Epoch 1/10\n",
+      " - 9s - loss: 0.2155 - acc: 0.9375 - val_loss: 0.1092 - val_acc: 0.9667\n",
+      "Epoch 2/10\n",
+      " - 8s - loss: 0.0855 - acc: 0.9741 - val_loss: 0.0788 - val_acc: 0.9757\n",
+      "Epoch 3/10\n",
+      " - 8s - loss: 0.0547 - acc: 0.9832 - val_loss: 0.0802 - val_acc: 0.9748\n",
+      "Epoch 4/10\n",
+      " - 10s - loss: 0.0395 - acc: 0.9875 - val_loss: 0.0900 - val_acc: 0.9727\n",
+      "Epoch 5/10\n",
+      " - 11s - loss: 0.0285 - acc: 0.9907 - val_loss: 0.0681 - val_acc: 0.9796\n",
+      "Epoch 6/10\n",
+      " - 9s - loss: 0.0215 - acc: 0.9927 - val_loss: 0.0669 - val_acc: 0.9799\n",
+      "Epoch 7/10\n",
+      " - 9s - loss: 0.0166 - acc: 0.9949 - val_loss: 0.0857 - val_acc: 0.9759\n",
+      "Epoch 8/10\n",
+      " - 8s - loss: 0.0146 - acc: 0.9953 - val_loss: 0.0830 - val_acc: 0.9764\n",
+      "Epoch 9/10\n",
+      " - 8s - loss: 0.0107 - acc: 0.9965 - val_loss: 0.0695 - val_acc: 0.9833\n",
+      "Epoch 10/10\n",
+      " - 9s - loss: 0.0089 - acc: 0.9972 - val_loss: 0.0844 - val_acc: 0.9795\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x7f697dc77ac8>"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.fit(X_train,Y_train, validation_data=(X_test,Y_test),epochs = 10, batch_size = 50, verbose = 2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "accuracy = model.evaluate(X_test, Y_test, verbose=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy is 97.95\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"accuracy is %0.2f\" % (accuracy[-1]*100)) "
+   ]
+  },
+  {
+   "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
+}