sanjushekhawat submission: Predicting Pneumonia using CNN

sanjushekhawt57@gmail.com/sanju_cnn.ipynb

@@ -0,0 +1,153 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tensorflow\n",
+    "import tensorflow.keras\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Convolution2D\n",
+    "from tensorflow.keras.layers import MaxPooling2D\n",
+    "from tensorflow.keras.layers import Flatten\n",
+    "from tensorflow.keras.layers import Dense\n",
+    "from tensorflow.keras.layers import Reshape\n",
+    "\n",
+    "classifier =  Sequential()\n",
+    "\n",
+    "classifier.add(Convolution2D(32,(3,3),input_shape=(64,64,3),activation='relu'))\n",
+    "classifier.add(MaxPooling2D(pool_size=(2,2)))\n",
+    "\n",
+    "classifier.add(Convolution2D(32,(3,3),input_shape=(64,64,3),activation='relu'))\n",
+    "classifier.add(MaxPooling2D(pool_size=(2,2)))\n",
+    "\n",
+    "classifier.add(Convolution2D(32,(3,3),input_shape=(64,64,3),activation='relu'))\n",
+    "classifier.add(MaxPooling2D(pool_size=(2,2)))\n",
+    "\n",
+    "\n",
+    "classifier.add(Convolution2D(32,(3,3),input_shape=(64,64,3),activation='relu'))\n",
+    "classifier.add(MaxPooling2D(pool_size=(2,2)))\n",
+    "\n",
+    "\n",
+    "classifier.add(Flatten())\n",
+    "classifier.add(Dense(units=128,activation='relu'))\n",
+    "classifier.add(Dense(units=1,activation='sigmoid'))\n",
+    "classifier.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])\n",
+    "\n",
+    "print(classifier.summary())\n",
+    "\n",
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "\n",
+    "train_datagen=ImageDataGenerator(rescale=1/1.255,shear_range=0.2,zoom_range=0.2,horizontal_flip=True)\n",
+    "test_datagen = ImageDataGenerator(rescale=1./255)\n",
+    "training_set = train_datagen.flow_from_directory(\n",
+    "        'C:/Users/rishi/OneDrive/Desktop/chest_xray/chest_xray/train',\n",
+    "        target_size=(64, 64),\n",
+    "        batch_size=32,\n",
+    "        class_mode='binary')\n",
+    "\n",
+    "test_set = train_datagen.flow_from_directory(\n",
+    "        'C:/Users/rishi/OneDrive/Desktop/chest_xray/chest_xray/test',\n",
+    "        target_size=(64, 64),\n",
+    "        batch_size=32,\n",
+    "        class_mode='binary')\n",
+    "\n",
+    "val_set = train_datagen.flow_from_directory(\n",
+    "        'C:/Users/rishi/OneDrive/Desktop/chest_xray/chest_xray/val',\n",
+    "        target_size=(64, 64),\n",
+    "        batch_size=32,\n",
+    "        class_mode='binary')\n",
+    "\n",
+    "cl=classifier.fit_generator(\n",
+    "        training_set,\n",
+    "        steps_per_epoch=163,\n",
+    "        epochs=10,\n",
+    "        validation_data=test_set,\n",
+    "        validation_steps=624/32)\n",
+    " \n",
+    "\n",
+    "from sklearn.metrics import classification_report, confusion_matrix\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "labels = test_set.class_indices\n",
+    "\n",
+    "labels = {v: k for k, v in labels.items()}\n",
+    "\n",
+    "classes = list(labels.values())\n",
+    "\n",
+    "y_pred = classifier.predict(test_set)\n",
+    "\n",
+    "y_pred =(y_pred>0.5)\n",
+    "\n",
+    "print(confusion_matrix(test_set.classes, y_pred))\n",
+    "\n",
+    "print(classification_report(test_set.classes, y_pred, target_names=classes))\n",
+    "print(labels)\n",
+    "\n",
+    "\n",
+    "test_accuracy=classifier.evaluate_generator(test_set,624)\n",
+    "print(\"Test accuracy:\",test_accuracy[1]*100,'%')\n",
+    "\n",
+    "\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "print(accuracy_score(test_set.classes, y_pred))\n",
+    "\n",
+    "from sklearn.metrics import recall_score\n",
+    "recall_score(test_set.classes, y_pred)\n",
+    "\n",
+    "from sklearn.metrics import precision_score\n",
+    "precision_score(test_set.classes, y_pred)\n",
+    "\n",
+    "from sklearn.metrics import f1_score\n",
+    "f1_score(test_set.classes, y_pred)\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.plot(cl.history['acc'])\n",
+    "plt.plot(cl.history['val_acc'])\n",
+    "plt.title('Model Accuracy')\n",
+    "plt.ylabel('Accuracy')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(['training_set', 'test_set'], loc='upper left')\n",
+    "plt.show()\n",
+    "\n",
+    "#Loss\n",
+    "plt.plot(cl.history['loss'])\n",
+    "plt.plot(cl.history['val_loss'])\n",
+    "plt.title('Loss')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.legend(['training_set', 'test_set'], loc='upper left')\n",
+    "plt.show()\n"
+   ]
+  }
+ ],
+ "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
+}