{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"},{"sourceId":5441,"databundleVersionId":38425,"sourceType":"competition"},{"sourceId":791828,"sourceType":"datasetVersion","datasetId":119698},{"sourceId":1003830,"sourceType":"datasetVersion","datasetId":550917}],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":" Loading Libraries ","metadata":{}},{"cell_type":"code","source":"# Basic\nimport os\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\nfrom random import seed\nfrom random import random\nimport numpy as np\nimport pandas as pd\n\n# visuals\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom matplotlib.image import imread\nfrom PIL import Image\n\n# Scikit-learn\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import classification_report,confusion_matrix,ConfusionMatrixDisplay\n\n# Tensorflow\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.layers import Dense,MaxPooling2D,Dropout,Flatten,BatchNormalization,Conv2D\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau,EarlyStopping","metadata":{"_kg_hide-output":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Data Extraction","metadata":{}},{"cell_type":"code","source":"train_path = \"../input/dogs-vs-cats/test1.zip\"\ntest_path = \"../input/dogs-vs-cats/train.zip\"\n\nfiles = \"/kaggle/working/\"\n\nimport zipfile\n\nwith zipfile.ZipFile(train_path, 'r') as zipp:\n    zipp.extractall(files)\n    \nwith zipfile.ZipFile(test_path, 'r') as zipp:\n    zipp.extractall(files)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Loading Images in a Dataframe","metadata":{}},{"cell_type":"code","source":"image_dir = \"../working/train/\"\n\nfilenames = os.listdir(image_dir)\nlabels = [x.split(\".\")[0] for x in filenames]\n\ndata = pd.DataFrame({\"filename\": filenames, \"label\": labels})\n\ndata.head()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Visualize few images of Dogs","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(20,20)) # specifying the overall grid size\nplt.subplots_adjust(hspace=0.4)\n\n\nfor i in range(10):\n    \n    plt.subplot(1,10,i+1)    # the number of images in the grid is 10*10 (100)\n    filename = 'train/' + 'dog.' + str(i) + '.jpg'\n    image = imread(filename)\n    plt.imshow(image)\n    plt.title('Dog',fontsize=12)\n    plt.axis('off')\n\nplt.show()","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Visualize few images of Cats","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(20,20)) # specifying the overall grid size\nplt.subplots_adjust(hspace=0.4)\n\n\nfor i in range(10):\n    \n    plt.subplot(1,10,i+1)    # the number of images in the grid is 10*10 (100)\n    filename = 'train/' + 'cat.' + str(i) + '.jpg'\n    image = imread(filename)\n    plt.imshow(image)\n    plt.title('Cat',fontsize=12)\n    plt.axis('off')\n\nplt.show()","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Train Test Split","metadata":{}},{"cell_type":"code","source":"# train test split using dataframe\n\nlabels = data['label']\n\nX_train, X_temp = train_test_split(data, test_size=0.2, stratify=labels, random_state = 42)\n\nlabel_test_val = X_temp['label']\n\nX_test, X_val = train_test_split(X_temp, test_size=0.5, stratify=label_test_val, random_state = 42)\n\nprint('The shape of train data',X_train.shape)\nprint('The shape of test data',X_test.shape)\nprint('The shape of validation data',X_val.shape)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"labels = ['Cat','Dog']\n\nlabel1,count1 = np.unique(X_train.label,return_counts=True)\nlabel2,count2 = np.unique(X_val.label,return_counts=True)\nlabel3,count3 = np.unique(X_test.label,return_counts=True)\n\nuni1 = pd.DataFrame(data=count1,index=labels,columns=['Count1'])\nuni2 = pd.DataFrame(data=count2,index=labels,columns=['Count2'])\nuni3 = pd.DataFrame(data=count3,index=labels,columns=['Count3'])\n\n\nplt.figure(figsize=(20,6),dpi=200)\nsns.set_style('darkgrid')\n\nplt.subplot(131)\nsns.barplot(data=uni1,x=uni1.index,y='Count1',palette='icefire',width=0.2).set_title('Class distribution in Training set',fontsize=15)\nplt.xlabel('Labels',fontsize=12)\nplt.ylabel('Count',fontsize=12)\n\nplt.subplot(132)\nsns.barplot(data=uni2,x=uni2.index,y='Count2',palette='icefire',width=0.2).set_title('Class distribution in validation set',fontsize=15)\nplt.xlabel('Labels',fontsize=12)\nplt.ylabel('Count',fontsize=12)\n\n\nplt.subplot(133)\nsns.barplot(data=uni3,x=uni3.index,y='Count3',palette='icefire',width=0.2).set_title('Class distribution in Testing set',fontsize=15)\nplt.xlabel('Labels',fontsize=12)\nplt.ylabel('Count',fontsize=12)\n\nplt.show()","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Using Directory","metadata":{}},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/']\n\nfor subdir in subdirs:\n    # create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = dataset_home + subdir + labldir\n        makedirs(newdir, exist_ok=True)\n# seed random number generator\nseed(1)\n# define ratio of pictures to use for validation\nval_ratio = 0.2\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\nfor file in listdir(src_directory):\n        src = src_directory + '/' + file\n        dst_dir = 'train/'\n        if random() < val_ratio:\n            dst_dir = 'test/'\n        if file.startswith('cat'):\n            dst = dataset_home + dst_dir + 'cats/' + file\n            copyfile(src, dst)\n        elif file.startswith('dog'):\n            dst = dataset_home + dst_dir + 'dogs/' + file\n            copyfile(src, dst)\n\n            \npath1 = \"/kaggle/working/dataset_dogs_vs_cats/train/cats\"\npath2 = \"/kaggle/working/dataset_dogs_vs_cats/train/dogs\"\npath3 = \"/kaggle/working/dataset_dogs_vs_cats/test/cats\"\npath4 = \"/kaggle/working/dataset_dogs_vs_cats/test/dogs\"\n\n\nprint('Then number of cat images in training data is' ,len(os.listdir(path1)))\nprint('Then number of dog images in training data is' ,len(os.listdir(path2)))\nprint('Then number of cat images in validation data is' ,len(os.listdir(path3)))\nprint('Then number of dog images in validation data is' ,len(os.listdir(path4)))\n","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Data Preparation","metadata":{}},{"cell_type":"code","source":"# parameters\nimage_size = 128\nimage_channel = 3\nbat_size = 32","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Image Data Generator ","metadata":{}},{"cell_type":"code","source":"# Creating image data generator\ntrain_datagen = ImageDataGenerator(rescale=1./255,\n                                    rotation_range = 15,\n                                    horizontal_flip = True,\n                                    zoom_range = 0.2,\n                                    shear_range = 0.1,\n                                    fill_mode = 'reflect',\n                                    width_shift_range = 0.1,\n                                    height_shift_range = 0.1)\n\ntest_datagen = ImageDataGenerator(rescale=1./255)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Applying image data gernerator to train and test data\n\ntrain_generator = train_datagen.flow_from_dataframe(X_train,\n                                                    directory = 'train/',\n                                                    x_col= 'filename',\n                                                    y_col= 'label',\n                                                    batch_size = bat_size,\n                                                    target_size = (image_size,image_size)\n                                                   )\nval_generator = test_datagen.flow_from_dataframe(X_val, \n                                                 directory = 'train/',\n                                                 x_col= 'filename',\n                                                 y_col= 'label',\n                                                 batch_size = bat_size,\n                                                 target_size = (image_size,image_size),\n                                                 shuffle=False\n                                                )\n\ntest_generator = test_datagen.flow_from_dataframe(X_test, \n                                                  directory = 'train/',\n                                                  x_col= 'filename',\n                                                  y_col= 'label',\n                                                  batch_size = bat_size,\n                                                  target_size = (image_size,image_size),\n                                                  shuffle=False\n                                                 )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Using Directory","metadata":{}},{"cell_type":"code","source":"train_gen = train_datagen.flow_from_directory('/kaggle/working/dataset_dogs_vs_cats/train/', \n                                              class_mode='binary',\n                                              target_size = (image_size,image_size),\n                                              batch_size = bat_size,\n                                             )\n\nval_gen = test_datagen.flow_from_directory('/kaggle/working/dataset_dogs_vs_cats/test/', \n                                          class_mode='binary',\n                                          batch_size = bat_size,\n                                          target_size = (image_size,image_size),\n                                          shuffle = False\n                                         )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Deep Learning Model ","metadata":{}},{"cell_type":"code","source":"model = Sequential()\n\n# Input Layer\nmodel.add(Conv2D(32,(3,3),activation='relu',input_shape = (image_size,image_size,image_channel))) \nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.2))\n\n# Bloack 1 \nmodel.add(Conv2D(64,(3,3),activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.2))\n# Block 2\nmodel.add(Conv2D(128,(3,3),activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.2))\n# Block 3\nmodel.add(Conv2D(256,(3,3),activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.2))\n\n# Fully Connected layers \nmodel.add(Flatten())\nmodel.add(Dense(512,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.2))\n\n# Output layer\nmodel.add(Dense(2,activation='softmax'))\n\nmodel.summary()","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Callbacks","metadata":{}},{"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor = 'val_accuracy',\n                                            patience=2,\n                                            factor=0.5,\n                                            min_lr = 0.00001,\n                                            verbose = 1)\n\nearly_stoping = EarlyStopping(monitor='val_loss',patience= 3,restore_best_weights=True,verbose=0)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"cat_dog = model.fit(train_generator,\n                    validation_data = val_generator, \n                    callbacks=[early_stoping,learning_rate_reduction],\n                    epochs = 30,\n                    # steps_per_epoch = len(train_generator),\n                    # validation_steps = len(val_generaotor),\n                   )","metadata":{"_kg_hide-output":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Plot the results","metadata":{}},{"cell_type":"code","source":"# plots for accuracy and Loss with epochs\n\nerror = pd.DataFrame(cat_dog.history)\n\nplt.figure(figsize=(18,5),dpi=200)\nsns.set_style('darkgrid')\n\nplt.subplot(121)\nplt.title('Cross Entropy Loss',fontsize=15)\nplt.xlabel('Epochs',fontsize=12)\nplt.ylabel('Loss',fontsize=12)\nplt.plot(error['loss'])\nplt.plot(error['val_loss'])\n\nplt.subplot(122)\nplt.title('Classification Accuracy',fontsize=15)\nplt.xlabel('Epochs',fontsize=12)\nplt.ylabel('Accuracy',fontsize=12)\nplt.plot(error['accuracy'])\nplt.plot(error['val_accuracy'])\n\nplt.show()","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Evaluvation","metadata":{}},{"cell_type":"code","source":"# Evaluvate for train generator\nloss,acc = model.evaluate(train_generator,batch_size = bat_size, verbose = 0)\n\nprint('The accuracy of the model for training data is:',acc*100)\nprint('The Loss of the model for training data is:',loss)\n\n# Evaluvate for validation generator\nloss,acc = model.evaluate(val_generator,batch_size = bat_size, verbose = 0)\n\nprint('The accuracy of the model for validation data is:',acc*100)\nprint('The Loss of the model for validation data is:',loss)","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Finally, we will save the model for future use.","metadata":{}},{"cell_type":"code","source":"# Save the Model\nmodel.save(\"model.h5\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Prediction ","metadata":{}},{"cell_type":"code","source":"# prediction\nresult = model.predict(test_generator,batch_size = bat_size,verbose = 0)\n\ny_pred = np.argmax(result, axis = 1)\n\ny_true = test_generator.labels\n\n# Evaluvate\nloss,acc = model.evaluate(test_generator, batch_size = bat_size, verbose = 0)\n\nprint('The accuracy of the model for testing data is:',acc*100)\nprint('The Loss of the model for testing data is:',loss)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Classification report","metadata":{}},{"cell_type":"code","source":"labels =['Cat','Dog']\nprint(classification_report(y_true, y_pred,target_names=labels))","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"confusioin matrix","metadata":{}},{"cell_type":"code","source":"confusion_mtx = confusion_matrix(y_true,y_pred) \n\nf,ax = plt.subplots(figsize = (8,4),dpi=200)\nsns.heatmap(confusion_mtx, annot=True, linewidths=0.1, cmap = \"gist_yarg_r\", linecolor=\"black\", fmt='.0f', ax=ax,cbar=False, xticklabels=labels, yticklabels=labels)\n\nplt.xlabel(\"Predicted Label\",fontsize=10)\nplt.ylabel(\"True Label\",fontsize=10)\nplt.title(\"Confusion Matrix\",fontsize=13)\n\nplt.show()","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"submission ","metadata":{}},{"cell_type":"code","source":"size =(128,128)\n\n# loading into dataframe\ntest_dir = \"../working/test1/\"\nfilenames = os.listdir(test_dir)\ntest_data = pd.DataFrame({\"filename\": filenames})\ntest_data['label'] = 'unknown'\n\n# Create data genenerator for test data\ntest1_idg =  test_datagen.flow_from_dataframe(test_data, \n                                     \"test1/\", \n                                     x_col= \"filename\",\n                                     y_col = 'label',\n                                     batch_size = bat_size,\n                                     target_size=size, \n                                     shuffle = False)\n\n# Test Prediction\ntest1_predict = model.predict(test1_idg,verbose = 0)\n\ntest1_predict_argmax = np.argmax(test1_predict, axis=1)\n\ny_test_pred = test1_predict_argmax\n\ntest_data['label'] = y_test_pred\n\n# mapping\nlabel_mapping = {0: 'cat', 1: 'dog'}\ntest_data['label'] = test_data['label'].map(label_mapping)\ntest_data.head()\n\n# csv file output for submission\nsub = pd.read_csv('/kaggle/input/dogs-vs-cats/sampleSubmission.csv',index_col='id')\n\nsub['label'] = y_test_pred\n\nsub.to_csv('submission.csv',index=True)","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":" Visualize Classified Images","metadata":{}},{"cell_type":"code","source":"fig, axes = plt.subplots(1, 10, figsize=(20, 4))\nfor idx in range(10):\n    image_path = os.path.join(test_dir, test_data.iloc[idx]['filename'])\n    image = Image.open(image_path)\n    axes[idx].imshow(image)\n    axes[idx].set_title(\"Label: \" + test_data.iloc[idx]['label'])\n    axes[idx].axis('off')\nplt.show()","metadata":{"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"After watching the images we can see the our model is quite accurate with 94% accuracy.","metadata":{}}]}