{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","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":"<div class=\"alert alert-block alert-info\"><h1 style=\"text-align:center;color:black\"> Dogs Vs Cats Classification Problem 📷 🚀 </h1> </div> \nThe Dogs & Cats is a foundational problem for a basic CNN(convolutional neural network) model which involves classifying images as a dog or a cat.The dataset can be used for learning how to develop,evaluate and use convolutional deep learning neural networks for classification of images. This includes how to develop a robust test harness for estimating the performance of the model, exploring improvements for the model by changing the paramters of the model, saving and loading the model to make predicitions on new data.\n\n![1_EvMbMNRHm_aOf1n4tDO1Xg.jpg](attachment:0e084368-1f23-4445-a9d6-d0bd7fb563a7.jpg)","metadata":{},"attachments":{"0e084368-1f23-4445-a9d6-d0bd7fb563a7.jpg":{"image/jpeg":"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"}}},{"cell_type":"markdown","source":"<div class=\"alert alert-block alert-warning\"><h2 style=\"text-align:Center;color:black\">Table of Content </h2> </div>\n\n1. [Introduction 💥](#1)\n1. [Data Description](#2)\n1. [Loading Libraries📖](#3)\n1. [Data Extraction📁](#4)\n1. [Data Exploration📊](#5)\n1. [Train Test Split](#6)\n    1. [Using Dataframe](#7)\n    1. [Using Directory](#8)\n1. [Data Preparation 🛠️](#9)\n    1. [Image Data Generator](#10)\n        1. [Using DataFrame](#11)\n        1. [Using Directory](#12)\n1. [Deep learning Model ⚙️](#13)\n    1. [Model Layers](#14)\n    1. [Callbacks](#15)\n    1. [Compile Model](#23)\n    1. [Fit Model](#16)\n    1. [Plot Result](#17)\n    1. [Evaluvation](#18)\n1. [Prediction](#19)\n    1. [Visualize Classified Images](#20)\n1. [Submission](#21)\n1. [Conclusion](#22)","metadata":{}},{"cell_type":"markdown","source":"<a id='1'></a>\n<div class=\"alert alert-block alert-danger\"><h2 style=\"text-align:center;color:black\"> Introduction 💥</h2> </div> \n\nIn this article, we will discover how to develop a CNN to classify images of dogs and cats.\n\nAfter reading this article, you will know :\n\n* How to load and prepare the images for training purpose.\n* How to split data for training and validation purpose.\n* How to apply Data Augmentation to the data.\n* How to develop a CNN model using keras and how to choose various parameters for improving performance of the model.\n* How to evaluate performance of our model.\n* How to save and load a model for further predictions.\n* How to draw the confusion matrix for trained model.","metadata":{}},{"cell_type":"markdown","source":"<a id='2'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Data Description </h2> </div>\n\nThe training archive contains 25,000 images of dogs and cats. \n\nTrain your algorithm on these files and predict the labels for test1.zip.\n* **1 = dog**\n* **0 = cat**\n","metadata":{}},{"cell_type":"markdown","source":"<a id='3'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Loading Libraries </h2> </div> ","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,"execution":{"iopub.status.busy":"2024-03-26T14:45:34.657587Z","iopub.execute_input":"2024-03-26T14:45:34.658332Z","iopub.status.idle":"2024-03-26T14:45:34.665937Z","shell.execute_reply.started":"2024-03-26T14:45:34.658299Z","shell.execute_reply":"2024-03-26T14:45:34.664670Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='4'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Data Extraction </h2> </div>","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":{"execution":{"iopub.status.busy":"2024-03-26T14:45:34.668063Z","iopub.execute_input":"2024-03-26T14:45:34.668406Z","iopub.status.idle":"2024-03-26T14:45:46.116465Z","shell.execute_reply.started":"2024-03-26T14:45:34.668381Z","shell.execute_reply":"2024-03-26T14:45:46.115617Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-03-26T14:45:46.118214Z","iopub.execute_input":"2024-03-26T14:45:46.118558Z","iopub.status.idle":"2024-03-26T14:45:46.158430Z","shell.execute_reply.started":"2024-03-26T14:45:46.118528Z","shell.execute_reply":"2024-03-26T14:45:46.157417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='5'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Data Exploration </h2> </div>","metadata":{}},{"cell_type":"markdown","source":"First, we start by visualizing the variable of interest.\n\nLet's view more images in a grid format.\n\n<h5 style=\"text-align:center;color:Green\">We visualize few images of Dogs. </h5>","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,"execution":{"iopub.status.busy":"2024-03-26T14:45:46.159594Z","iopub.execute_input":"2024-03-26T14:45:46.159925Z","iopub.status.idle":"2024-03-26T14:45:48.348217Z","shell.execute_reply.started":"2024-03-26T14:45:46.159898Z","shell.execute_reply":"2024-03-26T14:45:48.347330Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h5 style=\"text-align:center;color:Red\">We visualize few images of Cats. </h5>","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,"execution":{"iopub.status.busy":"2024-03-26T14:45:48.350763Z","iopub.execute_input":"2024-03-26T14:45:48.351142Z","iopub.status.idle":"2024-03-26T14:45:49.779045Z","shell.execute_reply.started":"2024-03-26T14:45:48.351096Z","shell.execute_reply":"2024-03-26T14:45:49.778126Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Images are of varying size.\n\nEvery time the cell is run different set of images will be displayed, one can scan the images of both categories. Presence of humans in some images could be a challenge for the model to classify.\n\nSome images have more than one cats or dogs respectively.","metadata":{}},{"cell_type":"markdown","source":"<a id='6'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Train Test Split </h2> </div>","metadata":{}},{"cell_type":"markdown","source":"<a id='7'></a>\n<div class=\"alert alert-block alert-warning\"><h4 style=\"text-align:center;color:black\"> Using Dataframe </h4> </div>","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":{"execution":{"iopub.status.busy":"2024-03-26T14:45:49.780422Z","iopub.execute_input":"2024-03-26T14:45:49.780893Z","iopub.status.idle":"2024-03-26T14:45:49.849467Z","shell.execute_reply.started":"2024-03-26T14:45:49.780860Z","shell.execute_reply":"2024-03-26T14:45:49.848439Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Now we will Create a barplot to see the class distrubtion in trainting dataset.","metadata":{}},{"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,"execution":{"iopub.status.busy":"2024-03-26T14:45:49.850879Z","iopub.execute_input":"2024-03-26T14:45:49.851595Z","iopub.status.idle":"2024-03-26T14:45:50.647111Z","shell.execute_reply.started":"2024-03-26T14:45:49.851558Z","shell.execute_reply":"2024-03-26T14:45:50.646146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='8'></a>\n<div class=\"alert alert-block alert-warning\"><h4 style=\"text-align:center;color:black\"> Using Directory </h4> </div>","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,"execution":{"iopub.status.busy":"2024-03-26T14:45:50.648792Z","iopub.execute_input":"2024-03-26T14:45:50.649104Z","iopub.status.idle":"2024-03-26T14:45:54.137160Z","shell.execute_reply.started":"2024-03-26T14:45:50.649079Z","shell.execute_reply":"2024-03-26T14:45:54.136162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='9'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Data Preparation </h2> </div>\n\nfirstly, we will list out all the important parameters and respective values.","metadata":{}},{"cell_type":"code","source":"# parameters\nimage_size = 128\nimage_channel = 3\nbat_size = 32","metadata":{"execution":{"iopub.status.busy":"2024-03-26T14:45:54.138414Z","iopub.execute_input":"2024-03-26T14:45:54.138731Z","iopub.status.idle":"2024-03-26T14:45:54.145198Z","shell.execute_reply.started":"2024-03-26T14:45:54.138705Z","shell.execute_reply":"2024-03-26T14:45:54.144224Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='10'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\">Image Data Generator </h3> </div>\n\n* The data for will used by flow_from_dataframe and flow_from_directory.\n* The batch size is 32 and the image size is (128,128).\n","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":{"execution":{"iopub.status.busy":"2024-03-26T14:45:54.146153Z","iopub.execute_input":"2024-03-26T14:45:54.146404Z","iopub.status.idle":"2024-03-26T14:45:54.156571Z","shell.execute_reply.started":"2024-03-26T14:45:54.146382Z","shell.execute_reply":"2024-03-26T14:45:54.155694Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='11'></a>\n<div class=\"alert alert-block alert-warning\"><h4 style=\"text-align:center;color:black\"> Using Dataframe </h4> </div>","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2024-03-26T14:45:54.160772Z","iopub.execute_input":"2024-03-26T14:45:54.161056Z","iopub.status.idle":"2024-03-26T14:45:54.463694Z","shell.execute_reply.started":"2024-03-26T14:45:54.161032Z","shell.execute_reply":"2024-03-26T14:45:54.462989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='12'></a>\n<div class=\"alert alert-block alert-warning\"><h4 style=\"text-align:center;color:black\"> Using Directory </h4> </div>","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":{"execution":{"iopub.status.busy":"2024-03-26T14:45:54.464602Z","iopub.execute_input":"2024-03-26T14:45:54.464873Z","iopub.status.idle":"2024-03-26T14:45:55.151469Z","shell.execute_reply.started":"2024-03-26T14:45:54.464850Z","shell.execute_reply":"2024-03-26T14:45:55.150685Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='13'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Deep Learning Model </h2> </div>","metadata":{}},{"cell_type":"markdown","source":"<a id='14'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\">Model Layers </h3> </div>\n\n\n### Architecture\n\nThe architecture of the Cat vs Dog Image Classification model consists of the following Layers and components:\n\n#### Layers :\n* The input layer consist of a Conv2D with 32 filters and activation relu.\n* The model contain the 3 blocks of convolution with increasing filters and activation relu.\n* Each convolution block contains Batch Noramlization, Max pooling (pool_size = 2) and Dropout (0.2).\n* The fully connected layers contain Flatten layer, Dense layer with 512 units and a Dropout layer.\n* The output layer is a Dense layer with 2 units and softmax activation.\n\n#### Components:\n\n* **Input Layer:** Receives input images for classification.\n* **Convolutional Layers:** Extract features from the images through convolutional operations.\n* **Pooling Layers:** Reduce the spatial dimensions of the feature maps.\n* **Flatten Layer:** Convert the 2D feature maps into a 1D vector.\n* **Fully Connected Layers:** Perform classification using densely connected layers.\n* **Output Layer:** Provides the final prediction probabilities for cat and dog classes.","metadata":{}},{"cell_type":"code","source":"# model = Sequential()\n\n# # Input Layer\n# model.add(Conv2D(32,(3,3),activation='relu',input_shape = (image_size,image_size,image_channel))) \n# model.add(BatchNormalization())\n# model.add(MaxPooling2D(pool_size=(2,2)))\n# model.add(Dropout(0.2))\n\n# # Bloack 1 \n# model.add(Conv2D(64,(3,3),activation='relu'))\n# model.add(BatchNormalization())\n# model.add(MaxPooling2D(pool_size=(2,2)))\n# model.add(Dropout(0.2))\n# # Block 2\n# model.add(Conv2D(128,(3,3),activation='relu'))\n# model.add(BatchNormalization())\n# model.add(MaxPooling2D(pool_size=(2,2)))\n# model.add(Dropout(0.2))\n# # Block 3\n# model.add(Conv2D(256,(3,3),activation='relu'))\n# model.add(BatchNormalization())\n# model.add(MaxPooling2D(pool_size=(2,2)))\n# model.add(Dropout(0.2))\n\n# # Fully Connected layers \n# model.add(Flatten())\n# model.add(Dense(512,activation='relu'))\n# model.add(BatchNormalization())\n# model.add(Dropout(0.2))\n\n# # Output layer\n# model.add(Dense(2,activation='softmax'))\n\n# model.summary()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-03-26T14:45:55.152592Z","iopub.execute_input":"2024-03-26T14:45:55.152897Z","iopub.status.idle":"2024-03-26T14:45:55.157696Z","shell.execute_reply.started":"2024-03-26T14:45:55.152872Z","shell.execute_reply":"2024-03-26T14:45:55.156779Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_classes = 2","metadata":{"execution":{"iopub.status.busy":"2024-03-26T14:45:55.159002Z","iopub.execute_input":"2024-03-26T14:45:55.159352Z","iopub.status.idle":"2024-03-26T14:45:55.166579Z","shell.execute_reply.started":"2024-03-26T14:45:55.159318Z","shell.execute_reply":"2024-03-26T14:45:55.165695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\n\n# Khởi tạo mô hình\nmodel = Sequential()\n\n# Thêm lớp convolution với 32 bộ lọc, kích thước cửa sổ 3x3 và hàm kích hoạt relu\nmodel.add(Conv2D(32, (3, 3), activation='relu', input_shape=(image_size,image_size,image_channel)))\n\n# Thêm lớp pooling với kích thước cửa sổ 2x2\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\n# Thêm lớp convolution với 64 bộ lọc, kích thước cửa sổ 3x3 và hàm kích hoạt relu\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\n\n# Thêm lớp pooling với kích thước cửa sổ 2x2\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\n# Thêm lớp convolution với 128 bộ lọc, kích thước cửa sổ 3x3 và hàm kích hoạt relu\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\n\n# Thêm lớp pooling với kích thước cửa sổ 2x2\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\n# Làm phẳng dữ liệu đầu ra từ các lớp convolution/pooling trước đó\nmodel.add(Flatten())\n\n# Thêm lớp fully connected với 128 đơn vị và hàm kích hoạt relu\nmodel.add(Dense(128, activation='relu'))\n\n# Lớp đầu ra với số lượng lớp tương ứng với số lớp của bài toán phân loại\nmodel.add(Dense(num_classes, activation='softmax'))\n\n# Compile mô hình với hàm loss là categorical crossentropy, optimizer là adam và metrics là accuracy\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n\n# In tóm tắt kiến trúc của mô hình\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2024-03-26T14:45:55.167907Z","iopub.execute_input":"2024-03-26T14:45:55.168273Z","iopub.status.idle":"2024-03-26T14:45:55.279106Z","shell.execute_reply.started":"2024-03-26T14:45:55.168240Z","shell.execute_reply":"2024-03-26T14:45:55.278250Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='15'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\"> Callbacks </h3> </div>\nwe will be using two callbacks -\n\n* **ReduceLROnPlateau :** Reduce learning rate when a metric has stopped improving.\n* **EarlyStopping :** Stop training when a monitored metric has stopped improving.","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":{"execution":{"iopub.status.busy":"2024-03-26T14:45:55.280018Z","iopub.execute_input":"2024-03-26T14:45:55.280260Z","iopub.status.idle":"2024-03-26T14:45:55.285005Z","shell.execute_reply.started":"2024-03-26T14:45:55.280239Z","shell.execute_reply":"2024-03-26T14:45:55.284136Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='23'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\"> Compile the model </h3> </div>\nFinally we will compile the model .There are 3 things to mention here : Optimizer,Loss, Metrics\n\n* **Optimizer** :- To minimize cost function we use different methods For ex :- like gradient descent, stochastic gradient descent. So these are call optimizers. We are using a default one here which is adam.\n​\n* **Loss** :- To make our model better we either minimize loss or maximize accuracy. Neural Networks always minimize loss. To measure it we can use different formulas like 'categorical_crossentropy' or 'binary_crossentropy'. Here I have used binary_crossentropy.\n​\n* **Metrics** :- This is to denote the measure of your model. Can be accuracy or some other metric.","metadata":{}},{"cell_type":"code","source":"model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2024-03-26T14:45:55.286297Z","iopub.execute_input":"2024-03-26T14:45:55.286657Z","iopub.status.idle":"2024-03-26T14:45:55.296120Z","shell.execute_reply.started":"2024-03-26T14:45:55.286612Z","shell.execute_reply":"2024-03-26T14:45:55.295185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='16'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\"> Fit the model </h3> </div>\n\nWe are now going to train our compiled model using the train iterator (train_generator) and use the val iterator (val_generator) as a validation dataset during training.\n\nThe number of steps for the train and validation iterators must be specified. This is the number of batches that will comprise one epoch. This can be specified via the length of each iterator, and will be the total number of images in the train and validation directories divided by the batch size (32).\n\nThe model will be fit for 30 epochs.","metadata":{}},{"cell_type":"code","source":"cat_dog = model.fit(train_generator,\n                    validation_data = val_generator, \n                    callbacks=[early_stoping,learning_rate_reduction],\n                    epochs = 3,\n                    # steps_per_epoch = len(train_generator),\n                    # validation_steps = len(val_generaotor),\n                   )","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-03-26T14:45:55.297296Z","iopub.execute_input":"2024-03-26T14:45:55.298094Z","iopub.status.idle":"2024-03-26T14:50:45.254827Z","shell.execute_reply.started":"2024-03-26T14:45:55.298066Z","shell.execute_reply":"2024-03-26T14:50:45.253971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='17'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\"> Plot the results </h3> </div>","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,"execution":{"iopub.status.busy":"2024-03-26T14:50:45.256054Z","iopub.execute_input":"2024-03-26T14:50:45.256335Z","iopub.status.idle":"2024-03-26T14:50:46.113123Z","shell.execute_reply.started":"2024-03-26T14:50:45.256311Z","shell.execute_reply":"2024-03-26T14:50:46.112209Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='18'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\"> Evaluvation </h3> </div>\n\nwe will evaluvate the Training and validation data accuracy and loss.","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,"execution":{"iopub.status.busy":"2024-03-26T14:50:46.114250Z","iopub.execute_input":"2024-03-26T14:50:46.114541Z","iopub.status.idle":"2024-03-26T14:52:19.106000Z","shell.execute_reply.started":"2024-03-26T14:50:46.114516Z","shell.execute_reply":"2024-03-26T14:52:19.104914Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-03-26T14:52:19.107237Z","iopub.execute_input":"2024-03-26T14:52:19.107549Z","iopub.status.idle":"2024-03-26T14:52:19.196924Z","shell.execute_reply.started":"2024-03-26T14:52:19.107522Z","shell.execute_reply":"2024-03-26T14:52:19.195907Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='19'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Prediction </h2> </div>\n\nNow, we will predict the model on test dataset.","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":{"execution":{"iopub.status.busy":"2024-03-26T14:57:56.683912Z","iopub.execute_input":"2024-03-26T14:57:56.684300Z","iopub.status.idle":"2024-03-26T14:58:03.548580Z","shell.execute_reply.started":"2024-03-26T14:57:56.684270Z","shell.execute_reply":"2024-03-26T14:58:03.547617Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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,"execution":{"iopub.status.busy":"2024-03-26T14:58:07.529726Z","iopub.execute_input":"2024-03-26T14:58:07.530764Z","iopub.status.idle":"2024-03-26T14:58:07.547212Z","shell.execute_reply.started":"2024-03-26T14:58:07.530727Z","shell.execute_reply":"2024-03-26T14:58:07.546286Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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,"execution":{"iopub.status.busy":"2024-03-26T14:58:34.022078Z","iopub.execute_input":"2024-03-26T14:58:34.022719Z","iopub.status.idle":"2024-03-26T14:58:34.310791Z","shell.execute_reply.started":"2024-03-26T14:58:34.022687Z","shell.execute_reply":"2024-03-26T14:58:34.309700Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='20'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> submission </h2> </div>\nMake predictions on kaggle test data for 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,"execution":{"iopub.status.busy":"2024-03-26T14:58:41.810264Z","iopub.execute_input":"2024-03-26T14:58:41.810993Z","iopub.status.idle":"2024-03-26T14:58:57.811484Z","shell.execute_reply.started":"2024-03-26T14:58:41.810961Z","shell.execute_reply":"2024-03-26T14:58:57.810703Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id='21'></a>\n<div class=\"alert alert-block alert-danger\"><h3 style=\"text-align:center;color:black\"> Visualize Classified Images  </h3> </div>","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,"execution":{"iopub.status.busy":"2024-03-26T14:58:59.616381Z","iopub.execute_input":"2024-03-26T14:58:59.616778Z","iopub.status.idle":"2024-03-26T14:59:01.054248Z","shell.execute_reply.started":"2024-03-26T14:58:59.616744Z","shell.execute_reply":"2024-03-26T14:59:01.053357Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"After watching the images we can see the our model is quite accurate with 94% accuracy.","metadata":{}},{"cell_type":"markdown","source":"\n<a id='22'></a>\n<div class=\"alert alert-block alert-info\"><h2 style=\"text-align:center;color:black\"> Conclusion </h2> </div>\n\n\nWe successfully built a deep neural network model by implementing Convolutional Neural Network (CNN) to classify dog and cat images with very high accuracy 97.32 %. \n\nThe model was used to predict the classes of the images from the independent test set and results were submitted to test the accuracy of the prediction with fresh data.\n\nThe Cat vs Dog Image Classification model demonstrates the successful implementation of a Convolutional Neural Network for image classification tasks. By accurately distinguishing between images of cats and dogs, this project showcases the potential of deep learning algorithms in solving real-world problems involving image analysis. Through this project, we aim to inspire further exploration of CNNs and their applications in various domains,","metadata":{}}]}