{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 1. Import Library","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')\n\nimport os\nimport shutil\nimport itertools\nimport pathlib\nfrom PIL import Image\n\nimport cv2\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom sklearn.metrics import confusion_matrix , classification_report, ConfusionMatrixDisplay\nfrom sklearn.model_selection import train_test_split\n\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D , MaxPooling2D , Dense , BatchNormalization , Dropout,Flatten , Activation\nfrom tensorflow.keras.optimizers import Adam , Adamax\nfrom tensorflow.keras import regularizers\n\nsns.set_style('whitegrid')","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:23:54.690532Z","iopub.execute_input":"2024-01-26T11:23:54.690856Z","iopub.status.idle":"2024-01-26T11:24:08.032131Z","shell.execute_reply.started":"2024-01-26T11:23:54.690809Z","shell.execute_reply":"2024-01-26T11:24:08.031307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 2. Prepare Data","metadata":{}},{"cell_type":"code","source":"!unzip /kaggle/input/dogs-vs-cats/train.zip","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!unzip /kaggle/input/dogs-vs-cats/test1.zip","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 3. Create Path\n","metadata":{}},{"cell_type":"code","source":"path , dirs , files = next(os.walk('/kaggle/working/train'))\nfile_count = len(files)\nprint(file_count)\nbase_dir = '/kaggle/working/dogs_vs_cats_small'\nos.mkdir(base_dir)","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:35:21.093536Z","iopub.execute_input":"2024-01-26T11:35:21.093960Z","iopub.status.idle":"2024-01-26T11:35:21.131453Z","shell.execute_reply.started":"2024-01-26T11:35:21.093927Z","shell.execute_reply":"2024-01-26T11:35:21.130581Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 4. Create Directories for Train , Test and Validation Data\n","metadata":{}},{"cell_type":"code","source":"train_dir = os.path.join(base_dir , 'train')\nos.mkdir(train_dir) #make a new train directory inside my base directory\n\nvalid_dir= os.path.join(base_dir , 'validation')\nos.mkdir(valid_dir) #make a new validation directory inside my base directory\n\ntest_dir = os.path.join(base_dir , 'test')\nos.mkdir(test_dir) #make a new test directory inside my base directory\n\ntrain_cats_dir = os.path.join(train_dir , 'cats')\nos.mkdir(train_cats_dir) #make a new cats directory inside my train directory\n\ntrain_dogs_dir = os.path.join(train_dir , 'dogs')\nos.mkdir(train_dogs_dir) #make a new dogs directory inside my train directory\n\nvalid_cats_dir = os.path.join(valid_dir, 'cats')\nos.mkdir(valid_cats_dir) #make a new cats directory inside my validation directory\n\nvalid_dogs_dir = os.path.join(valid_dir , 'dogs')\nos.mkdir(valid_dogs_dir) #make a new dogs directory inside my validation directory\n\ntest_cats_dir = os.path.join(test_dir , 'cats')\nos.mkdir(test_cats_dir) #make a new cats directory inside my test directory\n\ntest_dogs_dir = os.path.join(test_dir , 'dogs')\nos.mkdir(test_dogs_dir) #make a new dogs directory inside my test directory","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:35:26.273402Z","iopub.execute_input":"2024-01-26T11:35:26.274074Z","iopub.status.idle":"2024-01-26T11:35:26.282928Z","shell.execute_reply.started":"2024-01-26T11:35:26.274039Z","shell.execute_reply":"2024-01-26T11:35:26.282036Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dir_path = '/kaggle/working/train'\n\ncat_count = 0\ndog_count= 0\nfor i in os.listdir(dir_path):\n    if i.startswith('cat.'):\n        cat_count += 1\n    elif i.startswith('dog.'):\n        dog_count += 1\n        \nprint(f\"Number of cat images: {cat_count}\")\nprint(f\"Number of dog images: {dog_count}\")","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:35:31.062743Z","iopub.execute_input":"2024-01-26T11:35:31.063454Z","iopub.status.idle":"2024-01-26T11:35:31.093274Z","shell.execute_reply.started":"2024-01-26T11:35:31.063425Z","shell.execute_reply":"2024-01-26T11:35:31.092346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 5. Separate Train, Test and Validation Data","metadata":{}},{"cell_type":"code","source":"original_dataset_dir = '/kaggle/working/train'\n\n# Create lists of file names for cat images in each set\nfnames = ['cat.{}.jpg'.format(i) for i in range(10001)]  # Move 10,000 cat images to the train cat directory\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(train_cats_dir, fname)\n    shutil.copyfile(src, dst)\n\nfnames = ['cat.{}.jpg'.format(i) for i in range(10001, 11251)]  # Move 1250 cat images to the validation cat directory\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(valid_cats_dir, fname)\n    shutil.copyfile(src, dst)\n\nfnames = ['cat.{}.jpg'.format(i) for i in range(11251, 12500)]  # Move 1250 cat images to the test cat directory\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(test_cats_dir, fname)\n    shutil.copyfile(src, dst)\n\n# Create lists of file names for dog images in each set\nfnames = ['dog.{}.jpg'.format(i) for i in range(10001)]  # Move 10,000 dog images to the train dog directory\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(train_dogs_dir, fname)\n    shutil.copyfile(src, dst)\n\nfnames = ['dog.{}.jpg'.format(i) for i in range(10001, 11251)]  # Move 1250 dog images to the validation dog directory\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(valid_dogs_dir, fname)\n    shutil.copyfile(src, dst)\n\nfnames = ['dog.{}.jpg'.format(i) for i in range(11251, 12500)]  # Move 1250 dog images to the test dog directory\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(test_dogs_dir, fname)\n    shutil.copyfile(src, dst)","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:35:36.006502Z","iopub.execute_input":"2024-01-26T11:35:36.007435Z","iopub.status.idle":"2024-01-26T11:35:38.557078Z","shell.execute_reply.started":"2024-01-26T11:35:36.007399Z","shell.execute_reply":"2024-01-26T11:35:38.556202Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f'Total training cat images {len(os.listdir(train_cats_dir))}')\nprint(f'Total validation cat images {len(os.listdir(valid_cats_dir))}')\nprint(f'Total test cat images {len(os.listdir(test_cats_dir))}')\nprint('\\n')\nprint(f'Total training dog images {len(os.listdir(train_dogs_dir))}')\nprint(f'Total validation cat images {len(os.listdir(valid_dogs_dir))}')\nprint(f'Total test cat images {len(os.listdir(test_dogs_dir))}')","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:35:48.070298Z","iopub.execute_input":"2024-01-26T11:35:48.070998Z","iopub.status.idle":"2024-01-26T11:35:48.092075Z","shell.execute_reply.started":"2024-01-26T11:35:48.070964Z","shell.execute_reply":"2024-01-26T11:35:48.091267Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_size = (224 , 224)\nbatch_size = 32\nimg_shape = (img_size[0] , img_size[1] , 3)\n\ntr_gen = ImageDataGenerator()\nts_gen = ImageDataGenerator()\n\ntrain_gen = tr_gen.flow_from_directory(train_dir , target_size = img_size , class_mode = 'binary' , \n                                       color_mode = 'rgb' , shuffle = True , batch_size = batch_size)\n\nvalid_gen = ts_gen.flow_from_directory(valid_dir , target_size = img_size , class_mode = 'binary' , \n                                       color_mode = 'rgb' , shuffle = True , batch_size = batch_size)\n\ntest_gen = ts_gen.flow_from_directory(test_dir , target_size = img_size , class_mode = 'binary' , \n                                       color_mode = 'rgb' , shuffle = False , batch_size = batch_size)","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:35:52.290885Z","iopub.execute_input":"2024-01-26T11:35:52.291673Z","iopub.status.idle":"2024-01-26T11:35:52.983746Z","shell.execute_reply.started":"2024-01-26T11:35:52.291641Z","shell.execute_reply":"2024-01-26T11:35:52.982497Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 6. View Sample Images","metadata":{}},{"cell_type":"code","source":"g_dict = train_gen.class_indices\nclasses = list(g_dict.keys())\nimages, labels = next(train_gen)\nnum_samples = len(images)\n\nplt.figure(figsize=(20, 20))\n\nfor i in range(min(16, num_samples)):\n    plt.subplot(4, 4, i + 1)\n    image = images[i] / 255\n    plt.imshow(image)\n    class_index = int(labels[i])\n    class_name = classes[class_index]\n    plt.title(class_name, color='blue', fontsize=12)\n    plt.axis('off')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:35:59.418150Z","iopub.execute_input":"2024-01-26T11:35:59.419203Z","iopub.status.idle":"2024-01-26T11:36:03.444714Z","shell.execute_reply.started":"2024-01-26T11:35:59.419161Z","shell.execute_reply":"2024-01-26T11:36:03.443633Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 7. Build Model","metadata":{}},{"cell_type":"code","source":"img_shape = (img_size[0], img_size[1], 3)\n\n# Load pre-trained EfficientNetB5 without the top (fully connected) layers\nbase_model = tf.keras.applications.efficientnet.EfficientNetB5(\n    include_top=False,\n    weights='imagenet',\n    input_shape=img_shape,\n    pooling='max'\n)\n\n# Freeze the weights of the pre-trained layers\nbase_model.trainable = False\n\n# Number of classes (binary classification in this case)\nnum_classes = len(classes)\n\n# Build the model using Sequential API\nmodel = Sequential([\n    base_model,\n    BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001),\n    Dense(256, kernel_regularizer=regularizers.l2(l=0.016),\n          activity_regularizer=regularizers.l1(0.006),\n          bias_regularizer=regularizers.l1(0.006), activation='relu'),\n    Dropout(rate=0.4, seed=40),\n    Dense(1, activation='sigmoid')\n])\n\n# Compile the model\nmodel.compile(\n    optimizer=Adamax(learning_rate=0.001),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\n# Display model summary\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:36:10.430751Z","iopub.execute_input":"2024-01-26T11:36:10.431787Z","iopub.status.idle":"2024-01-26T11:36:20.116152Z","shell.execute_reply.started":"2024-01-26T11:36:10.431749Z","shell.execute_reply":"2024-01-26T11:36:20.115285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 8. Fit Model","metadata":{}},{"cell_type":"code","source":"history = model.fit(x= train_gen , validation_data= valid_gen , epochs= 10 , verbose = 1 , validation_steps = None , shuffle = False)","metadata":{"execution":{"iopub.status.busy":"2024-01-26T11:53:02.730274Z","iopub.execute_input":"2024-01-26T11:53:02.730643Z","iopub.status.idle":"2024-01-26T12:09:05.073287Z","shell.execute_reply.started":"2024-01-26T11:53:02.730614Z","shell.execute_reply":"2024-01-26T12:09:05.072304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 9. Train Vs. Validation Accuracy","metadata":{}},{"cell_type":"code","source":"train_acc = history.history['accuracy']\ntrain_loss = history.history['loss']\n\nval_acc = history.history['val_accuracy']\nval_loss = history.history['val_loss']\n\nindex_loss = np.argmin(val_loss)\nindex_acc = np.argmax(val_acc)\n\nval_lowest = val_loss[index_loss]\nval_highest = val_acc[index_acc]\n\nEpochs = [i+1 for i in range(len(train_acc))]\n\nloss_label = f'Best Epoch = {str(index_loss + 1)}'\nacc_label = f'Best Epoch = {str(index_acc + 1)}'\n\nplt.figure(figsize=(20, 8))\nplt.style.use('fivethirtyeight')\n\nplt.subplot(1, 2, 1)\nplt.plot(Epochs, train_loss, 'r', label='Training Loss')\nplt.plot(Epochs, val_loss, 'g', label='Validation Loss')\nplt.scatter(index_loss + 1, val_lowest, s=150, c='blue', label=loss_label)\nplt.title('Training vs Validation (loss)')\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.legend()\n\nplt.subplot(1, 2, 2)\nplt.plot(Epochs, train_acc, 'r', label='Training Accuracy')\nplt.plot(Epochs, val_acc, 'g', label='Validation Accuracy')\nplt.scatter(index_acc + 1, val_highest, s=150, c='blue', label=acc_label)\nplt.title('Training vs Validation (Accuracy)')\nplt.xlabel('Epochs')\nplt.ylabel('Accuracy')\nplt.legend()\n\nplt.tight_layout()\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2024-01-26T12:09:50.354716Z","iopub.execute_input":"2024-01-26T12:09:50.355116Z","iopub.status.idle":"2024-01-26T12:09:51.307536Z","shell.execute_reply.started":"2024-01-26T12:09:50.355087Z","shell.execute_reply":"2024-01-26T12:09:51.306558Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 10. Evaluate Model","metadata":{}},{"cell_type":"code","source":"train_score = model.evaluate(train_gen , steps= 32 , verbose = 1)\nval_score = model.evaluate(valid_gen , steps = 32 , verbose = 1)\ntest_score = model.evaluate(test_gen , steps = 32 , verbose = 1)\n\nprint(f'Train loss = {train_score[0] }')\nprint(f'Train Accuracy = {train_score[1]}')\nprint(f'Validation loss = {val_score[0]}')\nprint(f'Validation Accuracy = {val_score[1]}')\nprint(f'Test loss = {test_score[0]}')\nprint(f'Test Accuracy = {test_score[1]}')","metadata":{"execution":{"iopub.status.busy":"2024-01-26T12:10:10.133074Z","iopub.execute_input":"2024-01-26T12:10:10.133425Z","iopub.status.idle":"2024-01-26T12:10:23.946252Z","shell.execute_reply.started":"2024-01-26T12:10:10.133400Z","shell.execute_reply":"2024-01-26T12:10:23.945261Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 11. Make Predictions","metadata":{}},{"cell_type":"code","source":"# Make predictions on the test set\npreds = model.predict(test_gen)\n\n# Convert the predictions to binary classes (0 or 1)\npredicted_classes = (preds > 0.5).astype(int)","metadata":{"execution":{"iopub.status.busy":"2024-01-26T12:10:30.584648Z","iopub.execute_input":"2024-01-26T12:10:30.585040Z","iopub.status.idle":"2024-01-26T12:10:44.378262Z","shell.execute_reply.started":"2024-01-26T12:10:30.585009Z","shell.execute_reply":"2024-01-26T12:10:44.377348Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 12. View prediction Result\n","metadata":{}},{"cell_type":"code","source":"# Get the true labels from the generator\ntrue_classes = test_gen.classes\n\n# Calculate the confusion matrix\nconfusion = confusion_matrix(true_classes, predicted_classes)\n\n# Display the confusion matrix as a heatmap\ndisp = ConfusionMatrixDisplay(confusion_matrix=confusion, display_labels=test_gen.class_indices)\ndisp.plot(cmap='viridis', values_format='d')","metadata":{"execution":{"iopub.status.busy":"2024-01-26T12:10:51.299216Z","iopub.execute_input":"2024-01-26T12:10:51.299554Z","iopub.status.idle":"2024-01-26T12:10:51.642024Z","shell.execute_reply.started":"2024-01-26T12:10:51.299530Z","shell.execute_reply":"2024-01-26T12:10:51.641158Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Generate and print the classification report\nclassification_rep = classification_report(true_classes, predicted_classes, target_names=test_gen.class_indices)\nprint(\"\\nClassification Report:\")\nprint(classification_rep)","metadata":{"execution":{"iopub.status.busy":"2024-01-26T12:10:59.944493Z","iopub.execute_input":"2024-01-26T12:10:59.944947Z","iopub.status.idle":"2024-01-26T12:10:59.962526Z","shell.execute_reply.started":"2024-01-26T12:10:59.944912Z","shell.execute_reply":"2024-01-26T12:10:59.961516Z"},"trusted":true},"execution_count":null,"outputs":[]}]}