{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install py7zr","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:27:39.338659Z","iopub.execute_input":"2023-09-19T17:27:39.339616Z","iopub.status.idle":"2023-09-19T17:27:57.211701Z","shell.execute_reply.started":"2023-09-19T17:27:39.339578Z","shell.execute_reply":"2023-09-19T17:27:57.210507Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import py7zr\n\nwith py7zr.SevenZipFile('/kaggle/input/cifar-10/test.7z', mode='r') as z:\n    z.extractall(path=\"/kaggle/working/\")\n\nwith py7zr.SevenZipFile('/kaggle/input/cifar-10/train.7z', mode='r') as z:\n    z.extractall(path=\"/kaggle/working/\")","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:28:01.905316Z","iopub.execute_input":"2023-09-19T17:28:01.905694Z","iopub.status.idle":"2023-09-19T17:49:53.80007Z","shell.execute_reply.started":"2023-09-19T17:28:01.905661Z","shell.execute_reply":"2023-09-19T17:49:53.798937Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install numpy==1.22.0","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:51:22.998518Z","iopub.execute_input":"2023-09-19T17:51:22.998905Z","iopub.status.idle":"2023-09-19T17:51:45.290383Z","shell.execute_reply.started":"2023-09-19T17:51:22.998875Z","shell.execute_reply":"2023-09-19T17:51:45.289006Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator, load_img, img_to_array\n# from keras.preprocessing.image import ImageDataGenerator, load_img, img_to_array\n# why keras only\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom keras.optimizers import Adam\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:51:48.196142Z","iopub.execute_input":"2023-09-19T17:51:48.196581Z","iopub.status.idle":"2023-09-19T17:51:48.20712Z","shell.execute_reply.started":"2023-09-19T17:51:48.196545Z","shell.execute_reply":"2023-09-19T17:51:48.204744Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"strategy = tf.distribute.MirroredStrategy()\nprint(\"Number of devices: {}\".format(strategy.num_replicas_in_sync))","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:51:56.681897Z","iopub.execute_input":"2023-09-19T17:51:56.682387Z","iopub.status.idle":"2023-09-19T17:52:03.486868Z","shell.execute_reply.started":"2023-09-19T17:51:56.682346Z","shell.execute_reply":"2023-09-19T17:52:03.485857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_dir = \"/kaggle/working/train/\"\ntest_dir = \"/kaggle/working/test/\"","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:52:18.281901Z","iopub.execute_input":"2023-09-19T17:52:18.282554Z","iopub.status.idle":"2023-09-19T17:52:18.286664Z","shell.execute_reply.started":"2023-09-19T17:52:18.282514Z","shell.execute_reply":"2023-09-19T17:52:18.285756Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\n# Data Augmentation\ndatagen = ImageDataGenerator(\n    rescale=1./255,          # Rescale pixel values to [0, 1]\n    validation_split=0.2,    # Reserve some data for validation\n    horizontal_flip=True,    # Random horizontal flip\n    width_shift_range=0.1,   # Horizontal shift\n    height_shift_range=0.1,  # Vertical shift\n    rotation_range=20,       # Random rotation between -20 to 20 degrees\n    zoom_range=0.15,         # Random zoom in the range [0.85, 1.15]\n    shear_range=0.15         # Shear Intensity\n)","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:52:20.818639Z","iopub.execute_input":"2023-09-19T17:52:20.819002Z","iopub.status.idle":"2023-09-19T17:52:20.82502Z","shell.execute_reply.started":"2023-09-19T17:52:20.818974Z","shell.execute_reply":"2023-09-19T17:52:20.824011Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pd.read_csv('/kaggle/input/cifar-10/trainLabels.csv')\n\n# Convert class labels from string to str format\n# df_train['label'] = df_train['label'].astype(str)\n# df_train['id'] = df_train['id'].astype(str) + '.png'\ndf_train['id'] = df_train['id'].astype(str) + '.png'\n\n\n# Load images using Keras's ImageDataGenerator\ndatagen = ImageDataGenerator(\n    rescale=1./255,\n    validation_split=0.2,\n    horizontal_flip=True,\n    width_shift_range=0.1,\n    height_shift_range=0.1\n)\n\ntrain_generator = datagen.flow_from_dataframe(\n    df_train,\n    directory=train_dir,\n    x_col='id',\n    y_col='label',\n    target_size=(32, 32),\n    class_mode='categorical',\n    batch_size=64,\n    subset='training'\n)\n\nvalidation_generator = datagen.flow_from_dataframe(\n    df_train,\n    directory=train_dir,\n    x_col='id',\n    y_col='label',\n    target_size=(32, 32),\n    class_mode='categorical',\n    batch_size=128,\n    subset='validation'\n)","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:52:24.740456Z","iopub.execute_input":"2023-09-19T17:52:24.741243Z","iopub.status.idle":"2023-09-19T17:52:26.007831Z","shell.execute_reply.started":"2023-09-19T17:52:24.741203Z","shell.execute_reply":"2023-09-19T17:52:26.006737Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import gc\ndel df_train\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:52:29.123307Z","iopub.execute_input":"2023-09-19T17:52:29.123691Z","iopub.status.idle":"2023-09-19T17:52:30.052078Z","shell.execute_reply.started":"2023-09-19T17:52:29.123661Z","shell.execute_reply":"2023-09-19T17:52:30.050867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.layers import BatchNormalization\nfrom tensorflow.keras.layers import Dense, Dropout, Activation,Flatten,Conv2D,MaxPooling2D\nwith strategy.scope():\n    model = Sequential()\n    model.add(Conv2D(filters=32, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation=None, use_bias=False, input_shape=(32, 32, 3)))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n\n    model.add(Conv2D(filters=48, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n\n    model.add(Conv2D(filters=64, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n\n    model.add(Conv2D(filters=80, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n\n    model.add(Conv2D(filters=96, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n\n    model.add(Conv2D(filters=128, kernel_size=(3, 3), strides=(1, 1), padding='valid', activation=None, use_bias=False))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n\n    model.add(Flatten())\n    model.add(Dense(units=10))\n    model.add(BatchNormalization())\n    model.add(Activation('softmax'))\n    model.compile(loss='categorical_crossentropy', optimizer= Adam(learning_rate= 0.003 ), metrics=['accuracy'])\n    model.summary()","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:52:31.436096Z","iopub.execute_input":"2023-09-19T17:52:31.436464Z","iopub.status.idle":"2023-09-19T17:52:32.025111Z","shell.execute_reply.started":"2023-09-19T17:52:31.436435Z","shell.execute_reply":"2023-09-19T17:52:32.024268Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"early_stop = EarlyStopping(patience=10, restore_best_weights=True)\nreduce_lr = ReduceLROnPlateau(factor=0.2, patience=3)\n\nhistory = model.fit(\n    train_generator,\n    validation_data=validation_generator,\n    epochs=10,\n    callbacks=[early_stop, reduce_lr]\n)\nmodel.save(\"/kaggle/working/cifar10_model03.h5\")","metadata":{"execution":{"iopub.status.busy":"2023-09-19T17:52:40.090834Z","iopub.execute_input":"2023-09-19T17:52:40.091191Z","iopub.status.idle":"2023-09-19T18:03:33.576875Z","shell.execute_reply.started":"2023-09-19T17:52:40.091163Z","shell.execute_reply":"2023-09-19T18:03:33.575845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Clear Memory\ndel train_generator, validation_generator\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-09-19T18:04:17.109871Z","iopub.execute_input":"2023-09-19T18:04:17.110356Z","iopub.status.idle":"2023-09-19T18:04:17.396913Z","shell.execute_reply.started":"2023-09-19T18:04:17.110305Z","shell.execute_reply":"2023-09-19T18:04:17.395685Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_files = os.listdir(test_dir)\n\nbatch_size = 1024\npredicted_classes = []\n\nprint(f\"Total test files: {len(test_files)}\")\n\nfor i in range(0, len(test_files), batch_size):\n    print(f\"Processing images {i} to {i+batch_size}...\")\n    \n    batch_files = test_files[i:i+batch_size]\n    test_images = [load_img(test_dir + fname, target_size=(32,32)) for fname in batch_files]\n    test_array = np.array([img_to_array(img) for img in test_images]) / 255.0\n\n    batch_predictions = model.predict(test_array)\n    batch_labels = np.argmax(batch_predictions, axis=1)\n    predicted_classes.extend(batch_labels)\n\n    # Freeing up memory\n    del test_images, test_array, batch_predictions\n    gc.collect()\n\npredicted_classes = np.array(predicted_classes)\nprint(f\"Total predicted classes: {len(predicted_classes)}\")\n\n# rest of the code \n\n# Assuming these are the class names in the order you trained your model\nclass_names = [\"airplane\", \"automobile\", \"bird\", \"cat\", \"deer\", \"dog\", \"frog\", \"horse\", \"ship\", \"truck\"]\n\n# Map the numerical labels to class names\npredicted_class_names = [class_names[label] for label in predicted_classes]\n\n# Create CSV for Submission\nsubmission_df = pd.DataFrame({\n    'id': [int(fname.split('.')[0]) for fname in test_files],  # Convert to integer to ensure proper format\n    'label': predicted_class_names\n})\n\n# Sort the dataframe by 'id' column for cleaner output\nsubmission_df = submission_df.sort_values(by='id')\n\nsubmission_df.to_csv(\"/kaggle/working/submission02.csv\", index=False)\n","metadata":{"execution":{"iopub.status.busy":"2023-09-19T18:04:19.485564Z","iopub.execute_input":"2023-09-19T18:04:19.485945Z","iopub.status.idle":"2023-09-19T18:08:46.249147Z","shell.execute_reply.started":"2023-09-19T18:04:19.485916Z","shell.execute_reply":"2023-09-19T18:08:46.247851Z"},"trusted":true},"execution_count":null,"outputs":[]}]}