{"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":"!pip install py7zr","metadata":{"execution":{"iopub.status.busy":"2023-09-19T18:52:41.504363Z","iopub.execute_input":"2023-09-19T18:52:41.505585Z","iopub.status.idle":"2023-09-19T18:52:56.766734Z","shell.execute_reply.started":"2023-09-19T18:52:41.505543Z","shell.execute_reply":"2023-09-19T18:52:56.765528Z"},"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":"2023-09-19T18:52:56.769777Z","iopub.execute_input":"2023-09-19T18:52:56.770919Z","iopub.status.idle":"2023-09-19T19:13:21.955882Z","shell.execute_reply.started":"2023-09-19T18:52:56.770878Z","shell.execute_reply":"2023-09-19T19:13:21.954866Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install numpy==1.22.0","metadata":{"execution":{"iopub.status.busy":"2023-09-19T19:13:21.957248Z","iopub.execute_input":"2023-09-19T19:13:21.958301Z","iopub.status.idle":"2023-09-19T19:13:41.182110Z","shell.execute_reply.started":"2023-09-19T19:13:21.958264Z","shell.execute_reply":"2023-09-19T19:13:41.180990Z"},"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":"2023-09-19T19:13:41.185647Z","iopub.execute_input":"2023-09-19T19:13:41.186037Z","iopub.status.idle":"2023-09-19T19:13:50.630843Z","shell.execute_reply.started":"2023-09-19T19:13:41.186001Z","shell.execute_reply":"2023-09-19T19:13:50.629749Z"},"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":"2023-09-19T19:13:50.632564Z","iopub.execute_input":"2023-09-19T19:13:50.633276Z","iopub.status.idle":"2023-09-19T19:13:55.648952Z","shell.execute_reply.started":"2023-09-19T19:13:50.633238Z","shell.execute_reply":"2023-09-19T19:13:55.647769Z"},"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":"2023-09-19T19:13:55.650523Z","iopub.execute_input":"2023-09-19T19:13:55.651579Z","iopub.status.idle":"2023-09-19T19:13:55.656749Z","shell.execute_reply.started":"2023-09-19T19:13:55.651539Z","shell.execute_reply":"2023-09-19T19:13:55.655668Z"},"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":"2023-09-19T19:13:55.658101Z","iopub.execute_input":"2023-09-19T19:13:55.658984Z","iopub.status.idle":"2023-09-19T19:13:55.668145Z","shell.execute_reply.started":"2023-09-19T19:13:55.658947Z","shell.execute_reply":"2023-09-19T19:13:55.667074Z"},"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":"2023-09-19T19:13:55.670571Z","iopub.execute_input":"2023-09-19T19:13:55.671922Z","iopub.status.idle":"2023-09-19T19:13:56.774668Z","shell.execute_reply.started":"2023-09-19T19:13:55.671897Z","shell.execute_reply":"2023-09-19T19:13:56.773650Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import gc\ndel df_train\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-09-19T19:13:56.776128Z","iopub.execute_input":"2023-09-19T19:13:56.776767Z","iopub.status.idle":"2023-09-19T19:13:56.954874Z","shell.execute_reply.started":"2023-09-19T19:13:56.776729Z","shell.execute_reply":"2023-09-19T19:13:56.953699Z"},"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":"2023-09-19T19:13:56.958553Z","iopub.execute_input":"2023-09-19T19:13:56.958925Z","iopub.status.idle":"2023-09-19T19:13:57.466885Z","shell.execute_reply.started":"2023-09-19T19:13:56.958891Z","shell.execute_reply":"2023-09-19T19:13:57.466076Z"},"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":"2023-09-19T19:13:57.468009Z","iopub.execute_input":"2023-09-19T19:13:57.468409Z","iopub.status.idle":"2023-09-19T19:24:02.709580Z","shell.execute_reply.started":"2023-09-19T19:13:57.468373Z","shell.execute_reply":"2023-09-19T19:24:02.708539Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Clear Memory\ndel train_generator, validation_generator\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-09-19T19:24:02.711006Z","iopub.execute_input":"2023-09-19T19:24:02.711379Z","iopub.status.idle":"2023-09-19T19:24:02.941729Z","shell.execute_reply.started":"2023-09-19T19:24:02.711345Z","shell.execute_reply":"2023-09-19T19:24:02.940799Z"},"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":"2023-09-19T19:24:02.944181Z","iopub.execute_input":"2023-09-19T19:24:02.944612Z","iopub.status.idle":"2023-09-19T19:28:12.624454Z","shell.execute_reply.started":"2023-09-19T19:24:02.944574Z","shell.execute_reply":"2023-09-19T19:28:12.623352Z"},"trusted":true},"execution_count":null,"outputs":[]}]}