{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":21154,"databundleVersionId":1243559,"sourceType":"competition"}],"dockerImageVersionId":31192,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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\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":{"iopub.status.busy":"2025-12-03T09:56:40.567003Z","iopub.execute_input":"2025-12-03T09:56:40.567302Z","iopub.status.idle":"2025-12-03T09:56:40.678459Z","shell.execute_reply.started":"2025-12-03T09:56:40.567281Z","shell.execute_reply":"2025-12-03T09:56:40.677551Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf \nfrom kaggle_datasets import KaggleDatasets\nimport math, re, os\n\n\nprint(tf.__version__)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:41.28532Z","iopub.execute_input":"2025-12-03T09:56:41.285594Z","iopub.status.idle":"2025-12-03T09:56:41.29057Z","shell.execute_reply.started":"2025-12-03T09:56:41.285575Z","shell.execute_reply":"2025-12-03T09:56:41.289796Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**1. Persiapan Lingkungan & Inisialisasi TPU**\n\nBlok kode ini berfungsi untuk mendeteksi ketersediaan perangkat keras TPU (Tensor Processing Unit) secara otomatis. Tujuannya adalah agar kode dapat dijalankan secara fleksibel baik di lingkungan yang memiliki TPU, maupun di lingkungan standar (CPU/GPU) tanpa perlu mengubah kode secara manual.","metadata":{}},{"cell_type":"code","source":"# Detect TPU, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver() \n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy() \n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:41.999574Z","iopub.execute_input":"2025-12-03T09:56:41.999861Z","iopub.status.idle":"2025-12-03T09:56:42.005716Z","shell.execute_reply.started":"2025-12-03T09:56:41.999842Z","shell.execute_reply":"2025-12-03T09:56:42.004417Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**2. Akses Data dari Google Cloud Storage (GCS)**\n\nAkses Data dari Google Cloud Storage (GCS)\nKode ini bertujuan untuk mendapatkan jalur penyimpanan (path) dataset di Google Cloud Storage (GCS). Langkah ini sangat krusial saat menggunakan TPU karena TPU membaca data jauh lebih cepat langsung dari GCS dibandingkan dari disk lokal Kaggle.","metadata":{}},{"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path()\nprint(GCS_DS_PATH) # what do gcs paths look like?","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:42.542908Z","iopub.execute_input":"2025-12-03T09:56:42.54321Z","iopub.status.idle":"2025-12-03T09:56:42.853928Z","shell.execute_reply.started":"2025-12-03T09:56:42.543181Z","shell.execute_reply":"2025-12-03T09:56:42.853045Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**3. Konfigurasi Data & Pipeline TFRecord**\n\nBagian ini mengatur bagaimana data ditemukan di Google Cloud Storage (GCS) dan bagaimana format biner TFRecord diubah menjadi tensor gambar yang bisa diproses oleh model.\n","metadata":{}},{"cell_type":"code","source":"IMAGE_SIZE = [224, 224]\nGCS_PATH = GCS_DS_PATH + '/tfrecords-jpeg-224x224'\nAUTO = tf.data.experimental.AUTOTUNE\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') \n\nCLASSES = ['pink primrose',    'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea',     'wild geranium',     'tiger lily',           'moon orchid',              'bird of paradise', 'monkshood',        'globe thistle',         # 00 - 09\n           'snapdragon',       \"colt's foot\",               'king protea',      'spear thistle', 'yellow iris',       'globe-flower',         'purple coneflower',        'peruvian lily',    'balloon flower',   'giant white arum lily', # 10 - 19\n           'fire lily',        'pincushion flower',         'fritillary',       'red ginger',    'grape hyacinth',    'corn poppy',           'prince of wales feathers', 'stemless gentian', 'artichoke',        'sweet william',         # 20 - 29\n           'carnation',        'garden phlox',              'love in the mist', 'cosmos',        'alpine sea holly',  'ruby-lipped cattleya', 'cape flower',              'great masterwort', 'siam tulip',       'lenten rose',           # 30 - 39\n           'barberton daisy',  'daffodil',                  'sword lily',       'poinsettia',    'bolero deep blue',  'wallflower',           'marigold',                 'buttercup',        'daisy',            'common dandelion',      # 40 - 49\n           'petunia',          'wild pansy',                'primula',          'sunflower',     'lilac hibiscus',    'bishop of llandaff',   'gaura',                    'geranium',         'orange dahlia',    'pink-yellow dahlia',    # 50 - 59\n           'cautleya spicata', 'japanese anemone',          'black-eyed susan', 'silverbush',    'californian poppy', 'osteospermum',         'spring crocus',            'iris',             'windflower',       'tree poppy',            # 60 - 69\n           'gazania',          'azalea',                    'water lily',       'rose',          'thorn apple',       'morning glory',        'passion flower',           'lotus',            'toad lily',        'anthurium',             # 70 - 79\n           'frangipani',       'clematis',                  'hibiscus',         'columbine',     'desert-rose',       'tree mallow',          'magnolia',                 'cyclamen ',        'watercress',       'canna lily',            # 80 - 89\n           'hippeastrum ',     'bee balm',                  'pink quill',       'foxglove',      'bougainvillea',     'camellia',             'mallow',                   'mexican petunia',  'bromelia',         'blanket flower',        # 90 - 99\n           'trumpet creeper',  'blackberry lily',           'common tulip',     'wild rose']                                                                                                                                               # 100 - 102\n\n\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0  # convert image to floats in [0, 1] range\n    image = tf.reshape(image, [*IMAGE_SIZE, 3]) # explicit size needed for TPU\n    return image\n\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"class\": tf.io.FixedLenFeature([], tf.int64),  # shape [] means single element\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = tf.cast(example['class'], tf.int32)\n    return image, label # returns a dataset of (image, label) pairs\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n        \"id\": tf.io.FixedLenFeature([], tf.string),  # shape [] means single element\n        # class is missing, this competitions's challenge is to predict flower classes for the test dataset\n    }\n    example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    idnum = example['id']\n    return image, idnum # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    # Read from TFRecords. For optimal performance, reading from multiple files at once and\n    # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False # disable order, increase speed\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n    dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:43.24611Z","iopub.execute_input":"2025-12-03T09:56:43.246654Z","iopub.status.idle":"2025-12-03T09:56:43.430169Z","shell.execute_reply.started":"2025-12-03T09:56:43.246631Z","shell.execute_reply":"2025-12-03T09:56:43.429257Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**4. Augmentasi & Pembangunan Pipeline Dataset**\n\nBagian ini mendefinisikan transformasi data dan menyusun pipeline tf.data yang efisien untuk pelatihan kinerja tinggi pada TPU.","metadata":{}},{"cell_type":"code","source":"def data_augment(image, label):\n    # Thanks to the dataset.prefetch(AUTO)\n    # statement in the next function (below), this happens essentially\n    # for free on TPU. Data pipeline code is executed on the \"CPU\"\n    # part of the TPU while the TPU itself is computing gradients.\n    image = tf.image.random_flip_left_right(image)\n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label   \n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n    dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n    dataset = dataset.repeat() # the training dataset must repeat for several epochs\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n    return dataset\n\ndef get_validation_dataset(ordered=False):\n    dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\ndef count_data_items(filenames):\n    # the number of data items is written in the name of the .tfrec\n    # files, i.e. flowers00-230.tfrec = 230 data items\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:43.911217Z","iopub.execute_input":"2025-12-03T09:56:43.911999Z","iopub.status.idle":"2025-12-03T09:56:43.919713Z","shell.execute_reply.started":"2025-12-03T09:56:43.911975Z","shell.execute_reply":"2025-12-03T09:56:43.919048Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**5. Konfigurasi Batch Size & Instansiasi Dataset**\n\nBlok kode ini menetapkan ukuran batch global dan menginisialisasi objek dataset yang telah dikonfigurasi sebelumnya.","metadata":{}},{"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128 (=16*8) with TPU on\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nds_train = get_training_dataset()\nds_valid = get_validation_dataset()\nds_test = get_test_dataset()\n\nprint(\"Training:\", ds_train)\nprint (\"Validation:\", ds_valid)\nprint(\"Test:\", ds_test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:44.643047Z","iopub.execute_input":"2025-12-03T09:56:44.643659Z","iopub.status.idle":"2025-12-03T09:56:44.771776Z","shell.execute_reply.started":"2025-12-03T09:56:44.643632Z","shell.execute_reply":"2025-12-03T09:56:44.770941Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**6. Inspeksi Bentuk Data (Data Shape Inspection)**\n\nBagian ini memverifikasi dimensi data yang keluar dari pipeline tf.data.Dataset. Ini langkah penting untuk memastikan ukuran batch, resolusi gambar, dan label sudah sesuai dengan ekspektasi model.","metadata":{}},{"cell_type":"code","source":"np.set_printoptions(threshold=15, linewidth=80)\n\nprint(\"Training data shapes:\")\nfor image, label in ds_train.take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training data label examples:\", label.numpy())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:45.227978Z","iopub.execute_input":"2025-12-03T09:56:45.228668Z","iopub.status.idle":"2025-12-03T09:56:46.924147Z","shell.execute_reply.started":"2025-12-03T09:56:45.228644Z","shell.execute_reply":"2025-12-03T09:56:46.923176Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**7. Inspeksi Data Uji**\n\nBlok kode ini melakukan pemeriksaan struktur pada dataset pengujian. Perbedaan mendasar antara data latih dan data uji adalah data uji tidak memiliki label kelas, melainkan ID unik.","metadata":{}},{"cell_type":"code","source":"print(\"Test data shapes:\")\nfor image, idnum in ds_test.take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype('U')) # U=unicode string","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:46.925346Z","iopub.execute_input":"2025-12-03T09:56:46.925617Z","iopub.status.idle":"2025-12-03T09:56:47.332428Z","shell.execute_reply.started":"2025-12-03T09:56:46.925601Z","shell.execute_reply":"2025-12-03T09:56:47.331708Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**8. Utilitas Visualisasi Data & Evaluasi Model**\n\nBagian ini mendefinisikan fungsi-fungsi kustom untuk memvisualisasikan batch gambar, menampilkan hasil prediksi (benar/salah), dan memplot kurva performa pelatihan.","metadata":{}},{"cell_type":"code","source":"from matplotlib import pyplot as plt\n\ndef batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    if numpy_labels.dtype == object: # binary string in this case,\n                                     # these are image ID strings\n        numpy_labels = [None for _ in enumerate(numpy_images)]\n    # If no labels, only image IDs, return None for labels (this is\n    # the case for test data)\n    return numpy_images, numpy_labels\n\ndef title_from_label_and_target(label, correct_label):\n    if correct_label is None:\n        return CLASSES[label], True\n    correct = (label == correct_label)\n    return \"{} [{}{}{}]\".format(CLASSES[label], 'OK' if correct else 'NO', u\"\\u2192\" if not correct else '',\n                                CLASSES[correct_label] if not correct else ''), correct\n\ndef display_one_flower(image, title, subplot, red=False, titlesize=16):\n    plt.subplot(*subplot)\n    plt.axis('off')\n    plt.imshow(image)\n    if len(title) > 0:\n        plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n    return (subplot[0], subplot[1], subplot[2]+1)\n    \ndef display_batch_of_images(databatch, predictions=None):\n    \"\"\"This will work with:\n    display_batch_of_images(images)\n    display_batch_of_images(images, predictions)\n    display_batch_of_images((images, labels))\n    display_batch_of_images((images, labels), predictions)\n    \"\"\"\n    # data\n    images, labels = batch_to_numpy_images_and_labels(databatch)\n    if labels is None:\n        labels = [None for _ in enumerate(images)]\n        \n    # auto-squaring: this will drop data that does not fit into square\n    # or square-ish rectangle\n    rows = int(math.sqrt(len(images)))\n    cols = len(images)//rows\n        \n    # size and spacing\n    FIGSIZE = 13.0\n    SPACING = 0.1\n    subplot=(rows,cols,1)\n    if rows < cols:\n        plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n    else:\n        plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n    \n    # display\n    for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n        title = '' if label is None else CLASSES[label]\n        correct = True\n        if predictions is not None:\n            title, correct = title_from_label_and_target(predictions[i], label)\n        dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n        subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n    \n    #layout\n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspace=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n    plt.show()\n\n\ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1: # set up the subplots on the first call\n        plt.subplots(figsize=(10,10), facecolor='#F0F0F0')\n        plt.tight_layout()\n    ax = plt.subplot(subplot)\n    ax.set_facecolor('#F8F8F8')\n    ax.plot(training)\n    ax.plot(validation)\n    ax.set_title('model '+ title)\n    ax.set_ylabel(title)\n    #ax.set_ylim(0.28,1.05)\n    ax.set_xlabel('epoch')\n    ax.legend(['train', 'valid.'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:48.315075Z","iopub.execute_input":"2025-12-03T09:56:48.315783Z","iopub.status.idle":"2025-12-03T09:56:48.327773Z","shell.execute_reply.started":"2025-12-03T09:56:48.315759Z","shell.execute_reply":"2025-12-03T09:56:48.32679Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:49.310492Z","iopub.execute_input":"2025-12-03T09:56:49.311141Z","iopub.status.idle":"2025-12-03T09:56:49.370489Z","shell.execute_reply.started":"2025-12-03T09:56:49.311115Z","shell.execute_reply":"2025-12-03T09:56:49.369889Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:49.963208Z","iopub.execute_input":"2025-12-03T09:56:49.963504Z","iopub.status.idle":"2025-12-03T09:56:54.22311Z","shell.execute_reply.started":"2025-12-03T09:56:49.963482Z","shell.execute_reply":"2025-12-03T09:56:54.221809Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**9. Konstruksi Model**\n\nBagian ini mendefinisikan arsitektur Deep Learning yang akan digunakan. Kode ini menggunakan pendekatan Transfer Learning, yaitu memanfaatkan model yang sudah \"pintar\" (dilatih pada dataset besar ImageNet) dan menyesuaikannya untuk mengenali bunga.","metadata":{}},{"cell_type":"code","source":"EPOCHS = 10\nwith strategy.scope():\n    pretrained_model = tf.keras.applications.VGG16(\n        weights='imagenet',\n        include_top=False ,\n        input_shape=[*IMAGE_SIZE, 3]\n    )\n    pretrained_model.trainable = False\n    \n    model = tf.keras.Sequential([\n        # To a base pretrained on ImageNet to extract features from images...\n        pretrained_model,\n        # ... attach a new head to act as a classifier.\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:56:54.224854Z","iopub.execute_input":"2025-12-03T09:56:54.2251Z","iopub.status.idle":"2025-12-03T09:56:54.833702Z","shell.execute_reply.started":"2025-12-03T09:56:54.225082Z","shell.execute_reply":"2025-12-03T09:56:54.833073Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.compile(\n    optimizer='adam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)\n\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:57:00.082453Z","iopub.execute_input":"2025-12-03T09:57:00.083173Z","iopub.status.idle":"2025-12-03T09:57:00.103773Z","shell.execute_reply.started":"2025-12-03T09:57:00.083147Z","shell.execute_reply":"2025-12-03T09:57:00.103032Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Learning Rate Schedule for Fine Tuning #\ndef exponential_lr(epoch,\n                   start_lr = 0.00001, min_lr = 0.00001, max_lr = 0.00005,\n                   rampup_epochs = 5, sustain_epochs = 0,\n                   exp_decay = 0.8):\n\n    def lr(epoch, start_lr, min_lr, max_lr, rampup_epochs, sustain_epochs, exp_decay):\n        # linear increase from start to rampup_epochs\n        if epoch < rampup_epochs:\n            lr = ((max_lr - start_lr) /\n                  rampup_epochs * epoch + start_lr)\n        # constant max_lr during sustain_epochs\n        elif epoch < rampup_epochs + sustain_epochs:\n            lr = max_lr\n        # exponential decay towards min_lr\n        else:\n            lr = ((max_lr - min_lr) *\n                  exp_decay**(epoch - rampup_epochs - sustain_epochs) +\n                  min_lr)\n        return lr\n    return lr(epoch,\n              start_lr,\n              min_lr,\n              max_lr,\n              rampup_epochs,\n              sustain_epochs,\n              exp_decay)\n\nlr_callback = tf.keras.callbacks.LearningRateScheduler(exponential_lr, verbose=True)\n\nrng = [i for i in range(EPOCHS)]\ny = [exponential_lr(x) for x in rng]\nplt.plot(rng, y)\nprint(\"Learning rate schedule: {:.3g} to {:.3g} to {:.3g}\".format(y[0], max(y), y[-1]))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:57:02.077704Z","iopub.execute_input":"2025-12-03T09:57:02.078547Z","iopub.status.idle":"2025-12-03T09:57:02.235724Z","shell.execute_reply.started":"2025-12-03T09:57:02.07852Z","shell.execute_reply":"2025-12-03T09:57:02.235061Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Define training epochs\nEPOCHS = 10\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n    ds_train,\n    validation_data=ds_valid,\n    epochs=EPOCHS,\n    steps_per_epoch=STEPS_PER_EPOCH,\n    callbacks=[lr_callback],\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T09:57:03.080356Z","iopub.execute_input":"2025-12-03T09:57:03.080664Z","iopub.status.idle":"2025-12-03T10:15:00.930673Z","shell.execute_reply.started":"2025-12-03T09:57:03.080641Z","shell.execute_reply":"2025-12-03T10:15:00.92973Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"plt.figure(figsize=(8, 6))\nplt.plot(history.history['sparse_categorical_accuracy'])\nplt.plot(history.history['val_sparse_categorical_accuracy'])\nplt.title(\"Model Accuracy\")\nplt.ylabel(\"Accuracy\")\nplt.xlabel(\"Epoch\")\nplt.legend(['Train', 'Validation'])\nplt.show()\n\nplt.figure(figsize=(8, 6))\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title(\"Model Loss\")\nplt.ylabel(\"Loss\")\nplt.xlabel(\"Epoch\")\nplt.legend(['Train', 'Validation'])\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T10:16:11.174799Z","iopub.execute_input":"2025-12-03T10:16:11.175176Z","iopub.status.idle":"2025-12-03T10:16:11.599061Z","shell.execute_reply.started":"2025-12-03T10:16:11.175151Z","shell.execute_reply":"2025-12-03T10:16:11.598258Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T10:16:57.245097Z","iopub.execute_input":"2025-12-03T10:16:57.245492Z","iopub.status.idle":"2025-12-03T10:16:57.310265Z","shell.execute_reply.started":"2025-12-03T10:16:57.245464Z","shell.execute_reply":"2025-12-03T10:16:57.309467Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images, labels = next(batch)\nprobabilities = model.predict(images)\npredictions = np.argmax(probabilities, axis=-1)\ndisplay_batch_of_images((images, labels), predictions)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T10:17:07.975099Z","iopub.execute_input":"2025-12-03T10:17:07.975699Z","iopub.status.idle":"2025-12-03T10:17:19.302128Z","shell.execute_reply.started":"2025-12-03T10:17:07.975675Z","shell.execute_reply":"2025-12-03T10:17:19.300722Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True)\n\nprint('Computing predictions...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities = model.predict(test_images_ds)\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T10:17:38.580137Z","iopub.execute_input":"2025-12-03T10:17:38.580426Z","iopub.status.idle":"2025-12-03T10:18:31.646821Z","shell.execute_reply.started":"2025-12-03T10:17:38.580406Z","shell.execute_reply":"2025-12-03T10:18:31.645969Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print('Generating submission.csv file...')\n\n# Get image ids from test set and convert to unicode\ntest_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\ntest_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U')\n\n# Write the submission file\nnp.savetxt(\n    'submission.csv',\n    np.rec.fromarrays([test_ids, predictions]),\n    fmt=['%s', '%d'],\n    delimiter=',',\n    header='id,label',\n    comments='',\n)\n\n# Look at the first few predictions\n!head submission.csv","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-03T10:19:06.716134Z","iopub.execute_input":"2025-12-03T10:19:06.716935Z","iopub.status.idle":"2025-12-03T10:19:10.503343Z","shell.execute_reply.started":"2025-12-03T10:19:06.716907Z","shell.execute_reply":"2025-12-03T10:19:10.502551Z"}},"outputs":[],"execution_count":null}]}