{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"tpuV5e8","dataSources":[{"sourceType":"competition","sourceId":21154,"databundleVersionId":1243559}],"dockerImageVersionId":31331,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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":{"iopub.status.busy":"2026-04-18T05:45:28.539795Z","iopub.execute_input":"2026-04-18T05:45:28.539946Z","iopub.status.idle":"2026-04-18T05:45:28.566447Z","shell.execute_reply.started":"2026-04-18T05:45:28.539929Z","shell.execute_reply":"2026-04-18T05:45:28.565719Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!export PATH=\"${HOME}/.local/bin:${PATH}\" && uv pip uninstall --system jax","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!export PATH=\"${HOME}/.local/bin:${PATH}\" && uv pip install --system tensorflow-tpu==\"2.18.0\" --find-links https://storage.googleapis.com/libtpu-tf-releases/index.html\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import math, re\nimport tensorflow as tf\n\nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-18T05:45:28.874977Z","iopub.execute_input":"2026-04-18T05:45:28.875181Z","iopub.status.idle":"2026-04-18T05:45:43.594480Z","shell.execute_reply.started":"2026-04-18T05:45:28.875162Z","shell.execute_reply":"2026-04-18T05:45:43.593396Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\n\n# Detect and initialize TPU\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver(tpu=\"local\")  \n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.TPUStrategy(tpu)\n    print(f\"Running on TPU: {tpu.master()}\")\nexcept Exception as e:\n    print(f\"Could not initialize TPU: {e}\")\n    strategy = tf.distribute.get_strategy()  # Fallback to default CPU/GPU\n    print(\"Running on CPU or single GPU\")\n\n# Print number of available TPU cores\nprint(\"Number of devices:\", strategy.num_replicas_in_sync, \"🚀\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-18T05:45:50.892651Z","iopub.execute_input":"2026-04-18T05:45:50.893084Z","iopub.status.idle":"2026-04-18T05:46:07.164537Z","shell.execute_reply.started":"2026-04-18T05:45:50.893052Z","shell.execute_reply":"2026-04-18T05:46:07.163388Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = [512, 512]\nGCS_PATH = '/kaggle/input/competitions/tpu-getting-started/tfrecords-jpeg-512x512'\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\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0\n    image = tf.reshape(image, [*IMAGE_SIZE, 3])\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\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\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\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\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    ignore_order = tf.data.Options()\n\n    if not ordered:\n        ignore_order.experimental_deterministic = False\n\n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO)\n    dataset = dataset.with_options(ignore_order)\n    dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n\n    return dataset","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-18T05:46:12.831160Z","iopub.execute_input":"2026-04-18T05:46:12.831570Z","iopub.status.idle":"2026-04-18T05:46:12.854397Z","shell.execute_reply.started":"2026-04-18T05:46:12.831536Z","shell.execute_reply":"2026-04-18T05:46:12.853310Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def data_augment(image, label):\n    image = tf.image.random_flip_left_right(image)\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()\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n\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    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":"2026-04-18T05:46:18.686452Z","iopub.execute_input":"2026-04-18T05:46:18.686721Z","iopub.status.idle":"2026-04-18T05:46:18.692841Z","shell.execute_reply.started":"2026-04-18T05:46:18.686681Z","shell.execute_reply":"2026-04-18T05:46:18.691778Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"BATCH_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":"2026-04-18T05:46:21.547512Z","iopub.execute_input":"2026-04-18T05:46:21.547821Z","iopub.status.idle":"2026-04-18T05:46:21.714607Z","shell.execute_reply.started":"2026-04-18T05:46:21.547804Z","shell.execute_reply":"2026-04-18T05:46:21.713665Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from matplotlib import pyplot as plt\nEPOCHS = 12\n\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":"2026-04-18T05:46:24.950832Z","iopub.execute_input":"2026-04-18T05:46:24.951192Z","iopub.status.idle":"2026-04-18T05:46:25.121079Z","shell.execute_reply.started":"2026-04-18T05:46:24.951163Z","shell.execute_reply":"2026-04-18T05:46:25.119886Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Model Definition\nEPOCHS = 12\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\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        pretrained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n\n    model.compile(\n        optimizer='adam',\n        loss='sparse_categorical_crossentropy',\n        metrics=['sparse_categorical_accuracy']\n    )\n    \n    model.summary()\n    \n    history = 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":"2026-04-18T05:46:29.380464Z","iopub.execute_input":"2026-04-18T05:46:29.380765Z","iopub.status.idle":"2026-04-18T07:17:26.846822Z","shell.execute_reply.started":"2026-04-18T05:46:29.380744Z","shell.execute_reply":"2026-04-18T07:17:26.845364Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def 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":"2026-04-18T07:26:45.472141Z","iopub.execute_input":"2026-04-18T07:26:45.472459Z","iopub.status.idle":"2026-04-18T07:26:45.476931Z","shell.execute_reply.started":"2026-04-18T07:26:45.472438Z","shell.execute_reply":"2026-04-18T07:26:45.476040Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"display_training_curves(\n    history.history['loss'],\n    history.history['val_loss'],\n    'loss',\n    211,\n)\ndisplay_training_curves(\n    history.history['sparse_categorical_accuracy'],\n    history.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n    212,\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-18T07:26:53.427389Z","iopub.execute_input":"2026-04-18T07:26:53.427765Z","iopub.status.idle":"2026-04-18T07:26:54.800913Z","shell.execute_reply.started":"2026-04-18T07:26:53.427732Z","shell.execute_reply":"2026-04-18T07:26:54.799913Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import confusion_matrix\n\ncmdataset = get_validation_dataset(ordered=True)\nimages_ds = cmdataset.map(lambda image, label: image)\nlabels_ds = cmdataset.map(lambda image, label: label).unbatch()\n\ncm_correct_labels = next(iter(labels_ds.batch(NUM_VALIDATION_IMAGES))).numpy()\ncm_probabilities = model.predict(images_ds)\ncm_predictions = np.argmax(cm_probabilities, axis=-1)\n\nlabels = range(len(CLASSES))\ncmat = confusion_matrix(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n)\ncmat = (cmat.T / cmat.sum(axis=1)).T # normalize","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-18T07:26:58.788732Z","iopub.execute_input":"2026-04-18T07:26:58.789043Z","iopub.status.idle":"2026-04-18T07:29:01.124475Z","shell.execute_reply.started":"2026-04-18T07:26:58.789022Z","shell.execute_reply":"2026-04-18T07:29:01.122835Z"}},"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":"2026-04-18T07:29:14.804788Z","iopub.execute_input":"2026-04-18T07:29:14.805063Z","iopub.status.idle":"2026-04-18T07:33:31.183208Z","shell.execute_reply.started":"2026-04-18T07:29:14.805042Z","shell.execute_reply":"2026-04-18T07:33:31.182136Z"}},"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":"2026-04-18T07:33:41.846102Z","iopub.execute_input":"2026-04-18T07:33:41.846443Z","iopub.status.idle":"2026-04-18T07:33:46.673609Z","shell.execute_reply.started":"2026-04-18T07:33:41.846425Z","shell.execute_reply":"2026-04-18T07:33:46.672412Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nprint(os.listdir())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-18T07:40:21.557984Z","iopub.execute_input":"2026-04-18T07:40:21.558282Z","iopub.status.idle":"2026-04-18T07:40:21.562525Z","shell.execute_reply.started":"2026-04-18T07:40:21.558255Z","shell.execute_reply":"2026-04-18T07:40:21.561616Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.save('/kaggle/working/model.keras')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-18T07:44:21.780414Z","iopub.execute_input":"2026-04-18T07:44:21.780731Z","iopub.status.idle":"2026-04-18T07:44:22.170104Z","shell.execute_reply.started":"2026-04-18T07:44:21.780712Z","shell.execute_reply":"2026-04-18T07:44:22.169042Z"}},"outputs":[],"execution_count":null}]}