{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"tpu1vmV38","dataSources":[{"sourceId":21154,"databundleVersionId":1243559,"sourceType":"competition"},{"sourceId":37130068,"sourceType":"kernelVersion"}],"dockerImageVersionId":30646,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"\n# Introduction #\n\nHalooooo;\nperkenalkan nama aku keindra bagas maulana dengan gdsc id 23111110000554 dan di notebook ini aku belajar untuk mengklasifikasikan gambar...\ndan kebetulan notebook ini dikumpulkan sebagai pengumpulan penugasan dari GDSC ITB \nrequirement tugas:\nTask 1: Flower Classification\n//\n- Dataset: Petals to the Metal - Flower Classification on TPU | Kaggle\n- Classify over 100 species of flower using deep learning methods.\n- Create your own notebook or expand the tutorial notebook (here) with your own work.\n- You can create your own models from scratch or use pretrained models to classify the images. You can - also try both models to compare.\n- Submit your predictions to the open competition above.\n//\nkarena sudah memenuhi requirment dan sudah bisa mengklasifikasikan 104 tipe bunga mengunakan tensorflow berdasarkan gambar.\nberikut ini adalah notebook ku, sedikit banyak masih mengambil refrensi dari orang. mohon maaf bila ada kesalahan","metadata":{}},{"cell_type":"code","source":"import math\nimport re\nimport os\nimport numpy as np\nimport tensorflow as tf\nfrom kaggle_datasets import KaggleDatasets\nfrom matplotlib import pyplot as plt\nfrom tensorflow.keras.callbacks import LearningRateScheduler\n\nprint(\"Tensorflow version \" + tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2024-04-30T16:26:25.078046Z","iopub.execute_input":"2024-04-30T16:26:25.07846Z","iopub.status.idle":"2024-04-30T16:26:28.778338Z","shell.execute_reply.started":"2024-04-30T16:26:25.078421Z","shell.execute_reply":"2024-04-30T16:26:28.777346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Detect TPU, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    if tpu:\n        tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n        tf.config.experimental_connect_to_cluster(tpu)\n        tf.tpu.experimental.initialize_tpu_system(tpu)\n        print('Running on TPU')\n    else:\n        print(\"Not connected to a TPU runtime. Using CPU/GPU strategy.\")\nexcept Exception as e:\n    print(\"Error occurred while connecting to TPU:\", str(e))\n    tpu = None\n\n# Create the TPU strategy outside the model.fit call (if TPU is available)\nif tpu:\n    tpu_strategy = tf.distribute.TPUStrategy(tpu)\nelse:\n    tpu_strategy = None","metadata":{"execution":{"iopub.status.busy":"2024-04-30T16:26:28.779817Z","iopub.execute_input":"2024-04-30T16:26:28.780269Z","iopub.status.idle":"2024-04-30T16:26:36.530806Z","shell.execute_reply.started":"2024-04-30T16:26:28.780238Z","shell.execute_reply":"2024-04-30T16:26:36.529786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path('tpu-getting-started')\nprint(GCS_DS_PATH) # what do gcs paths look like?","metadata":{"execution":{"iopub.status.busy":"2024-04-30T16:26:43.92801Z","iopub.execute_input":"2024-04-30T16:26:43.929178Z","iopub.status.idle":"2024-04-30T16:26:43.934032Z","shell.execute_reply.started":"2024-04-30T16:26:43.929132Z","shell.execute_reply":"2024-04-30T16:26:43.93304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nIMAGE_SIZE = [512, 512]\nGCS_PATH = GCS_DS_PATH + '/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\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":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-30T16:26:45.480177Z","iopub.execute_input":"2024-04-30T16:26:45.480583Z","iopub.status.idle":"2024-04-30T16:26:45.507889Z","shell.execute_reply.started":"2024-04-30T16:26:45.48055Z","shell.execute_reply":"2024-04-30T16:26:45.506952Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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))\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-30T16:26:46.65078Z","iopub.execute_input":"2024-04-30T16:26:46.65159Z","iopub.status.idle":"2024-04-30T16:26:46.660658Z","shell.execute_reply.started":"2024-04-30T16:26:46.651549Z","shell.execute_reply":"2024-04-30T16:26:46.659683Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define batch size (adjusted based on strategy)\nBATCH_SIZE = 16 * (tpu_strategy.num_replicas_in_sync if tpu_strategy else 1)\n\n# Load datasets (assuming the rest of your code defines these functions)\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":{"execution":{"iopub.status.busy":"2024-04-30T16:28:00.201533Z","iopub.execute_input":"2024-04-30T16:28:00.201919Z","iopub.status.idle":"2024-04-30T16:28:00.319198Z","shell.execute_reply.started":"2024-04-30T16:28:00.201888Z","shell.execute_reply":"2024-04-30T16:28:00.318225Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-04-30T16:28:01.421667Z","iopub.execute_input":"2024-04-30T16:28:01.422066Z","iopub.status.idle":"2024-04-30T16:28:04.599767Z","shell.execute_reply.started":"2024-04-30T16:28:01.422034Z","shell.execute_reply":"2024-04-30T16:28:04.598777Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":{"execution":{"iopub.status.busy":"2024-04-30T16:28:04.731724Z","iopub.execute_input":"2024-04-30T16:28:04.7321Z","iopub.status.idle":"2024-04-30T16:28:05.699519Z","shell.execute_reply.started":"2024-04-30T16:28:04.732069Z","shell.execute_reply":"2024-04-30T16:28:05.698531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-30T16:28:05.701031Z","iopub.execute_input":"2024-04-30T16:28:05.701346Z","iopub.status.idle":"2024-04-30T16:28:05.717587Z","shell.execute_reply.started":"2024-04-30T16:28:05.701315Z","shell.execute_reply":"2024-04-30T16:28:05.716718Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","metadata":{"execution":{"iopub.status.busy":"2024-04-30T16:28:06.272643Z","iopub.execute_input":"2024-04-30T16:28:06.273036Z","iopub.status.idle":"2024-04-30T16:28:06.670904Z","shell.execute_reply.started":"2024-04-30T16:28:06.273003Z","shell.execute_reply":"2024-04-30T16:28:06.669842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"execution":{"iopub.status.busy":"2024-04-30T16:28:07.072973Z","iopub.execute_input":"2024-04-30T16:28:07.073321Z","iopub.status.idle":"2024-04-30T16:28:10.580873Z","shell.execute_reply.started":"2024-04-30T16:28:07.073288Z","shell.execute_reply":"2024-04-30T16:28:10.579728Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 12\n\nwith tpu_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        # Base pretrained model\n        pretrained_model,\n        \n        # Additional layers for classification\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(1024, activation='relu'),  # Additional dense layer\n        tf.keras.layers.Dropout(0.5),                    # Dropout layer for regularization\n        tf.keras.layers.Dense(512, activation='relu'),   # Additional dense layer\n        tf.keras.layers.Dropout(0.5),                    # Dropout layer for regularization\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n","metadata":{"execution":{"iopub.status.busy":"2024-04-30T16:28:10.582343Z","iopub.execute_input":"2024-04-30T16:28:10.582627Z","iopub.status.idle":"2024-04-30T16:28:11.13294Z","shell.execute_reply.started":"2024-04-30T16:28:10.582599Z","shell.execute_reply":"2024-04-30T16:28:11.132038Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(\n    optimizer='adam',\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy'],\n)\n\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2024-04-30T16:28:11.133965Z","iopub.execute_input":"2024-04-30T16:28:11.134243Z","iopub.status.idle":"2024-04-30T16:28:11.152358Z","shell.execute_reply.started":"2024-04-30T16:28:11.134216Z","shell.execute_reply":"2024-04-30T16:28:11.151726Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\n    return lr(epoch, start_lr, min_lr, max_lr, rampup_epochs, sustain_epochs, 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]))\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-30T16:30:26.686385Z","iopub.execute_input":"2024-04-30T16:30:26.686793Z","iopub.status.idle":"2024-04-30T16:30:26.84995Z","shell.execute_reply.started":"2024-04-30T16:30:26.686762Z","shell.execute_reply":"2024-04-30T16:30:26.849033Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define training epochs\nEPOCHS = 12\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\n# Train the model within the TPU strategy scope (if applicable)\nif tpu_strategy:\n    with tpu_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        ])\n\n        model.compile(optimizer='adam',\n                      loss='sparse_categorical_crossentropy',\n                      metrics=['accuracy'])\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        )\nelse:\n    # Train with default strategy (CPU or GPU)\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    ])\n\n    model.compile(optimizer='adam',\n                  loss='sparse_categorical_crossentropy',\n                  metrics=['accuracy'])\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":{"execution":{"iopub.status.busy":"2024-04-30T16:30:48.861448Z","iopub.execute_input":"2024-04-30T16:30:48.861882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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_count":null,"outputs":[]},{"cell_type":"code","source":"\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\n\ndef display_confusion_matrix(cmat, score, precision, recall):\n    plt.figure(figsize=(15,15))\n    ax = plt.gca()\n    ax.matshow(cmat, cmap='Reds')\n    ax.set_xticks(range(len(CLASSES)))\n    ax.set_xticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_xticklabels(), rotation=45, ha=\"left\", rotation_mode=\"anchor\")\n    ax.set_yticks(range(len(CLASSES)))\n    ax.set_yticklabels(CLASSES, fontdict={'fontsize': 7})\n    plt.setp(ax.get_yticklabels(), rotation=45, ha=\"right\", rotation_mode=\"anchor\")\n    titlestring = \"\"\n    if score is not None:\n        titlestring += 'f1 = {:.3f} '.format(score)\n    if precision is not None:\n        titlestring += '\\nprecision = {:.3f} '.format(precision)\n    if recall is not None:\n        titlestring += '\\nrecall = {:.3f} '.format(recall)\n    if len(titlestring) > 0:\n        ax.text(101, 1, titlestring, fontdict={'fontsize': 18, 'horizontalalignment':'right', 'verticalalignment':'top', 'color':'#804040'})\n    plt.show()\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":{"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cmdataset = 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_count":null,"outputs":[]},{"cell_type":"code","source":"score = f1_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nprecision = precision_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\nrecall = recall_score(\n    cm_correct_labels,\n    cm_predictions,\n    labels=labels,\n    average='macro',\n)\ndisplay_confusion_matrix(cmat, score, precision, recall)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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_count":null,"outputs":[]},{"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_count":null,"outputs":[]},{"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_count":null,"outputs":[]},{"cell_type":"markdown","source":"---\n\n\n\n\n*Have questions or comments? Visit the [Learn Discussion forum](https://www.kaggle.com/learn-forum/161321) to chat with other Learners.*","metadata":{}}]}