{"metadata":{"colab":{"provenance":[],"gpuType":"T4"},"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"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"},"accelerator":"GPU","kaggle":{"accelerator":"none","dataSources":[{"sourceId":21154,"databundleVersionId":1243559,"sourceType":"competition"}],"dockerImageVersionId":30732,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import tensorflow as tf\nimport zipfile,os,shutil\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.applications import MobileNetV2\nfrom tensorflow.keras.layers import Input\nimport math, re, os\nimport numpy as np","metadata":{"id":"rGnOt39V7AII","execution":{"iopub.status.busy":"2024-06-29T13:17:56.299403Z","iopub.execute_input":"2024-06-29T13:17:56.299865Z","iopub.status.idle":"2024-06-29T13:17:56.308732Z","shell.execute_reply.started":"2024-06-29T13:17:56.299819Z","shell.execute_reply":"2024-06-29T13:17:56.307424Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [192, 192]\nAUTO = tf.data.experimental.AUTOTUNE\nTRAINING_FILENAMES = tf.io.gfile.glob('/kaggle/input/tpu-getting-started/tfrecords-jpeg-192x192/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob('/kaggle/input/tpu-getting-started/tfrecords-jpeg-192x192/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob('/kaggle/input/tpu-getting-started/tfrecords-jpeg-192x192/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  \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), \n        \"class\": tf.io.FixedLenFeature([], tf.int64),  \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), \n        \"id\": tf.io.FixedLenFeature([], tf.string), \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    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    return dataset","metadata":{"id":"cWS7LnSLIGdk","execution":{"iopub.status.busy":"2024-06-29T13:17:56.960370Z","iopub.execute_input":"2024-06-29T13:17:56.960802Z","iopub.status.idle":"2024-06-29T13:17:56.997114Z","shell.execute_reply.started":"2024-06-29T13:17:56.960767Z","shell.execute_reply":"2024-06-29T13:17:56.995896Z"},"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() \n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO) \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    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":{"id":"dcPi-W_KIzww","outputId":"ee95a2a6-1234-4dde-f316-fc6b9b3d65dd","execution":{"iopub.status.busy":"2024-06-29T13:18:00.348598Z","iopub.execute_input":"2024-06-29T13:18:00.349050Z","iopub.status.idle":"2024-06-29T13:18:00.365701Z","shell.execute_reply.started":"2024-06-29T13:18:00.349013Z","shell.execute_reply":"2024-06-29T13:18:00.363981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128 (=16*8) with TPU on\nstrategy = tf.distribute.get_strategy()\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":{"id":"cW7dD4CRJCDX","outputId":"da4c38e0-9fec-4cd6-b14e-dda25266ddb9","execution":{"iopub.status.busy":"2024-06-29T13:18:02.265494Z","iopub.execute_input":"2024-06-29T13:18:02.266049Z","iopub.status.idle":"2024-06-29T13:18:02.774564Z","shell.execute_reply.started":"2024-06-29T13:18:02.266005Z","shell.execute_reply":"2024-06-29T13:18:02.773208Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.set_printoptions(threshold=15, linewidth=80)\n\nprint(\"Training shapes:\")\nfor image, label in ds_train.take(3):\n    print(image.numpy().shape, label.numpy().shape)\nprint(\"Training label examples:\", label.numpy())","metadata":{"id":"P3z43Je_JaHj","outputId":"89efb984-9483-454d-cdc7-946ef68f01da","execution":{"iopub.status.busy":"2024-06-29T13:18:02.776925Z","iopub.execute_input":"2024-06-29T13:18:02.778253Z","iopub.status.idle":"2024-06-29T13:18:04.204080Z","shell.execute_reply.started":"2024-06-29T13:18:02.778203Z","shell.execute_reply":"2024-06-29T13:18:04.202758Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Test shapes:\")\nfor image, idnum in ds_test.take(3):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test IDs:\", idnum.numpy().astype('U')) # U=unicode string","metadata":{"id":"BtcN4aZPJhZS","outputId":"b1d30e5e-9056-463e-9203-8ea655c528a9","execution":{"iopub.status.busy":"2024-06-29T13:18:07.300998Z","iopub.execute_input":"2024-06-29T13:18:07.301484Z","iopub.status.idle":"2024-06-29T13:18:07.398967Z","shell.execute_reply.started":"2024-06-29T13:18:07.301440Z","shell.execute_reply":"2024-06-29T13:18:07.397379Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nfrom 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":{"id":"JffgzKiEJncS","execution":{"iopub.status.busy":"2024-06-29T13:18:07.445808Z","iopub.execute_input":"2024-06-29T13:18:07.446280Z","iopub.status.idle":"2024-06-29T13:18:07.471354Z","shell.execute_reply.started":"2024-06-29T13:18:07.446242Z","shell.execute_reply":"2024-06-29T13:18:07.470000Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(3))","metadata":{"id":"MJe7wA-SJp3R","execution":{"iopub.status.busy":"2024-06-29T13:18:08.128669Z","iopub.execute_input":"2024-06-29T13:18:08.129101Z","iopub.status.idle":"2024-06-29T13:18:08.171767Z","shell.execute_reply.started":"2024-06-29T13:18:08.129067Z","shell.execute_reply":"2024-06-29T13:18:08.170451Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"one_batch = next(ds_iter)\ndisplay_batch_of_images(one_batch)","metadata":{"id":"s_vqPoWdJrhi","outputId":"0d1fd879-655c-4883-a86f-beacf17056c5","execution":{"iopub.status.busy":"2024-06-29T13:18:08.304172Z","iopub.execute_input":"2024-06-29T13:18:08.304604Z","iopub.status.idle":"2024-06-29T13:18:10.103301Z","shell.execute_reply.started":"2024-06-29T13:18:08.304563Z","shell.execute_reply":"2024-06-29T13:18:10.101762Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 12\n\n\nmodel = tf.keras.models.Sequential([\n  MobileNetV2(weights=\"imagenet\", include_top=False,input_tensor=Input(shape=(192, 192, 3))),\n  tf.keras.layers.Conv2D(160, (3, 3), padding='same',activation='relu'),\n  tf.keras.layers.MaxPooling2D(2,2),\n  tf.keras.layers.BatchNormalization(),\n  tf.keras.layers.Flatten(),\n  tf.keras.layers.Dense(512, activation='relu'),\n  tf.keras.layers.Dense(256, activation='relu'),\n  tf.keras.layers.Dense(104, activation='softmax'),\n\n])\n\nmodel.layers[0].trainable = False","metadata":{"id":"CBIBfCSmLOIw","outputId":"5298420a-326b-45c3-faff-c421d7503bb5","execution":{"iopub.status.busy":"2024-06-29T13:18:10.105216Z","iopub.execute_input":"2024-06-29T13:18:10.105571Z","iopub.status.idle":"2024-06-29T13:18:11.729563Z","shell.execute_reply.started":"2024-06-29T13:18:10.105541Z","shell.execute_reply":"2024-06-29T13:18:11.727975Z"},"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":{"id":"lwEAXN4XLQwQ","outputId":"6a339c40-a311-4a8f-ac30-4f38eea20082","execution":{"iopub.status.busy":"2024-06-29T13:18:11.731440Z","iopub.execute_input":"2024-06-29T13:18:11.731832Z","iopub.status.idle":"2024-06-29T13:18:11.785121Z","shell.execute_reply.started":"2024-06-29T13:18:11.731798Z","shell.execute_reply":"2024-06-29T13:18:11.784002Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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)","metadata":{"id":"PYobrp0EML-D","execution":{"iopub.status.busy":"2024-06-29T13:18:11.788249Z","iopub.execute_input":"2024-06-29T13:18:11.788736Z","iopub.status.idle":"2024-06-29T13:18:11.798133Z","shell.execute_reply.started":"2024-06-29T13:18:11.788689Z","shell.execute_reply":"2024-06-29T13:18:11.796882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCHS = 12\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(\n      ds_train,\n      steps_per_epoch=STEPS_PER_EPOCH,\n      epochs=EPOCHS,\n      validation_data=ds_valid,\n      validation_steps=25,\n      verbose=2,\n        callbacks = [lr_callback]\n    )","metadata":{"id":"yWGIOmnkLsjx","outputId":"628296e9-afce-40d1-910e-db634f532ddf","execution":{"iopub.status.busy":"2024-06-29T13:18:11.799680Z","iopub.execute_input":"2024-06-29T13:18:11.800130Z","iopub.status.idle":"2024-06-29T13:56:36.063099Z","shell.execute_reply.started":"2024-06-29T13:18:11.800089Z","shell.execute_reply":"2024-06-29T13:56:36.059798Z"},"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":{"id":"AbDy36jrOqJd","outputId":"900d6f90-d7de-4ec9-86da-55dbac7f14d7","execution":{"iopub.status.busy":"2024-06-29T13:56:40.988112Z","iopub.execute_input":"2024-06-29T13:56:40.988951Z","iopub.status.idle":"2024-06-29T13:56:41.041353Z","shell.execute_reply.started":"2024-06-29T13:56:40.988909Z","shell.execute_reply":"2024-06-29T13:56:41.038994Z"},"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":{"id":"3hCUyQWtO929","execution":{"iopub.status.busy":"2024-06-29T13:56:41.042293Z","iopub.status.idle":"2024-06-29T13:56:41.042745Z","shell.execute_reply.started":"2024-06-29T13:56:41.042531Z","shell.execute_reply":"2024-06-29T13:56:41.042549Z"},"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 ","metadata":{"id":"gNmuI3I0PAMk","outputId":"bc37753f-486f-4f78-ab60-b286bd3ceb22","execution":{"iopub.status.busy":"2024-06-29T13:56:41.044076Z","iopub.status.idle":"2024-06-29T13:56:41.044540Z","shell.execute_reply.started":"2024-06-29T13:56:41.044326Z","shell.execute_reply":"2024-06-29T13:56:41.044344Z"},"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":{"id":"WPgk3mrEPCuo","outputId":"082fd6e6-a8d1-4da3-ae73-85da8af60de2","execution":{"iopub.status.busy":"2024-06-29T13:56:41.045822Z","iopub.status.idle":"2024-06-29T13:56:41.046295Z","shell.execute_reply.started":"2024-06-29T13:56:41.046033Z","shell.execute_reply":"2024-06-29T13:56:41.046049Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataset = get_validation_dataset()\ndataset = dataset.unbatch().batch(20)\nbatch = iter(dataset)","metadata":{"id":"rSPbO0QKPbdU","execution":{"iopub.status.busy":"2024-06-29T13:56:41.048572Z","iopub.status.idle":"2024-06-29T13:56:41.049025Z","shell.execute_reply.started":"2024-06-29T13:56:41.048816Z","shell.execute_reply":"2024-06-29T13:56:41.048834Z"},"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":{"id":"5RG3Lr-rPeXs","outputId":"f0a5bf94-342e-4ce5-85d8-e8f64f5c74cd","execution":{"iopub.status.busy":"2024-06-29T13:56:41.050142Z","iopub.status.idle":"2024-06-29T13:56:41.050549Z","shell.execute_reply.started":"2024-06-29T13:56:41.050351Z","shell.execute_reply":"2024-06-29T13:56:41.050368Z"},"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":{"id":"X6bOi48pPquw","outputId":"a615d4bb-7416-40fe-f71d-56ba96b9edfd","execution":{"iopub.status.busy":"2024-06-29T13:56:41.052591Z","iopub.status.idle":"2024-06-29T13:56:41.053080Z","shell.execute_reply.started":"2024-06-29T13:56:41.052838Z","shell.execute_reply":"2024-06-29T13:56:41.052857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('submission.csv file')\n\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\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!head submission.csv","metadata":{"id":"-dswRBqZPxWA","outputId":"c4c83a26-2bfc-49b2-fb44-e6070db360ce","execution":{"iopub.status.busy":"2024-06-29T13:56:41.055031Z","iopub.status.idle":"2024-06-29T13:56:41.055503Z","shell.execute_reply.started":"2024-06-29T13:56:41.055295Z","shell.execute_reply":"2024-06-29T13:56:41.055315Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}