{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import math, re, os \nimport numpy as np\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(tf.__version__)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from kaggle_datasets import KaggleDatasets\n\nGCS_DS_PATH=KaggleDatasets().get_gcs_path('tpu-getting-started')\nprint(GCS_DS_PATH)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_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\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    # concert image to floats [0,1,] range\n    image=tf.reshape(image,[*IMAGE_SIZE,3])\n    # 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),\n        # tf.string means bytestring\n        \"class\": tf.io.FixedLenFeature([],tf.int64)\n        # 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  # returns a dataset of image(s)\n\n\ndef read_unlabeled_tfrecord(example):\n    UNLABELED_TFREC_FORMAT = {\n        \"image\": tf.io.FixedLenFeature([],tf.string),\n        # tf.string means bytestring\n        \"id\": tf.io.FixedLenFeature([],tf.string)\n        # shape [] means single element\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 # returns a dataset of image(s)\n\n\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\n        # disable order, increase speed\n        \n    dataset=tf.data.TFRecordDataset(filenames,num_parallel_reads=AUTO)\n        # automatically interleaves reads from multiple files\n    dataset=dataset.with_options(ignore_order)\n        # uses data as soon as it strams it, rather than in its original order\n    dataset=dataset.map(read_labeled_tfrecord if labeled else\n                           read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n        # returns a dataset of (image, label) pairs if labeled=True \n        # or (image, id) pairs if labeled=False \n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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_crop(image, size=[512,512,3])\n    image=tf.image.random_flip_left_right(image)\n    \n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label \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    # the training dataset must repeat for several epochs\n    dataset=dataset.shuffle(2048)\n    dataset=dataset.batch(BATCH_SIZE)\n    dataset=dataset.prefetch(AUTO)\n    # 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\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    # prefetch next batch while training (autotune prefetch buffer size)\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'\n     .format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES,NUM_TEST_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128\n# (=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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.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    \n    if numpy_labels.dtype ==object:\n        # 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 \n    # (this is 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 \n                               '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\n                 else int(titlesize/1.2), color ='red' if red else\n                 'black',fontdict={'verticalalignment':'center'},\n                 pad = int(titlesize/1.5))\n    return (subplot[0],subplot[1],subplot[2]+1)\n\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 in to square\n    # or square-ish rectangle \n    rows=int(math.sqrt(len(images)))\n    cols =len(images)//rows \n    \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\n    # magic formula tested to work from 1x1 to 10*10 unages\n        subplot=display_one_flower(image, title, subplot, \n                                  not correct, titlesize=dynamic_titlesize)\n        \n    plt.tight_layout()\n    if label is None and predictions is None:\n        plt.subplots_adjust(wspce=0, hspace=0)\n    else:\n        plt.subplots_adjust(wspace=0, hspace=SPACING)\n    plt.show()\n        \ndef display_training_curves(training, validation, title, subplot):\n    if subplot%10==1:\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'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ds_iter = iter(ds_train.unbatch().batch(20))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\none_element = tf.data.Dataset.from_tensors( next(iter(dataset)) )\naugmented_element = one_element.repeat().map(data_augment).batch(25)\n\ndisplay_batch_of_images(next(iter(augmented_element)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Learning Rate Schedule for Fine Tuning # \nEPOCHS=20\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    def lr(epoch, start_lr, min_lr,max_lr,rampup_epochs,sustain_epochs,\n          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        elif epoch < rampup_epochs + sustain_epochs:\n            lr = max_lr \n        else:\n            lr = ((max_lr - min_lr)* exp_decay ** (epoch-rampup_epochs-sustain_epochs)\n                  + min_lr)\n            \n        return lr\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],\n                                                                 max(y),\n                                                                 y[-1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 20\nwith strategy.scope():\n    pretained_model=tf.keras.applications.EfficientNetB7(\n    weights='imagenet',\n    include_top=False,\n    input_shape=[*IMAGE_SIZE,3]\n    )\n    pretained_model.trainable = True\n    model = tf.keras.Sequential([\n        pretained_model,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dropout(0.2),                             \n        tf.keras.layers.Dense(len(CLASSES),activation='softmax')])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='sparse_categorical_crossentropy',optimizer='adam',metrics=['sparse_categorical_accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.callbacks import EarlyStopping\nearlystopping=EarlyStopping(monitor='val_loss',patience=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Define training epochs\nEPOCHS = 20\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES//BATCH_SIZE\n\nhistory = model.fit(ds_train,validation_data=ds_valid,\n                   epochs=EPOCHS,\n                   steps_per_epoch=STEPS_PER_EPOCH,callbacks=[lr_callback,earlystopping]\n                   )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display_training_curves(\n    history.history['loss'],\n    history.history['val_loss'],\n    'loss',\n    211)\ndisplay_training_curves(\n    history.history['sparse_categorical_accuracy'],\n    history.history['val_sparse_categorical_accuracy'],\n    'accuracy',\n212)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import 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='Blues')\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={\n            'fontsize':18,\n            'horizontalalignment':'right',\n            'verticalalignment':'top',\n            'color':'#804040'\n        })\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_xlabel('epoch')\n    ax.legend(['train','valid'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cmdataset=get_validation_dataset(ordered=True)\nimage_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(image_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,)\ncmat= (cmat.T/cmat.sum(axis=1)).T #normalize","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"score=f1_score(cm_correct_labels,cm_predictions,labels=labels,average='macro')\nprecision=precision_score(cm_correct_labels,cm_predictions,labels=labels,average='macro')\nrecall=recall_score(cm_correct_labels,cm_predictions,labels=labels,average='macro')\ndisplay_confusion_matrix(cmat,score,precision,recall)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset=get_validation_dataset()\ndataset=dataset.unbatch().batch(20)\nbatch=iter(dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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\nnp.savetxt('submission.csv',np.rec.fromarrays([test_ids,predictions]),\n          fmt=['%s', '%d'],\n          delimiter=',',\n          header='id,label',\n          comments='',)\n\n\n!head submssion.csv","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import h5py \nsave_model = model.save('Efficienet_B7_model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}