{"cells":[{"metadata":{},"cell_type":"markdown","source":"In this project, we'll make our first submission to the [**Petals to the Metal**](https://www.kaggle.com/c/tpu-getting-started) competition.  We'll learn how to accept the competition rules, run a notebook on Kaggle that uses (free!) TPUs, and how to submit your results to the leaderboard.\n\nBegin by running the next code cell to set up the notebook."},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install -U -t /kaggle/working/ git+https://github.com/Kaggle/learntools.git\nfrom learntools.core import binder\nbinder.bind(globals())\nfrom learntools.deep_learning.ex_tpu import *\nstep_1.check()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"If the code cell returns `Setup complete.`, then you're ready to continue."},{"metadata":{},"cell_type":"markdown","source":"# 1. Load Helper Functions"},{"metadata":{"trusted":true},"cell_type":"code","source":"from petal_helper import *","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 2. Create Distribution Strategy"},{"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":{},"cell_type":"markdown","source":"# 3. Loading the Competition Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = get_training_dataset()\nvalid_data = get_validation_dataset()\ntest_data = get_test_dataset()\n\nprint(\"Training:\", train_data)\nprint (\"Validation:\", valid_data)\nprint(\"Test:\", test_data)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 4. Explore the Data\n\nTry using some of the helper functions described in the **Getting Started** tutorial to explore the dataset."},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Number of classes: {}\".format(len(CLASSES)))\n\nprint(\"First five classes, sorted alphabetically:\")\nfor name in sorted(CLASSES)[:15]:\n    print(name)\n\nprint (\"Number of training images: {}\".format(NUM_TRAINING_IMAGES))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Examine the shape of the data."},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Training data shapes:\")\nfor image, label in train_data.take(10):\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 test_data.take(10):\n    print(image.numpy().shape, idnum.numpy().shape)\nprint(\"Test data IDs:\", idnum.numpy().astype('U')) # U=unicode string","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Peek at training data."},{"metadata":{"trusted":true},"cell_type":"code","source":"one_batch = next(iter(train_data.unbatch().batch(20)))\ndisplay_batch_of_images(one_batch)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 5. Define Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    pretrained_model = tf.keras.applications.ResNet152V2(\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(512, activation='relu'),\n        tf.keras.layers.Dropout(0.5),\n        tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n    ])\n    model.compile(\n        optimizer='adam',\n        loss = 'sparse_categorical_crossentropy',\n        metrics=['sparse_categorical_accuracy'],\n    )\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 6. Train Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Define the batch size. This will be 16 with TPU off and 128 with TPU on\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\n# Define training epochs for committing/submitting. (TPU on)\nEPOCHS = 20\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\n\nhistory = model.fit(train_data,validation_data=valid_data,epochs=EPOCHS,steps_per_epoch=STEPS_PER_EPOCH,)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Examine training curves."},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 7. Validation\n\nCreate a confusion matrix."},{"metadata":{"trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Look at examples from the dataset, with true and predicted classes."},{"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":{},"cell_type":"markdown","source":"# 8. Test Predictions\n\nCreate predictions to submit to the competition."},{"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":{},"cell_type":"markdown","source":"# 9. submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Generating and save the submission.csv file...')\n\n# Get image ids from test set and convert to integers\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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nsubmission = pd.read_csv('submission.csv', index_col=0)\nsubmission.head(15)","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}