{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom kaggle_datasets import KaggleDatasets\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nprint(\"Tensorflow version \" + tf.__version__)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()  # TPU detection. No parameters necessary if TPU_NAME environment variable is set. On Kaggle this is always the case.\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() # default distribution strategy in Tensorflow. Works on CPU and single GPU.\n\nAUTO = tf.data.experimental.AUTOTUNE\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_DS_PATH = KaggleDatasets().get_gcs_path() # you can list the bucket with \"!gsutil ls $GCS_DS_PATH\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = [512,512] # at this size, a GPU will run out of memory. Use the TPU\nEPOCHS = 15\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nNUM_TRAINING_IMAGES = 12753\nNUM_TEST_IMAGES = 7382\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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) # 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)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset\n\n\ndef data_augment(image, label, seed=2020):\n    image = tf.image.random_flip_left_right(image, seed=seed)    \n    image = tf.image.random_flip_up_down(image, seed=seed)\n    #image = tf.image.random_brightness(image, 0.2, seed=seed)\n    #image = tf.image.rot90(image)\n#     image = tf.image.random_jpeg_quality(image, 85, 100, seed=seed)\n#     image = tf.image.resize(image, [530, 530])\n#     image = tf.image.random_crop(image, [512, 512], seed=seed)\n    #image = tf.image.random_saturation(image, 0, 2)\n    return image, label   \n\n\ndef get_training_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-512x512/train/*.tfrec'), 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    return dataset\n\ndef get_validation_dataset():\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-512x512/val/*.tfrec'), labeled=True, ordered=False)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.cache()\n    return dataset\n\ndef get_test_dataset(ordered=False):\n    dataset = load_dataset(tf.io.gfile.glob(GCS_DS_PATH + '/tfrecords-jpeg-512x512/test/*.tfrec'), labeled=False, ordered=ordered)\n    dataset = dataset.batch(BATCH_SIZE)\n    return dataset\n\ntraining_dataset = get_training_dataset()\nvalidation_dataset = get_validation_dataset()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():    \n    covn_base = tf.keras.applications.Xception(weights='imagenet', include_top=False ,input_shape=[*IMAGE_SIZE, 3])\n    covn_base.trainable = True\n    \n    #print(len(covn_base.layers))\n\n    #for layers in covn_base.layers[:-50]:\n        #layers.trainable = False\n    model = tf.keras.Sequential([\n        covn_base,\n        tf.keras.layers.GlobalAveragePooling2D(),\n        #tf.keras.layers.Dense(1024,activation='relu'), #添加全连接层\n        #tf.keras.layers.Dropout(rate=0.5),\n        tf.keras.layers.Dense(104, activation='softmax')\n    ])\n    \nmodel.summary()        \nmodel.compile(\n    optimizer=tf.keras.optimizers.Adam(),\n    loss = 'sparse_categorical_crossentropy',\n    metrics=['sparse_categorical_accuracy']\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def lrfn(epoch):\n    LR_START = 0.000001\n    LR_MAX = 0.00005 * strategy.num_replicas_in_sync\n    LR_MIN = 0.000001\n    LR_RAMPUP_EPOCHS = 5\n    LR_SUSTAIN_EPOCHS = 0\n    LR_EXP_DECAY = .8\n    \n    if epoch < LR_RAMPUP_EPOCHS:\n        lr = (LR_MAX - LR_START) / LR_RAMPUP_EPOCHS * epoch + LR_START\n    elif epoch < LR_RAMPUP_EPOCHS + LR_SUSTAIN_EPOCHS:\n        lr = LR_MAX\n    else:\n        lr = (LR_MAX - LR_MIN) * LR_EXP_DECAY**(epoch - LR_RAMPUP_EPOCHS - LR_SUSTAIN_EPOCHS) + LR_MIN\n    return lr\n\nrng = [i for i in range(EPOCHS)]\ny = [lrfn(x) for x in rng]\n\nfig, ax = plt.subplots(figsize=(24, 6))\nplt.plot(rng, y)\nprint(\"Learning rate schedule: {:.3g} to {:.3g} to {:.3g}\".format(y[0], max(y), y[-1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr_schedule = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=1)\n\nhistory = model.fit(training_dataset, \n          steps_per_epoch=STEPS_PER_EPOCH, \n          epochs=EPOCHS, \n          validation_data=validation_dataset,\n          callbacks=[lr_schedule])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n# plot loss and accuracy image\nhistory_dict = history.history\ntrain_loss = history_dict[\"loss\"]\ntrain_accuracy = history_dict[\"sparse_categorical_accuracy\"]\nval_loss = history_dict[\"val_loss\"]\nval_accuracy = history_dict[\"val_sparse_categorical_accuracy\"]\n\n# figure 1\nplt.figure()\nplt.plot(range(EPOCHS), train_loss, label='train_loss')\nplt.plot(range(EPOCHS), val_loss, label='val_loss')\nplt.legend()\nplt.xlabel('epochs')\nplt.ylabel('loss')\n\n# figure 2\nplt.figure()\nplt.plot(range(EPOCHS), train_accuracy, label='train_accuracy')\nplt.plot(range(EPOCHS), val_accuracy, label='val_accuracy')\nplt.legend()\nplt.xlabel('epochs')\nplt.ylabel('accuracy')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True) # since we are splitting the dataset and iterating separately on images and ids, order matters.\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)\n\nprint('Generating submission.csv file...')\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') # all in one batch\nnp.savetxt('submission.csv', np.rec.fromarrays([test_ids, predictions]), fmt=['%s', '%d'], delimiter=',', header='id,label', comments='')","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}