{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport pandas as pd\nimport numpy as np\nimport tensorflow as tf\nfrom tqdm.auto import tqdm\nimport cv2\nimport matplotlib.pyplot as plt\nfrom sklearn.preprocessing import MultiLabelBinarizer","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN = os.listdir('../input/plant-pathology-2021-fgvc8/train_images')\nprint(\"Training Images = \",len(TRAIN))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv('../input/plant-pathology-2021-fgvc8/train.csv')\ndf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"L = []\nfor i in range(len(df)):\n    labels = df['labels'].iloc[i]\n    lst = [j for j in labels.split(' ')]\n    L.append(lst)\ndf['new_labels'] = L","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"s = list(df['new_labels'])\n\nmlb = MultiLabelBinarizer()\n\nconverted_df = pd.DataFrame(mlb.fit_transform(s),columns=mlb.classes_, index=df.index)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"converted_df['image'] = df['image']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"converted_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def _bytes_feature(value):\n    \"\"\"Returns a bytes_list from a string / byte.\"\"\"\n    if isinstance(value, type(tf.constant(0))):\n        value = value.numpy() # BytesList won't unpack a string from an EagerTensor.\n    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))\n\ndef _float_feature(value):\n    \"\"\"Returns a float_list from a float / double.\"\"\"\n    return tf.train.Feature(float_list=tf.train.FloatList(value=[value]))\n\ndef _int64_feature(value):\n    \"\"\"Returns an int64_list from a bool / enum / int / uint.\"\"\"\n    return tf.train.Feature(int64_list=tf.train.Int64List(value=value))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def serialize_example(feature, name, target):\n    feature = {\n      'image': _bytes_feature(feature),\n      'name': _bytes_feature(name),\n      'label': _int64_feature(target),\n\n    }\n    example_proto = tf.train.Example(features=tf.train.Features(feature=feature))\n    return example_proto.SerializeToString()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"merged = converted_df.sample(frac=1).reset_index(drop=True)\nNUM_TFRECORDS =  68\nIMGS_PER_FILE = len(converted_df)//NUM_TFRECORDS\nfor idx in tqdm(range(NUM_TFRECORDS)):\n    with tf.io.TFRecordWriter(f'File_{idx+1}_{IMGS_PER_FILE}.tfrec') as writer:\n        for k in tqdm(range(IMGS_PER_FILE*idx, IMGS_PER_FILE*(idx+1))):\n            path ='../input/plant-pathology-2021-fgvc8/train_images/'\n            img = cv2.imread(path+merged['image'].iloc[k])\n            img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)\n            img = cv2.resize(img,(512,512))\n            img = cv2.imencode('.jpg', img, (cv2.IMWRITE_JPEG_QUALITY, 94))[1].tostring()\n            name = merged['image'].iloc[k].split('.')[0]\n            target = list(merged.iloc[k])[:-1]\n            example = serialize_example(\n              img,\n              str.encode(name),\n              target\n            )\n            writer.write(example)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE= [512,512]; BATCH_SIZE = 16\nAUTO = tf.data.experimental.AUTOTUNE\nTRAINING_FILENAMES = tf.io.gfile.glob('./*.tfrec')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAINING_FILENAMES","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import math\nnp.set_printoptions(threshold=15, linewidth=80)\nCLASSES = [0,1]\n\ndef batch_to_numpy_images_and_labels(data):\n    images, labels = data\n    numpy_images = images.numpy()\n    numpy_labels = labels.numpy()\n    labels = [str(i) for i in  numpy_labels]\n    # decoder = np.vectorize(lambda x: x.decode('UTF-8'))\n    # numpy_labels = decoder(numpy_labels)\n    # numpy_images = numpy_images[:,:,::-1]\n    #if numpy_labels.dtype == object: # binary string in this case, 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 the case for test data)\n    return numpy_images, 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 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 = 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        # image = cv2.imdecode(image,cv2.IMREA)\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)","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    channels = tf.unstack(image, axis=-1)\n    image    = tf.stack([channels[2], channels[1], channels[0]], axis=-1)\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), \n        \"name\":tf.io.FixedLenFeature([],tf.string),\n        \"label\": tf.io.FixedLenFeature([6], tf.int64,default_value=[0,0,0,0,0,0]),\n\n    }\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    image = decode_image(example['image'])\n    label = (example['label'])\n    return image, label # returns a dataset of (image, label) pairs\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)\n    # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n    return dataset\n\ndef get_training_dataset():\n    dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"training_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(16)\ntrain_batch = iter(training_dataset)\n\ndisplay_batch_of_images(next(train_batch))","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}