add code

+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"augmentation.ipynb","provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyM0lQ+UqU7Sa/uXs3VwvxDl"},"kernelspec":{"name":"python3","display_name":"Python 3"}},"cells":[{"cell_type":"code","metadata":{"id":"wYGqloqDkEoU","colab_type":"code","outputId":"0d22028c-119d-4823-df3f-35d439ca019f","executionInfo":{"status":"ok","timestamp":1591716524562,"user_tz":-540,"elapsed":32835,"user":{"displayName":"‍신아형[학생](소프트웨어융합대학 컴퓨터공학과)","photoUrl":"","userId":"02057930622140727302"}},"colab":{"base_uri":"https://localhost:8080/","height":127}},"source":["from google.colab import drive\n","drive.mount('/content/gdrive')"],"execution_count":0,"outputs":[{"output_type":"stream","text":["Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly\n","\n","Enter your authorization code:\n","··········\n","Mounted at /content/gdrive\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"cPpLXwOPGYkB","colab_type":"code","colab":{}},"source":["import imgaug; print(imgaug.__file__)\n","!cd /content/../usr/local/lib/python3.6/dist-packages/\n","!pip uninstall imgaug\n","!pip install git+https://github.com/aleju/imgaug.git\n","!pip3 install pascal_voc_writer"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"3WumbxkdSAYo","colab_type":"code","colab":{}},"source":["# xml파일 파싱해서 filename, bounding-box 정보 반환\n","\n","import xml.etree.ElementTree as ET\n","\n","def read_anntation(xml_file: str):\n","    tree = ET.parse(xml_file)\n","    root = tree.getroot()\n","\n","    bounding_box_list = []\n","\n","    file_name = root.find('filename').text\n","    for obj in root.iter('object'):\n","\n","        object_label = obj.find(\"name\").text\n","        for box in obj.findall(\"bndbox\"):\n","            x_min = int(box.find(\"xmin\").text)\n","            y_min = int(box.find(\"ymin\").text)\n","            x_max = int(box.find(\"xmax\").text)\n","            y_max = int(box.find(\"ymax\").text)\n","\n","        bounding_box = [object_label, x_min, y_min, x_max, y_max]\n","        bounding_box_list.append(bounding_box)\n","\n","    return bounding_box_list, file_name"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"A-982sMgSOCV","colab_type":"code","colab":{}},"source":["# 4차원 nparray로 변환된 이미지, [bounding-box 리스트, xml 파일명, 이미지 파일명] 리스트 반환\n","\n","from os import listdir\n","import cv2\n","import numpy as np\n","\n","def read_train_dataset(dir):\n","    images = []\n","    annotations = []\n","\n","    for file in listdir(dir):\n","        if 'jpg' in file.lower() or 'png' in file.lower():\n","            images.append(cv2.imread(dir + file, 1))\n","            annotation_file = file.replace(file.split('.')[-1], 'xml')\n","            bounding_box_list, file_name = read_anntation(dir + annotation_file)\n","            annotations.append((bounding_box_list, annotation_file, file_name))\n","\n","    images = np.array(images)\n","\n","    return images, annotations"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"5Kz66PqlST6Q","colab_type":"code","colab":{}},"source":["import imgaug as ia\n","from imgaug import augmenters as iaa\n","from pascal_voc_writer import Writer\n","\n","ia.seed(1)\n","\n","\n","dir = '/content/gdrive/My Drive/capstone/data/'   # input 이미지 디렉토리\n","output_dir='/content/gdrive/My Drive/capstone/data/'   # output 이미지 디렉토리\n","\n","images, annotations = read_train_dataset(dir)\n","\n","for idx in range(len(images)):\n","    image = images[idx]\n","    boxes = annotations[idx][0]\n","\n","    ia_bounding_boxes = []\n","    for box in boxes:\n","        ia_bounding_boxes.append(ia.BoundingBox(x1=box[1], y1=box[2], x2=box[3], y2=box[4]))\n","    bbs = ia.BoundingBoxesOnImage(ia_bounding_boxes, shape=image.shape)\n","\n","    ######어둡게\n","    seq = iaa.MultiplyAndAddToBrightness(mul=(0.5, 0.5), add=(-10, 10))\n","\n","    ######밝게\n","    #seq = iaa.MultiplyAndAddToBrightness(mul= (1, 2.5), add=(-15, 15))\n","\n","    seq_det = seq.to_deterministic()\n","\n","    image_aug = seq_det.augment_images([image])[0]\n","    bbs_aug = seq_det.augment_bounding_boxes([bbs])[0]\n","\n","    new_image_file = output_dir + 'dark_' + annotations[idx][2]\n","    cv2.imwrite(new_image_file, image_aug)\n","\n","    h, w = np.shape(image_aug)[0:2]\n","    voc_writer = Writer(new_image_file, w, h)\n","\n","    for i in range(len(bbs_aug.bounding_boxes)):\n","        bb_box = bbs_aug.bounding_boxes[i]\n","        voc_writer.addObject(boxes[i][0], int(bb_box.x1), int(bb_box.y1), int(bb_box.x2), int(bb_box.y2))\n","\n","    voc_writer.save(output_dir + 'dark_' + annotations[idx][1])\n","    print(output_dir + 'dark_' + annotations[idx][1])"],"execution_count":0,"outputs":[]}]}
\ No newline at end of file

+"""
+Usage:
+
+# Create train data:
+python generate_tfrecord.py --label=<LABEL> --csv_input=<PATH_TO_ANNOTATIONS_FOLDER>/train_labels.csv  --output_path=<PATH_TO_ANNOTATIONS_FOLDER>/train.record <PATH_TO_ANNOTATIONS_FOLDER>/label_map.pbtxt
+
+# Create test data:
+python generate_tfrecord.py --label=<LABEL> --csv_input=<PATH_TO_ANNOTATIONS_FOLDER>/test_labels.csv  --output_path=<PATH_TO_ANNOTATIONS_FOLDER>/test.record  --label_map <PATH_TO_ANNOTATIONS_FOLDER>/label_map.pbtxt
+"""
+
+from __future__ import division
+from __future__ import print_function
+from __future__ import absolute_import
+
+import os
+import io
+import pandas as pd
+import tensorflow as tf
+import sys
+
+sys.path.append("../../models/research")
+
+from PIL import Image
+from object_detection.utils import dataset_util
+from collections import namedtuple, OrderedDict
+
+flags = tf.app.flags
+flags.DEFINE_string("csv_input", "", "Path to the CSV input")
+flags.DEFINE_string("output_path", "", "Path to output TFRecord")
+flags.DEFINE_string(
+    "label_map",
+    "",
+    "Path to the `label_map.pbtxt` contains the <class_name>:<class_index> pairs generated by `xml_to_csv.py` or manually.",
+)
+# if your image has more labels input them as
+# flags.DEFINE_string('label0', '', 'Name of class[0] label')
+# flags.DEFINE_string('label1', '', 'Name of class[1] label')
+# and so on.
+flags.DEFINE_string("img_path", "", "Path to images")
+FLAGS = flags.FLAGS
+
+
+def split(df, group):
+    data = namedtuple("data", ["filename", "object"])
+    gb = df.groupby(group)
+    return [
+        data(filename, gb.get_group(x))
+        for filename, x in zip(gb.groups.keys(), gb.groups)
+    ]
+
+
+def create_tf_example(group, path, label_map):
+    with tf.gfile.GFile(os.path.join(path, "{}".format(group.filename)), "rb") as fid:
+        encoded_jpg = fid.read()
+    encoded_jpg_io = io.BytesIO(encoded_jpg)
+    image = Image.open(encoded_jpg_io)
+    width, height = image.size
+
+    filename = group.filename.encode("utf8")
+    image_format = b"jpg"
+    # check if the image format is matching with your images.
+    xmins = []
+    xmaxs = []
+    ymins = []
+    ymaxs = []
+    classes_text = []
+    classes = []
+
+    for index, row in group.object.iterrows():
+        xmins.append(row["xmin"] / width)
+        xmaxs.append(row["xmax"] / width)
+        ymins.append(row["ymin"] / height)
+        ymaxs.append(row["ymax"] / height)
+        classes_text.append(row["class"].encode("utf8"))
+        class_index = label_map.get(row["class"])
+        assert (
+            class_index is not None
+        ), "class label: `{}` not found in label_map: {}".format(
+            row["class"], label_map
+        )
+        classes.append(class_index)
+
+    tf_example = tf.train.Example(
+        features=tf.train.Features(
+            feature={
+                "image/height": dataset_util.int64_feature(height),
+                "image/width": dataset_util.int64_feature(width),
+                "image/filename": dataset_util.bytes_feature(filename),
+                "image/source_id": dataset_util.bytes_feature(filename),
+                "image/encoded": dataset_util.bytes_feature(encoded_jpg),
+                "image/format": dataset_util.bytes_feature(image_format),
+                "image/object/bbox/xmin": dataset_util.float_list_feature(xmins),
+                "image/object/bbox/xmax": dataset_util.float_list_feature(xmaxs),
+                "image/object/bbox/ymin": dataset_util.float_list_feature(ymins),
+                "image/object/bbox/ymax": dataset_util.float_list_feature(ymaxs),
+                "image/object/class/text": dataset_util.bytes_list_feature(
+                    classes_text
+                ),
+                "image/object/class/label": dataset_util.int64_list_feature(classes),
+            }
+        )
+    )
+    return tf_example
+
+
+def main(_):
+    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
+    path = os.path.join(os.getcwd(), FLAGS.img_path)
+    examples = pd.read_csv(FLAGS.csv_input)
+
+    # Load the `label_map` from pbtxt file.
+    from object_detection.utils import label_map_util
+
+    label_map = label_map_util.load_labelmap(FLAGS.label_map)
+    categories = label_map_util.convert_label_map_to_categories(
+        label_map, max_num_classes=90, use_display_name=True
+    )
+    category_index = label_map_util.create_category_index(categories)
+    label_map = {}
+    for k, v in category_index.items():
+        label_map[v.get("name")] = v.get("id")
+    grouped = split(examples, "filename")
+    for group in grouped:
+        tf_example = create_tf_example(group, path, label_map)
+        writer.write(tf_example.SerializeToString())
+
+    writer.close()
+    output_path = os.path.join(os.getcwd(), FLAGS.output_path)
+    print("Successfully created the TFRecords: {}".format(output_path))
+
+
+if __name__ == "__main__":
+    tf.app.run()

+"""
+Usage:
+# Create train data:
+python xml_to_csv.py -i [PATH_TO_IMAGES_FOLDER]/train -o [PATH_TO_ANNOTATIONS_FOLDER]/train_labels.csv
+
+# Create test data:
+python xml_to_csv.py -i [PATH_TO_IMAGES_FOLDER]/test -o [PATH_TO_ANNOTATIONS_FOLDER]/test_labels.csv
+"""
+
+import os
+import glob
+import pandas as pd
+import argparse
+import xml.etree.ElementTree as ET
+
+
+def xml_to_csv(path):
+    """Iterates through all .xml files (generated by labelImg) in a given directory and combines them in a single Pandas datagrame.
+
+    Parameters:
+    ----------
+    path : {str}
+        The path containing the .xml files
+    Returns
+    -------
+    Pandas DataFrame
+        The produced dataframe
+    """
+    classes_names = []
+    xml_list = []
+    for xml_file in glob.glob(path + "/*.xml"):
+        tree = ET.parse(xml_file)
+        root = tree.getroot()
+        for member in root.findall("object"):
+            classes_names.append(member[0].text)
+            value = (
+                root.find("filename").text,
+                int(root.find("size")[0].text),
+                int(root.find("size")[1].text),
+                member[0].text,
+                int(member[4][0].text),
+                int(member[4][1].text),
+                int(member[4][2].text),
+                int(member[4][3].text),
+            )
+            xml_list.append(value)
+    column_name = [
+        "filename",
+        "width",
+        "height",
+        "class",
+        "xmin",
+        "ymin",
+        "xmax",
+        "ymax",
+    ]
+    xml_df = pd.DataFrame(xml_list, columns=column_name)
+    classes_names = list(set(classes_names))
+    classes_names.sort()
+    return xml_df, classes_names
+
+
+def main():
+    # Initiate argument parser
+    parser = argparse.ArgumentParser(
+        description="Sample TensorFlow XML-to-CSV converter"
+    )
+    parser.add_argument(
+        "-i",
+        "--inputDir",
+        help="Path to the folder where the input .xml files are stored",
+        type=str,
+    )
+    parser.add_argument(
+        "-o", "--outputFile", help="Name of output .csv file (including path)", type=str
+    )
+
+    parser.add_argument(
+        "-l",
+        "--labelMapDir",
+        help="Directory path to save label_map.pbtxt file is specified.",
+        type=str,
+        default="",
+    )
+
+    args = parser.parse_args()
+
+    if args.inputDir is None:
+        args.inputDir = os.getcwd()
+    if args.outputFile is None:
+        args.outputFile = args.inputDir + "/labels.csv"
+
+    assert os.path.isdir(args.inputDir)
+    os.makedirs(os.path.dirname(args.outputFile), exist_ok=True)
+    xml_df, classes_names = xml_to_csv(args.inputDir)
+    xml_df.to_csv(args.outputFile, index=None)
+    print("Successfully converted xml to csv.")
+    if args.labelMapDir:
+        os.makedirs(args.labelMapDir, exist_ok=True)
+        label_map_path = os.path.join(args.labelMapDir, "label_map.pbtxt")
+        print("Generate `{}`".format(label_map_path))
+
+        # Create the `label_map.pbtxt` file
+        pbtxt_content = ""
+        for i, class_name in enumerate(classes_names):
+            pbtxt_content = (
+                pbtxt_content
+                + "item {{\n    id: {0}\n    name: '{1}'\n}}\n\n".format(
+                    i + 1, class_name
+                )
+            )
+        pbtxt_content = pbtxt_content.strip()
+        with open(label_map_path, "w") as f:
+            f.write(pbtxt_content)
+
+
+if __name__ == "__main__":
+    main()