Merge branch 'master' of https://github.com/dctian/DeepPiCar

models/object_detection/code/generate_tfrecord.py

@@ -0,0 +1,134 @@
+"""
+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"png"
+    # 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()

models/object_detection/code/xml_to_csv.py

@@ -0,0 +1,118 @@
+"""
+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()

models/object_detection/data/images/test/car_video_3_100.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>train</folder>
+	<filename>car_video_3_100.png</filename>
+	<path>D:\temp\train\car_video_3_100.png</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>320</width>
+		<height>240</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Speed Limit 25</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>116</xmin>
+			<ymin>73</ymin>
+			<xmax>129</xmax>
+			<ymax>86</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>Stop Sign</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>19</xmin>
+			<ymin>82</ymin>
+			<xmax>32</xmax>
+			<ymax>95</ymax>
+		</bndbox>
+	</object>
+</annotation>

models/object_detection/data/images/test/car_video_4_002.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>train</folder>
+	<filename>car_video_4_002.png</filename>
+	<path>D:\temp\train\car_video_4_002.png</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>320</width>
+		<height>240</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Red Traffic Light</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>56</xmin>
+			<ymin>77</ymin>
+			<xmax>75</xmax>
+			<ymax>94</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>Red Traffic Light</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>210</xmin>
+			<ymin>78</ymin>
+			<xmax>220</xmax>
+			<ymax>100</ymax>
+		</bndbox>
+	</object>
+</annotation>

models/object_detection/data/images/test/car_video_4_273.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>train</folder>
+	<filename>car_video_4_273.png</filename>
+	<path>D:\temp\train\car_video_4_273.png</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>320</width>
+		<height>240</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Speed Limit 40</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>150</xmin>
+			<ymin>74</ymin>
+			<xmax>163</xmax>
+			<ymax>89</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>Stop Sign</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>271</xmin>
+			<ymin>88</ymin>
+			<xmax>280</xmax>
+			<ymax>100</ymax>
+		</bndbox>
+	</object>
+</annotation>