Merge RealTimeObjectDetection1 into vendor/RealTimeObjetDetection1/

Author: westbenj2020

vendor/RealTimeObjectDetection1/Tensorflow/scripts/generate_tfrecord.py

@@ -0,0 +1,168 @@
+""" Sample TensorFlow XML-to-TFRecord converter
+
+usage: generate_tfrecord.py [-h] [-x XML_DIR] [-l LABELS_PATH] [-o OUTPUT_PATH] [-i IMAGE_DIR] [-c CSV_PATH]
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -x XML_DIR, --xml_dir XML_DIR
+                        Path to the folder where the input .xml files are stored.
+  -l LABELS_PATH, --labels_path LABELS_PATH
+                        Path to the labels (.pbtxt) file.
+  -o OUTPUT_PATH, --output_path OUTPUT_PATH
+                        Path of output TFRecord (.record) file.
+  -i IMAGE_DIR, --image_dir IMAGE_DIR
+                        Path to the folder where the input image files are stored. Defaults to the same directory as XML_DIR.
+  -c CSV_PATH, --csv_path CSV_PATH
+                        Path of output .csv file. If none provided, then no file will be written.
+"""
+
+import os
+import glob
+import pandas as pd
+import io
+import xml.etree.ElementTree as ET
+import argparse
+
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'    # Suppress TensorFlow logging (1)
+import tensorflow.compat.v1 as tf
+from PIL import Image
+from object_detection.utils import dataset_util, label_map_util
+from collections import namedtuple
+
+# Initiate argument parser
+parser = argparse.ArgumentParser(
+    description="Sample TensorFlow XML-to-TFRecord converter")
+parser.add_argument("-x",
+                    "--xml_dir",
+                    help="Path to the folder where the input .xml files are stored.",
+                    type=str)
+parser.add_argument("-l",
+                    "--labels_path",
+                    help="Path to the labels (.pbtxt) file.", type=str)
+parser.add_argument("-o",
+                    "--output_path",
+                    help="Path of output TFRecord (.record) file.", type=str)
+parser.add_argument("-i",
+                    "--image_dir",
+                    help="Path to the folder where the input image files are stored. "
+                         "Defaults to the same directory as XML_DIR.",
+                    type=str, default=None)
+parser.add_argument("-c",
+                    "--csv_path",
+                    help="Path of output .csv file. If none provided, then no file will be "
+                         "written.",
+                    type=str, default=None)
+
+args = parser.parse_args()
+
+if args.image_dir is None:
+    args.image_dir = args.xml_dir
+
+label_map = label_map_util.load_labelmap(args.labels_path)
+label_map_dict = label_map_util.get_label_map_dict(label_map)
+
+
+def xml_to_csv(path):
+    """Iterates through all .xml files (generated by labelImg) in a given directory and combines
+    them in a single Pandas dataframe.
+
+    Parameters:
+    ----------
+    path : str
+        The path containing the .xml files
+    Returns
+    -------
+    Pandas DataFrame
+        The produced dataframe
+    """
+
+    xml_list = []
+    for xml_file in glob.glob(path + '/*.xml'):
+        tree = ET.parse(xml_file)
+        root = tree.getroot()
+        for member in root.findall('object'):
+            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)
+    return xml_df
+
+
+def class_text_to_int(row_label):
+    return label_map_dict[row_label]
+
+
+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):
+    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'
+    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'))
+        classes.append(class_text_to_int(row['class']))
+
+    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(args.output_path)
+    path = os.path.join(args.image_dir)
+    examples = xml_to_csv(args.xml_dir)
+    grouped = split(examples, 'filename')
+    for group in grouped:
+        tf_example = create_tf_example(group, path)
+        writer.write(tf_example.SerializeToString())
+    writer.close()
+    print('Successfully created the TFRecord file: {}'.format(args.output_path))
+    if args.csv_path is not None:
+        examples.to_csv(args.csv_path, index=None)
+        print('Successfully created the CSV file: {}'.format(args.csv_path))
+
+
+if __name__ == '__main__':
+    tf.app.run()

vendor/RealTimeObjectDetection1/Tensorflow/workspace/annotations/.gitkeep

@@ -0,0 +1,4 @@
+model_checkpoint_path: "ckpt-0"
+all_model_checkpoint_paths: "ckpt-0"
+all_model_checkpoint_timestamps: 1594332511.5251744
+last_preserved_timestamp: 1594332507.0004687

vendor/RealTimeObjectDetection1/Tensorflow/workspace/images/test/.gitkeep

@@ -0,0 +1,191 @@
+model {
+  ssd {
+    num_classes: 90
+    image_resizer {
+      fixed_shape_resizer {
+        height: 320
+        width: 320
+      }
+    }
+    feature_extractor {
+      type: "ssd_mobilenet_v2_fpn_keras"
+      depth_multiplier: 1.0
+      min_depth: 16
+      conv_hyperparams {
+        regularizer {
+          l2_regularizer {
+            weight: 3.9999998989515007e-05
+          }
+        }
+        initializer {
+          random_normal_initializer {
+            mean: 0.0
+            stddev: 0.009999999776482582
+          }
+        }
+        activation: RELU_6
+        batch_norm {
+          decay: 0.996999979019165
+          scale: true
+          epsilon: 0.0010000000474974513
+        }
+      }
+      use_depthwise: true
+      override_base_feature_extractor_hyperparams: true
+      fpn {
+        min_level: 3
+        max_level: 7
+        additional_layer_depth: 128
+      }
+    }
+    box_coder {
+      faster_rcnn_box_coder {
+        y_scale: 10.0
+        x_scale: 10.0
+        height_scale: 5.0
+        width_scale: 5.0
+      }
+    }
+    matcher {
+      argmax_matcher {
+        matched_threshold: 0.5
+        unmatched_threshold: 0.5
+        ignore_thresholds: false
+        negatives_lower_than_unmatched: true
+        force_match_for_each_row: true
+        use_matmul_gather: true
+      }
+    }
+    similarity_calculator {
+      iou_similarity {
+      }
+    }
+    box_predictor {
+      weight_shared_convolutional_box_predictor {
+        conv_hyperparams {
+          regularizer {
+            l2_regularizer {
+              weight: 3.9999998989515007e-05
+            }
+          }
+          initializer {
+            random_normal_initializer {
+              mean: 0.0
+              stddev: 0.009999999776482582
+            }
+          }
+          activation: RELU_6
+          batch_norm {
+            decay: 0.996999979019165
+            scale: true
+            epsilon: 0.0010000000474974513
+          }
+        }
+        depth: 128
+        num_layers_before_predictor: 4
+        kernel_size: 3
+        class_prediction_bias_init: -4.599999904632568
+        share_prediction_tower: true
+        use_depthwise: true
+      }
+    }
+    anchor_generator {
+      multiscale_anchor_generator {
+        min_level: 3
+        max_level: 7
+        anchor_scale: 4.0
+        aspect_ratios: 1.0
+        aspect_ratios: 2.0
+        aspect_ratios: 0.5
+        scales_per_octave: 2
+      }
+    }
+    post_processing {
+      batch_non_max_suppression {
+        score_threshold: 9.99999993922529e-09
+        iou_threshold: 0.6000000238418579
+        max_detections_per_class: 100
+        max_total_detections: 100
+        use_static_shapes: false
+      }
+      score_converter: SIGMOID
+    }
+    normalize_loss_by_num_matches: true
+    loss {
+      localization_loss {
+        weighted_smooth_l1 {
+        }
+      }
+      classification_loss {
+        weighted_sigmoid_focal {
+          gamma: 2.0
+          alpha: 0.25
+        }
+      }
+      classification_weight: 1.0
+      localization_weight: 1.0
+    }
+    encode_background_as_zeros: true
+    normalize_loc_loss_by_codesize: true
+    inplace_batchnorm_update: true
+    freeze_batchnorm: false
+  }
+}
+train_config {
+  batch_size: 128
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+  data_augmentation_options {
+    random_crop_image {
+      min_object_covered: 0.0
+      min_aspect_ratio: 0.75
+      max_aspect_ratio: 3.0
+      min_area: 0.75
+      max_area: 1.0
+      overlap_thresh: 0.0
+    }
+  }
+  sync_replicas: true
+  optimizer {
+    momentum_optimizer {
+      learning_rate {
+        cosine_decay_learning_rate {
+          learning_rate_base: 0.07999999821186066
+          total_steps: 50000
+          warmup_learning_rate: 0.026666000485420227
+          warmup_steps: 1000
+        }
+      }
+      momentum_optimizer_value: 0.8999999761581421
+    }
+    use_moving_average: false
+  }
+  fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED"
+  num_steps: 50000
+  startup_delay_steps: 0.0
+  replicas_to_aggregate: 8
+  max_number_of_boxes: 100
+  unpad_groundtruth_tensors: false
+  fine_tune_checkpoint_type: "classification"
+  fine_tune_checkpoint_version: V2
+}
+train_input_reader {
+  label_map_path: "PATH_TO_BE_CONFIGURED"
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED"
+  }
+}
+eval_config {
+  metrics_set: "coco_detection_metrics"
+  use_moving_averages: false
+}
+eval_input_reader {
+  label_map_path: "PATH_TO_BE_CONFIGURED"
+  shuffle: false
+  num_epochs: 1
+  tf_record_input_reader {
+    input_path: "PATH_TO_BE_CONFIGURED"
+  }
+}