'''

"""
Usage:# From tensorflow/models/# Create train data:
python generate_TFR.py --csv_input=data/train.csv  --output_path=data/train.record# Create test data:
python generate_TFR.py --csv_input=data/test.csv  --output_path=data/test.record需要修改三处os.chdir('D:python3models-masterresearchobject_detection')path = os.path.join(os.getcwd(), 'images/train')def class_text_to_int(row_label): #对应的标签返回一个整数，后面会有文件用到if row_label == 'ZJL':return 1elif row_label == 'CYX':return 2else:None
"""import os
import io
import pandas as pd
import tensorflow as tffrom PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDictos.chdir('D:python3models-masterresearchobject_detection')flags = tf.app.flags
flags.DEFINE_string('csv_input', '', 'Path to the CSV input')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
FLAGS = flags.FLAGS# TO-DO replace this with label map
def class_text_to_int(row_label):if row_label == 'ZJL':return 1elif row_label == 'CYX':return 2else:Nonedef 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.sizefilename = 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_exampledef main(_):writer = tf.python_io.TFRecordWriter(FLAGS.output_path)path = os.path.join(os.getcwd(), 'images/test') #20180418做了修改examples = pd.read_csv(FLAGS.csv_input)grouped = split(examples, 'filename')for group in grouped:tf_example = create_tf_example(group, path)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()

# SSD with Mobilenet v1 configuration for MSCOCO Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.
'''
需修改5处
1、train_input_reader: {tf_record_input_reader {input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"}label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
}
这的input_path是训练数据的路径，改为对应的路径，这里是input_path:data/train.record
这的label_map_path是label路径，这里是label_map_path:data/ZJL_CYX.pbtxt
2、eval_input_reader: {tf_record_input_reader {input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"}label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"shuffle: falsenum_readers: 1
}
这的input_path是测试数据的路径，改为对应的路径，这里是input_path:data/test.record
这的label_map_path是label路径，这里是label_map_path:data/ZJL_CYX.pbtxt
3、ssd {num_classes: 90box_coder {faster_rcnn_box_coder {y_scale: 10.0x_scale: 10.0height_scale: 5.0width_scale: 5.0}}
num_classes是标签类别数，这里只有杰伦和奕迅，所以 num_classes: 2
4、train_config: {batch_size: 24optimizer {rms_prop_optimizer: {learning_rate: {exponential_decay_learning_rate {initial_learning_rate: 0.004decay_steps: 800720decay_factor: 0.95}}momentum_optimizer_value: 0.9decay: 0.9epsilon: 1.0}
}
batch_size是每次迭代的数据数，我这里设为1
5、fine_tune_checkpoint: "ssd_mobilenet_v1_coco_11_06_2017/model.ckpt"from_detection_checkpoint: true
这两行注释掉或者删除掉，否则会运行很慢
'''
model {ssd {num_classes: 90box_coder {faster_rcnn_box_coder {y_scale: 10.0x_scale: 10.0height_scale: 5.0width_scale: 5.0}}matcher {argmax_matcher {matched_threshold: 0.5unmatched_threshold: 0.5ignore_thresholds: falsenegatives_lower_than_unmatched: trueforce_match_for_each_row: true}}similarity_calculator {iou_similarity {}}anchor_generator {ssd_anchor_generator {num_layers: 6min_scale: 0.2max_scale: 0.95aspect_ratios: 1.0aspect_ratios: 2.0aspect_ratios: 0.5aspect_ratios: 3.0aspect_ratios: 0.3333}}image_resizer {fixed_shape_resizer {height: 300width: 300}}box_predictor {convolutional_box_predictor {min_depth: 0max_depth: 0num_layers_before_predictor: 0use_dropout: falsedropout_keep_probability: 0.8kernel_size: 1box_code_size: 4apply_sigmoid_to_scores: falseconv_hyperparams {activation: RELU_6,regularizer {l2_regularizer {weight: 0.00004}}initializer {truncated_normal_initializer {stddev: 0.03mean: 0.0}}batch_norm {train: true,scale: true,center: true,decay: 0.9997,epsilon: 0.001,}}}}feature_extractor {type: 'ssd_mobilenet_v1'min_depth: 16depth_multiplier: 1.0conv_hyperparams {activation: RELU_6,regularizer {l2_regularizer {weight: 0.00004}}initializer {truncated_normal_initializer {stddev: 0.03mean: 0.0}}batch_norm {train: true,scale: true,center: true,decay: 0.9997,epsilon: 0.001,}}}loss {classification_loss {weighted_sigmoid {}}localization_loss {weighted_smooth_l1 {}}hard_example_miner {num_hard_examples: 3000iou_threshold: 0.99loss_type: CLASSIFICATIONmax_negatives_per_positive: 3min_negatives_per_image: 0}classification_weight: 1.0localization_weight: 1.0}normalize_loss_by_num_matches: truepost_processing {batch_non_max_suppression {score_threshold: 1e-8iou_threshold: 0.6max_detections_per_class: 100max_total_detections: 100}score_converter: SIGMOID}}
}train_config: {batch_size: 24optimizer {rms_prop_optimizer: {learning_rate: {exponential_decay_learning_rate {initial_learning_rate: 0.004decay_steps: 800720decay_factor: 0.95}}momentum_optimizer_value: 0.9decay: 0.9epsilon: 1.0}}fine_tune_checkpoint: "PATH_TO_BE_CONFIGURED/model.ckpt"from_detection_checkpoint: true# Note: The below line limits the training process to 200K steps, which we# empirically found to be sufficient enough to train the pets dataset. This# effectively bypasses the learning rate schedule (the learning rate will# never decay). Remove the below line to train indefinitely.num_steps: 200000data_augmentation_options {random_horizontal_flip {}}data_augmentation_options {ssd_random_crop {}}
}train_input_reader: {tf_record_input_reader {input_path: "PATH_TO_BE_CONFIGURED/mscoco_train.record"}label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"
}eval_config: {num_examples: 8000# Note: The below line limits the evaluation process to 10 evaluations.# Remove the below line to evaluate indefinitely.max_evals: 10
}eval_input_reader: {tf_record_input_reader {input_path: "PATH_TO_BE_CONFIGURED/mscoco_val.record"}label_map_path: "PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt"shuffle: falsenum_readers: 1
}

'''