在tensorflow对象检测api中使用ssd_mobilenet_v1_coco可以进行图像训练。
测试时得到错误：
File "/home/hipstudents/anaconda3/envs/tensorflow_gpuenv/lib/python3.6/site-packages/object_detection-0.1-py3.6.egg/object_detection/utils/object_detection_evaluation.py", line 203, in add_single_ground_truth_image_info
raise ValueError('Image with id {} already added.'.format(image_id))
请帮忙。
System Info:
What is the top-level directory of the model you are using: ~/
Have I written custom code (as opposed to using a stock example script provided in TensorFlow): Yes, written scripts to convert .xml files to tf record
OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 16.04
TensorFlow installed from (source or binary): Compiled from source
TensorFlow version (use command below): 1.11.0
Bazel version (if compiling from source): 0.16.1
CUDA/cuDNN version: 9.0.176, cuDNN: 9.0
GPU model and memory: GeForce GTX1080Ti, 11GB
Exact command to reproduce: python eval.py --logtostderr --pipeline_config_path=training/ssd_mobilenet_v1_coco.config --checkpoint_dir=training/ --eval_dir=eval/
我手动创建了数据集。然后使用labellimg进行标记。标记后，我创建了csv文件用于图像注释和文件名。然后我创建tf记录。我遵循本教程：https://towardsdatascience.com/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9
我的训练和测试图像的tfrecord生成器：
"""
Usage:
# From tensorflow/models/
# Create train data:
python generate_tfrecord.py --csv_input=data/train_labels.csv --output_path=train.record
# Create test data:
python generate_tfrecord.py --csv_input=data/test_labels.csv --output_path=test.record
"""
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
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 = flags.FLAGS
# TO-DO replace this with label map
def class_text_to_int(row_label):
if row_label == 'Field':
return 1
else:
None
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(FLAGS.output_path)
path = os.path.join(os.getcwd(), 'Images')
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()
在ssd_mobilenet_cocov1.config文件中，num_examples为8000。在我的例子中，测试数据集只有121个样本。我忘了更新它，得到了一个新的错误，我在互联网上找不到。因为这是一个愚蠢的错误，所以我认为很少有人这样做。这个答案可能会帮助那些会犯这种错误的人。我在配置文件中更改了以下内容，错误得到了解决：
eval_config: {
#num of test images. In my case 121. Previously It was 8000
num_examples: 121
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
在我的案例中，问题是在构建tfrecord文件时多次包含图像。虽然现在很明显，但我没有注意到开放图像数据集的许多类别共享相同的图像(在评估中会有相同的id，因此错误…(。一旦我纠正了创建tfrecords的算法，错误就消失了。
我已经解决了这篇文章的问题：https://www.coder.work/article/3120495
只需添加2行
eval_config {
num_examples: 50
use_moving_averages: false
metrics_set: "coco_detection_metrics"
}