-1
我在我自己的數據集上運行了一個快速測試ODA。我注意到它只能檢測一個類，就好像只有一個類一樣！爲什麼Tensorflow Object Detection API只檢測到第一個類，而忽略其餘的？
這裏是它檢測到正確的類的實例：
classes=[[ 1. 1. 2. 2. 1. 2. 1. 2. 1. 2. 2. 1. 2. 2. 2. 2. 2. 2.
2. 2. 2. 2. 1. 2. 1. 2. 1. 1. 2. 1. 2. 1. 2. 2. 2. 2.
1. 2. 2. 1. 2. 1. 1. 1. 2. 2. 2. 1. 1. 1. 2. 1. 1. 2.
2. 2. 1. 1. 2. 1. 2. 2. 1. 1. 1. 2. 1. 2. 2. 1. 2. 2.
2. 2. 1. 1. 1. 1. 2. 1. 2. 2. 1. 1. 2. 1. 2. 1. 2. 2.
1. 1. 2. 1. 1. 2. 2. 2. 1. 2.]]
這裏是一個例子，其中它不會做任何事情！：
並且這些打印在每張圖像下面的數字是classes變量的內容（下面給出的代碼）我打印的是否有任何其他類別被識別。
classes=[[ 1. 1. 2. 2. 1. 2. 1. 1. 1. 1. 2. 1. 2. 2. 2. 2. 2. 2.
2. 2. 2. 1. 2. 1. 1. 1. 1. 1. 1. 2. 2. 2. 1. 2. 1. 2.
2. 1. 2. 1. 2. 1. 2. 2. 2. 2. 1. 2. 1. 1. 1. 1. 2. 1.
2. 1. 2. 2. 1. 2. 1. 2. 2. 1. 2. 1. 1. 2. 1. 1. 2. 2.
2. 1. 1. 1. 2. 2. 1. 2. 1. 2. 2. 1. 1. 1. 2. 2. 2. 2.
1. 2. 2. 2. 2. 1. 1. 2. 1. 1.]]
這裏是它錯誤地檢測到的類（你可以再次看到它只能檢測類1）一個例子：
classes=[[ 1. 2. 2. 1. 1. 2. 1. 2. 2. 2. 2. 1. 1. 1. 1. 2. 1. 1.
2. 2. 2. 2. 2. 2. 1. 1. 2. 1. 2. 1. 1. 1. 1. 2. 1. 2.
2. 1. 1. 2. 1. 2. 1. 1. 1. 2. 1. 1. 2. 2. 1. 2. 1. 2.
2. 1. 1. 1. 1. 2. 1. 1. 1. 2. 2. 2. 2. 2. 2. 2. 1. 2.
2. 2. 1. 1. 2. 2. 1. 1. 2. 2. 2. 2. 2. 1. 2. 1. 1. 1.
2. 1. 1. 1. 1. 1. 1. 1. 2. 1.]]
所以基本上只繪製一個矩形僅限1級！而完全忽略類2.我使用的筆記本Jupyter示例中提供的代碼如下：
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# Definite input and output Tensors for detection_graph
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
for image_path in TEST_IMAGE_PATHS:
image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
image_np = load_image_into_numpy_array(image)
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
# Actual detection.
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=4,max_boxes_to_draw=50)
#print(scores)
plt.figure(figsize=(image_np.shape[1]/float(96), image_np.shape[0]/float(96)))#IMAGE_SIZE
plt.imshow(image_np)
#matplotlib.image.imsave(os.path.basename(image_path), image_np)
plt.show()
print(classes)
我甚至嘗試設置min_score_thresh=0.1但什麼都沒有改變！然後我嘗試max_boxes_to_draw，你可以看到，再次無濟於事。代碼方面的其他內容與this完全相同，除了它從互聯網上下載模型的部分，我註釋掉了它並閱讀了我自己的預訓練模型。
我是新來的對象檢測，並不知道是什麼導致此。
更新：
我的標記圖如下所示：
item{
id: 1
name: 'class1'
}
item{
id: 2
name: 'class2'
}
和我的數據集是由XML文件，如低於該使用下面我給的代碼片段轉換爲CSV 。註釋例如：
<annotation>
<folder>Imagenet_fldr</folder>
<filename>resized_imgnet_17.jpg</filename>
<path>G:\Tensorflow_section\dataset\Imagenet_fldr\resized_imgnet_17.jpg</path>
<source>
<database>arven</database>
</source>
<size>
<width>384</width>
<height>256</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>class1</name>
<pose>unknown</pose>
<truncated>1</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>2</xmin>
<ymin>2</ymin>
<xmax>380</xmax>
<ymax>252</ymax>
</bndbox>
</object>
</annotation>
，這裏是我用XML轉換爲CSV的片段：
import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
import sys
def xml_to_csv(path,directory):
xml_list = []
for xml_file in glob.glob(path + '/*.xml'):
#print(xml_file)
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall('object'):
value = (directory+'\\'+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 main():
for directory in os.listdir(sys.argv[1]):
image_path = sys.argv[1]+'\\'+directory
#print(image_path)
xml_df = xml_to_csv(image_path,directory)
xml_df.to_csv('{0}_labels.csv'.format(directory), index=None)
print('Successfully converted xml to csv.')
main()
最後我這是怎麼創建TFRecords：
"""
Usage:
# First specify the folder containing images!
# Create train data:
python xgenerate_tf_record.py --images_folder G:\\Tensorflow_section\\dtset\\ --csv_input=train_labels.csv --output_path=train.record
# Create test data:
python xgenerate_tf_record.py --images_folder G:\\Tensorflow_section\\dtset\\ --csv_input=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
from pathlib import Path
flags = tf.app.flags
flags.DEFINE_string('images_folder', '', 'Path to the directory containing images')
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 == 'class2':
return 0
if row_label == 'class1':
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_img = fid.read()
#print(group, path)
encoded_img_io = io.BytesIO(encoded_img)
image = Image.open(encoded_img_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():
ext = (Path(row['filename']).suffixes)[0].split(".")[1].lower()
#print('format = ',ext)
image_format = bytes(ext, encoding="utf8")
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_img),
'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(_):
#print('In the name of Allah')
writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
dataset_folders = FLAGS.images_folder #'G:\\Tensorflow_section\\dtset\\'
#print('dataset_folders = '+dataset_folders)
path = dataset_folders
examples = pd.read_csv(FLAGS.csv_input)
#print('examples: ',examples)
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()
你的標籤貼圖是怎樣的？你如何建立TFRecords？ – ITiger
@ITiger：我用所需的信息更新了問題。 – Breeze
現在我明白了，我想我在class_text_to_int（）方法中犯了一個錯誤！我應該寫2而不是0，看起來0完全忽略了這個類！我對嗎？ – Breeze