如何解决尝试生成 TFrecord 但我收到此错误“FileNotFoundError: [Errno 2] No such file or directory”
我正在点击此链接 https://colab.research.google.com/drive/11ko0DBnI1QLxVoJQR8gt9b4JDcvbCrtU#scrollTo=A_tyvKnBP6qD 来构建我的对象检测器。我正在使用 Google 协作。我的工作区结构与此链接中的完全相同。在这段代码之前,一切都很顺利:
from object_detection.utils import dataset_util
%cd /content/drive/MyDrive/Gun_Detection/models
data_base_url = '/content/drive/MyDrive/Gun_Detection/data'
image_dir = data_base_url + 'images/'
def class_text_to_int(row_label):
if row_label == 'pistol':
return 1
else:
None
def split(df,group):
data = namedtuple('data',['filename','object']) #we wanna group by
gb = df.groupby(group) #split data into group data by splitting,applying n combining
return [data(filename,gb.get_group(x))
for filename,x in zip(gb.groups.keys(),gb.groups)] #add group keys to index to identify pieces.
def create_tf_example(group,path):
with tf.io.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
for csv in ['train_labels','test_labels']:
writer = tf.io.TFRecordWriter(data_base_url + csv + '.record')
path = os.path.join(image_dir)
examples = pd.read_csv(data_base_url + csv + '.csv')
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(),data_base_url + csv + '.record')
print('Successfully created the TFRecords: {}'.format(data_base_url + csv + '.record'))
发生此错误后,datatrain_label.record 在我的驱动器中的 Gun Detection 文件夹中生成。我很困惑?我无法继续。请帮忙!
N.B:我不是 Python 专家,我还在学习。努力理解代码,但老实说我没有。
解决方法
提供 data_base_url 路径为 '/content/drive/MyDrive/Gun_Detection/data/'
你在它的末尾缺少一个 /
因为你的代码找不到 image_dir.
使用 os.path.join()
函数以避免这种情况。
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。