我在 github 的 python 中使用来自 tensorflow 的官方代码,但我没有通过该错误:
import tensorflow as tf
import cv2
cap = cv2.VideoCapture(1)
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
# ## Object detection imports
# Here are the imports from the object detection module.
# In[3]:
from object_detection.utils import label_map_util
File "C:/Users/azach/Desktop/python/tensorflow/models-
master/research/object_detection/utils/label_map_util.py", line 22, in
<module>
from object_detection.protos import string_int_label_map_pb2
ModuleNotFoundError: No module named 'object_detection'
正如有人在这里建议的那样:
Tensorflow:没有属性“load_labelmap”
我变了
from object_detection.protos import string_int_label_map_pb2
对此:
from protos import string_int_label_map_pb2
我在 Windows 10 上使用 Python 3.6.5、tensorflow 1.8。 *.proto 文件是用 protoc 3.4 编译的。
编辑:来自cmd的错误:
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
NameError: name 'label_map_util' is not defined
>>> categories = label_map_util.convert_label_map_to_categories(label_map,
max_num_classes=NUM_CLASSES, use_display_name=True)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
NameError: name 'label_map_util' is not defined
>>> category_index = label_map_util.create_category_index(categories)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
NameError: name 'label_map_util' is not defined