已解决****求助帖 本人用自己数据集训练Googlenet_inception_v3遇到如下问题。
不知如何是好,请问有大佬帮帮忙看看吗?报错信息以及涉错区域已提供。
报错信息如下
AttributeError: 'function' object has no attribute 'inception_v3_arg_scope'
根据学习别人的文章本人发现原理是 import那里出问题了,所以我把import那里添加/改成以下这句就解决报错了哦。
from slim.nets import inception_v3 as inception_v3
希望对各位有帮助
以下是我一开始遇到的报错信息的原文,给大家提供参考。
Tensorflow version:1.13.1
WARNING:tensorflow:From D:\ORANGE_I_CAN\the_first_retry\create_tf_record.py:27: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version.
Instructions for updating:
Use eager execution and:
`tf.data.TFRecordDataset(path)`
train nums:420,val nums:127
WARNING:tensorflow:From D:\ORANGE_I_CAN\the_first_retry\create_tf_record.py:138: string_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(string_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs