Traceback (most recent call last): File “cifar10_extract.py”, line 34, in <module> reshaped_image = inputs_origin(‘cifar10_data/cifar-10-batches-bin’) File “cifar10_extract.py”, line 23, in inputs_origin read_input = cifar10_input.read_cifar10(filename_queue) File “/home/pan/tfstudy/cifar10_input.py”, line 84, in read_cifar10 tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32) AttributeError: ‘module’ object has no attribute ‘strided_slice’
python train_image_classifier.py \
…: —train_dir=satellite/train_dir \
…: —dataset_name=satellite \
…: —dataset_split_name=train \
…: —dataset_dir=satellite/data \
…: —model_name=inception_v3 \
…: —checkpoint_path=satellite/pretrained/inception_v3.ckpt \
…: —checkpoint_exclude_scopes=InceptionV3/Logits,InceptionV3/AuxLogits \
…: —trainable_scopes=InceptionV3/Logits,InceptionV3/AuxLogits \
…: —max_number_of_steps=100000 \
…: —batch_size=32 \
…: —learning_rate_decay_type=fixed \
…: —s**e_interval_secs=300 \
…: —s**e_summaries_secs=2 \
…: —log_every_n_steps=10 \
…: —optimizer=rmsprop \
…: —weight_decay=0.0004 \
…: —clone_on_cpu=True
报错
File “<ipython-input-17-df2bf9e99e8a>“, line 1
python train_image_classifier.py —train_dir=satellite/train_dir —dataset_name=satellite —dataset_split_name=train —dataset_dir=satellite/data —model_name=inception_v3 —checkpoint_path=satellite/pretrained/inception_v3.ckpt —checkpoint_exclude_scopes=InceptionV3/Logits,InceptionV3/AuxLogits —trainable_scopes=InceptionV3/Logits,InceptionV3/AuxLogits —max_number_of_steps=100000 —batch_size=32 —learning_rate_decay_type=fixed —s**e_interval_secs=300 —s**e_summaries_secs=2 —log_every_n_steps=10 —optimizer=rmsprop —weight_decay=0.0004 —clone_on_cpu=True
请问作者，为什么我在用第三章的data_convert.py 代码时候，提示这个错误
第二章，训练模型时好像没有训练就出现错误了，但建立了cifar10_train文件夹和里面相应文件，恳请老师帮忙解答一下，win7系统py3.5环境。](http://download.broadview.com.cn/Original/180726c291e6db21b63b)
第三章，卫星数据与程序都准备好了，开始训练时，需要在命令行输入python train…后面要输入一大堆参数值，实在太多了，很容易出错，这个命令的文本有地方拷贝吗？
何老师，您好！
第二章，运行将CIFAR-10数据集保存为图片形式时，出现异常，我大概理解是input.py程序中的语句 tf.strided_slice 出现问题，但不知道如何修改。错误提示如下：
Traceback (most recent call last):
File “cifar10_extract.py”, line 34, in <module>
reshaped_image = inputs_origin(‘cifar10_data/cifar-10-batches-bin’)
File “cifar10_extract.py”, line 23, in inputs_origin
read_input = cifar10_input.read_cifar10(filename_queue)
File “/home/pan/tfstudy/cifar10_input.py”, line 84, in read_cifar10
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
AttributeError: ‘module’ object has no attribute ‘strided_slice’