tensorflow 训练cifar10报错

1、AttributeError: 'module' object has noattribute 'random_crop'

解决方案：

将distorted_image= tf.image.random_crop(reshaped_image, [height, width])改为：

distorted_image = tf.random_crop(reshaped_image,[height, width,3])

2、AttributeError: ‘module’ object has no attribute’per_image_whitening’
‘per_image_whitening 改为：’per_image_standardization

3、'module' object has no attribute 'image_summary' ---->Please switch to tf.summary.image

4、AttributeError: 'module' object has no attribute 'histogram_summary'

AttributeError: 'module' object has no attribute 'histogram_summary'

>> histogram_summary 改为：tf.summary.histogram

5、AttributeError: 'module' object has no attribute 'scalar_summary'

AttributeError: 'module' object has no attribute 'scalar_summary'

>> tf.scalar_summary 改为：tf.summary.scalar

6、AttributeError: 'module' object has no attribute 'mul'

 

According to the tensorflow 1.0.0 release notes,

 

tf.mul, tf.sub and tf.neg are deprecated in favor of tf.multiply, tf.subtract and tf.negative.

 

7、raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (2, 128, 1) and () are incompatible