TensorFlow 跑网上的cifar10 需要修改才能正常运行

Tersorflow  CIFAR-10 训练示例报错及解决方案

参考网址

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 'SummaryWriter'

解决方案：

tf.train.SummaryWriter改为：tf.summary.FileWriter

 

3.  AttributeError: 'module'object has no attribute 'summaries'

解决方案：

 tf.merge_all_summaries()改为：summary_op =tf.summaries.merge_all()

 

4. AttributeError: 'module' object hasno attribute 'histogram_summary'

tf.histogram_summary(var.op.name,var)改为：  tf.summaries.histogram()

 

5. AttributeError: 'module' object hasno attribute 'scalar_summary'

tf.scalar_summary(l.op.name+ ' (raw)', l)

解决方案：

tf.scalar_summary('images',images)改为：tf.summary.scalar('images', images)

tf.image_summary('images',images)改为：tf.summary.image('images', images)

 

6. ValueError: Only call `softmax_cross_entropy_with_logits` withnamed arguments (labels=..., logits=..., ...)

解决方案：

   cifar10.loss(labels, logits) 改为：cifar10.loss(logits=logits,labels=labels)

 cross_entropy= tf.nn.softmax_cross_entropy_with_logits(
        logits, dense_labels,name='cross_entropy_per_example')

改为：

  cross_entropy = tf.nn.softmax_cross_entropy_with_logits_v2(
        logits=logits, labels=dense_labels,name='cross_entropy_per_example')

 

7. TypeError: Using a `tf.Tensor` as a Python `bool` isnot allowed. Use `if t is not None:` instead of `if t:` to test if a tensor isdefined, and use TensorFlow ops such as tf.cond to execute subgraphsconditioned on the value of a tensor.

解决方案：

if grad: 改为  if grad is not None:

 

8. ValueError: Shapes (2, 128, 1) and () are incompatible

解决方案：

concated = tf.concat(1, [indices, sparse_labels])改为：

concated= tf.concat([indices, sparse_labels], 1)

 

9. 报错：

File"/home/lily/work/Tensorflow/CIRFAR-10/tensorflow.cifar10-master/cifar10_input.py",line 83, in read_cifar10

    result.key, value =reader.read(filename_queue)

  File"/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/io_ops.py",line 326, in read

queue_ref = queue.queue_ref

AttributeError: 'str' object hasno attribute 'queue_ref'

10.cifar10_train.py   90行左右

tf.all_initializer()

 改为

tf.global_variables_initializer()

解决方案：

由于训练样本的路径需要修改，给cifar10_input.py中data_dir赋值为本地数据所在的文件夹