Tersorflow深度學習入門—— CIFAR-10 訓練示例報錯及解決方案

前言：相關環境搭建

一：Tersorflow CIFAR-10 訓練示例報錯及解決方案（1）

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

##解決方案：

將distorted_image= tf.image.random_crop(reshaped_image,[height, width])改爲：

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

2. AttributeError:'module'object has no attribute 'SummaryWriter'

##解決方案：tf.train.SummaryWriter改爲：tf.summary.FileWriter

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

解決方案： tf.merge_all_summaries()改爲：summary_op =tf.summaries.merge_all()

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

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

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

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

##解決方案：

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

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

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

##解決方案：

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

cross_entropy=tf.nn.softmax_cross_entropy_with_logits(

logits,dense_labels,name='cross_entropy_per_example')

改爲：

cross_entropy =tf.nn.softmax_cross_entropy_with_logits(

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 tensorisdefined, and use TensorFlow ops such as tf.cond to execute subgraphsconditionedon the value of a tensor.

##解決方案：

if grad: 改爲 if grad is not None:

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

###解決方案：

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

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

9. 報錯：（這個暫時沒有遇到）

File"/home/lily/work/Tensorflow/CIRFAR-10/tensorflow.cifar10-master/cifar10_input.py",line83, in read_cifar10

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

File"/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/io_ops.py",line326, in read

queue_ref = queue.queue_ref

AttributeError: 'str' object hasno attribute 'queue_ref'

###解決方案：

由於訓練樣本的路徑需要修改，給cifar10_input.py中data_dir賦值爲本地數據所在的文件夾

以上參考自 http://blog.csdn.net/xiao_lxl/article/details/70622209

二：Tersorflow CIFAR-10 訓練示例報錯及解決方案（2）

1，File"tensorflow/models/slim/preprocessing/cifarnet_preproces.py", line70, in preprocess_for_train

return tf.image.per_image_whitening(distorted_image)
AttributeError: 'module' object has no attribute'per_image_whitening'

2，tensorflow:AttributeError: 'module' object has noattribute 'mul'

3，bin/im2txt/evaluate.runfiles/im2txt/im2txt/evaluate.py",line 174, in run summary_op = tf.merge_all_summaries() AttributeError: 'module'object has no attribute 'merge_all_summaries'

What can I do for this?