Tersorflow CIFAR-10 Training Example Error and its solution
1. Attributeerror: ' Module ' object has Noattribute ' Random_crop '
Solution:
Replace the distorted_image= tf.image.random_crop (reshaped_image, [height, width]) with the following:
Distorted_image = Tf.random_crop (Reshaped_image,[height, width,3])
2. Attributeerror: ' has ', ' summarywriter '
Solution:
Tf.train.SummaryWriter replaced by: Tf.summary.FileWriter
3. Attributeerror: ' has ', ' summaries '
Solution:
Tf.merge_all_summaries () Read: Summary_op =tf.summaries.merge_all ()
4. Attributeerror: ' Module ' object hasno attribute ' Histogram_summary '
Tf.histogram_summary (Var.op.name,var) read: Tf.summaries.histogram ()
5. Attributeerror: ' Module ' object hasno attribute ' Scalar_summary '
Tf.scalar_summary (l.op.name+ ' (raw) ', L)
Solution:
Tf.scalar_summary (' images ', images) instead: tf.summary.scalar (' images ', images)
Tf.image_summary (' images ', images) instead: tf.summary.image (' images ', images)
6. Valueerror:only call ' softmax_cross_entropy_with_logits ' withnamed arguments (labels= ..., logits= ...)
Solution:
Cifar10.loss (labels, logits) replaced by: Cifar10.loss (Logits=logits,labels=labels)
Cross_entropy= Tf.nn.softmax_cross_entropy_with_logits (
Logits, dense_labels,name= ' cross_entropy_per_example ')
To
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 ' isn't ' None: ' instead of ' if T: ' to test if a tensor isdefined, and use TensorFlow ops such as Tf.cond to Execut e subgraphsconditioned on the value of a tensor.
Solution:
If grad: Change to If grad not None:
8. Valueerror:shapes (2, 128, 1) and () are incompatible
Solution:
concated = Tf.concat (1, [Indices, Sparse_labels]) instead:
concated= Tf.concat ([Indices, Sparse_labels], 1)
9. Error:
File "/home/lily/work/tensorflow/cirfar-10/tensorflow.cifar10-master/cifar10_input.py", line and 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 '
Solution:
Because the path of the training sample needs to be modified, the Data_dir assigned to the cifar10_input.py is the folder where the local data resides
Other renaming of the TensorFlow API can be referenced
Http://www.codesec.net/view/504579.html
Continuous update ...