关于TensorFlow新旧版本函数接口变化详解
TensorFlow版本更新太快 了,所以导致一些以前接口函数不一致,会报错。
这里总结了一下自己犯的错,以防以后再碰到,也可以给别人参考。
首先我的cifar10的代码都是找到当前最新的tf官网给的,所以后面还有新的tf出来改动了的话,可能又会失效了。
1.python3:(unicode error) 'utf-8' codec can't decode
刚开始执行的时候就报这个错,很郁闷后来发现是因为我用多个编辑器编写,
保存。导致不同编辑器编码解码不一致,会报错。所以唯一的办法全程用
一个编辑器去写,保存。或者保证都是用一种方式编码解码就OK了
一:Tersorflow CIFAR-10 训练示例报错及解决方案(1) 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(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:(这个暂时没有遇到) 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
二:Tersorflow CIFAR-10 训练示例报错及解决方案
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'
以上这篇关于TensorFlow新旧版本函数接口变化详解就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持我们。
赞 (0)