1. 程式人生 > >TensorFlow不同版本引起的錯誤

TensorFlow不同版本引起的錯誤

這幾天分別基於tensorflow0.11和1.0版本測試,記錄下兩個版本不同的API, 參考:http://blog.csdn.NET/edwards_june/article/details/65652385

前4個是 V0.11 的API 用在 V1.0 的錯誤 1. AttributeError: ‘module’ object has no attribute ‘merge_all_summaries’

tf.merge_all_summaries() 改為:summary_op=tf.summary.merge_all()

  1. AttributeError: ‘module’ object has no attribute ‘SummaryWriter’

    tf.train.SummaryWriter 改為:tf.summary.FileWriter

  2. AttributeError: ‘module’ object has no attribute ‘scalar_summary’

    tf.scalar_summary 改為:tf.summary.scalar

  3. AttributeError: ‘module’ object has no attribute ‘histogram_summary’

    histogram_summary 改為:tf.summary.histogram

下邊這個是 V1.0 的API 用在 V0.11 的錯誤 File “dis-alexnet_benchmark.py”, line 110, in alexnet_v2 biases_initializer=tf.zeros_initializer(), TypeError: zeros_initializer() takes at least 1 argument (0 given)

將 biases_initializer=tf.zeros_initializer() 改為:biases_initializer=tf.zeros_initializer