AttributeError: module 'tensorflow_core.compat.v1' has no attribute 'contrib'

Question

x = tf.placeholder(dtype = tf.float32, shape = [None, 28, 28])
y = tf.placeholder(dtype = tf.int32, shape = [None])
images_flat = tf.contrib.layers.flatten(x)
logits = tf.contrib.layers.fully_connected(images_flat, 62, tf.nn.relu)
loss = 
tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits( 
   labels = y, logits = logits))
   train_op = 
   tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
   correct_pred = tf.argmax(logits, 1)
   accuracy = tf.reduce_mean(tf.cast(correct_pred, 
   tf.float32))

   print("images_flat: ", images_flat)
   print("logits: ", logits)
   print("loss: ", loss)
   print("predicted_labels: ", correct_pred)


AttributeError                            Traceback (most recent call last)
<ipython-input-17-183722ce66a3> in <module>
      1 x = tf.placeholder(dtype = tf.float32, shape = [None, 28, 28])
      2 y = tf.placeholder(dtype = tf.int32, shape = [None])
----> 3 images_flat = tf.contrib.layers.flatten(x)
      4 logits = tf.contrib.layers.fully_connected(images_flat, 62, tf.nn.relu)
      5 loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels = y, logits = logits))

AttributeError: module 'tensorflow_core.compat.v1' has no attribute 'contrib'

2.This 是我在 Jupyter Notebook 中的代码。我刚从 python 开始，得到了我在标题中提到的错误。如果有人可以帮助我提供代码示例来解决问题，我将不胜感激。

Answer 1

tf.contrib 在 TensorFlow 2.0 alpha 版本中被从 TensorFlow 中删除了一次。

您很可能已经在使用 TensorFlow 2.0。

您可以在此处找到更多详细信息：https://github.com/tensorflow/tensorflow/releases/tag/v2.0.0-alpha0

要使用特定版本的tensorflow，请使用

pip install tensorflow==1.14

或

pip install tensorflow-gpu==1.14

Answer 2

我认为您需要在要执行的 python 文件中添加以下行。

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

Answer 3

contrib 是 Google 团队头疼的问题。我们必须逐案处理 contrib 的问题。下面我只举两个例子。

1.With关于CNN，有如下方法

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

# -initializer = tf.contrib.layers.xavier_initializer(seed=1)
initializer = tf.truncated_normal_initializer(stddev=0.1)

2.With相对于RNN/LSTM，有以下不同的方法。

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

# -outputs, states = tf.contrib.rnn.static_rnn(lstm_cells, _X, dtype=tf.float32)
outputs, states = tf.compat.v1.nn.static_rnn(lstm_cells, _X, dtype=tf.float32)

AttributeError: module 'tensorflow_core.compat.v1' has no attribute 'contrib'

AttributeError: module 'tensorflow_core.compat.v1' has no attribute 'contrib'

python

jupyter

tensorflow

tensorflow2.0