尝试计算 Tensorflow 线性回归模型的 R 平方时出错

Question

我有一个使用 Tensorflow 编写的简单单变量线性回归模型。

我正在尝试计算此模型的决定系数（R 平方）。

我将R_squared 声明为tf.Variable（我也尝试将其声明为占位符，并将其声明为普通的python 变量）。

R_squared = tf.variable(0,name = 'R_squared')
prediction = tf.add(tf.multiply(X,W),b)
training_cost = tf.reduce_sum(tf.pow(prediction-Y,2))/(2 * n_samples)
unexplained_cost = tf.reduce_sum(tf.square(tf.subtract(Y,prediction)))
R_squared =  tf.subtract(1.0, tf.divide(unexplained_cost, training_cost))

稍后在运行优化器后的代码中，我尝试打印出来 R_squared。

print ('R squared = ', tf_session.run(R_squared))

但我总是遇到同样的错误：

Traceback (most recent call last):
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1327, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1306, in _run_fn
    status, run_metadata)
  File "/usr/lib/python3.4/contextlib.py", line 66, in __exit__
    next(self.gen)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder' with dtype float
     [[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=<unknown>, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "./linear_regression.py", line 126, in <module>
    print ('R squared = ', tf_session.run(R_squared))
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 895, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1124, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1321, in _do_run
    options, run_metadata)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1340, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder' with dtype float
     [[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=<unknown>, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Caused by op 'Placeholder', defined at:
  File "./linear_regression.py", line 78, in <module>
    X = tf.placeholder('float')
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/ops/array_ops.py", line 1548, in placeholder
    return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2094, in _placeholder
    name=name)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 1204, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder' with dtype float
     [[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=<unknown>, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

我也尝试打印出R_squared.eval()，但我仍然遇到同样的错误。

另外，在张量对象上调用eval 方法与将其传递给会话run 方法有什么区别？

任何帮助表示赞赏。

Answer 1

我强烈建议不要使用配方来计算这个！我发现的例子并没有产生一致的结果，尤其是只有一个目标变量。这让我非常头疼！

正确的做法是使用tensorflow_addons.metrics.RQsquare()。 Tensorflow Add Ons 是 on PyPi here，文档是 part of Tensorflow here。您所要做的就是将y_shape 设置为输出的形状，通常是(1,) 用于单个输出变量。

Answer 2

您已将 X 定义为代码中某处的占位符。占位符通常为空，除非您为其分配默认值或使用 feed_dict 为其提供值。

例如，尝试使用：

tf_session.run(R_squared, feed_dict={X: 1})

您显然可以将 1 替换为您想要的任何其他值 - 您也可以使用任何 Python 变量。

关于 eval 和 run 的区别，见this question。