estimator.predict 引发“ValueError: None values not supported"； [英] estimator.predict raises "ValueError: None values not supported"

问题描述

所以我基本上复制粘贴了适应这个模型的 tensorflow 教程中的代码:

So I basically copypasted the code from the tensorflow tutorial adapted to this model:

它试图对神经网络进行建模以识别楼梯"形状，如下所示:

Which tries to model a neural network to identify "stairs" shape, as it shows here:

_{(来源:gormanalysis.com)}

import numpy as np
import tensorflow as tf
import _pickle as cPickle

with open("var_x.txt", "rb") as fp:   # Unpickling
    var_x = cPickle.load(fp)

with open("var_y.txt", "rb") as fp:   # Unpickling
    var_y = cPickle.load(fp)

# Declare list of features, we only have one real-valued feature
def model_fn(features, labels, mode):

  # Build a linear model and predict values
  W = tf.get_variable("W", [4], dtype=tf.float64)
  b = tf.get_variable("b", [1], dtype=tf.float64)
  y = tf.sigmoid( W*features['x'] + b)
  # Loss sub-graph
  loss = tf.reduce_sum(tf.square(y - labels))
  # Training sub-graph
  global_step = tf.train.get_global_step()
  optimizer = tf.train.GradientDescentOptimizer(0.01)
  train = tf.group(optimizer.minimize(loss),
                   tf.assign_add(global_step, 1))
  # EstimatorSpec connects subgraphs we built to the
  # appropriate functionality.
  return tf.estimator.EstimatorSpec(
      mode=mode,
      predictions=y,
      loss=loss,
      train_op=train)

estimator = tf.estimator.Estimator(model_fn=model_fn)
# define our data sets
x_train = np.array(var_x)
y_train = np.array(var_y)

input_fn = tf.estimator.inputs.numpy_input_fn(
    {"x": x_train}, y_train, batch_size=4, num_epochs=10, shuffle=True)

# train
estimator.train(input_fn=input_fn, steps=1000)
# Here we evaluate how well our model did.

print(estimator.get_variable_value("b"))
print(estimator.get_variable_value("W"))

new_samples = np.array(
    [255., 1., 255., 255.], dtype=np.float64)
predict_input_fn = tf.estimator.inputs.numpy_input_fn(
    x={"x": new_samples},
    num_epochs=1,
    shuffle=False)

predictions = list(estimator.predict(input_fn=predict_input_fn))

print(predictions)

问题是，当我尝试预测一个显然应该是楼梯的图形时:[255., 1., 255., 255.] 我得到一个ValueError: None values not supported.".训练效果很好(除了它发现的权重与这里的权重不太相似的事实:http://blog.kaggle.com/2017/11/27/introduction-to-neural-networks/).但是预测方法不起作用.这段代码肯定只是 tensorflow 示例的副本，适用于 x 的四维向量.

The problem is that when I try to predict a figure that should clearly be a stairs: [255., 1., 255., 255.] I get a "ValueError: None values not supported.". The training works just fine (save for the facts that the weights it finds are not very similar to the ones here: http://blog.kaggle.com/2017/11/27/introduction-to-neural-networks/). But the predict method doesn't work. This code is mustly just a copy of the tensorflow example, adapted to a four dimensional vector for x.

推荐答案

在您的 model_fn 中，您定义了每种模式(train/eval/predict)中的 loss.这意味着即使在预测模式下，labels 也会被使用并且需要提供.

In your model_fn, you define the loss in every mode (train / eval / predict). This means that even in predict mode, the labels will be used and need to be provided.

当您处于预测模式时，您实际上只需要返回预测，以便您可以提前从函数中返回:

When you are in predict mode, you actually just need to return the predictions so you can return early from the function:

def model_fn(features, labels, mode):
    #...
    y = ...
    if mode == tf.estimator.ModeKeys.PREDICT:
        return tf.estimator.EstimatorSpec(mode=mode, predictions=y)
    #...

顺便说一下，W * features 返回一个形状为 (4,) 的张量，您需要在添加偏差之前对其求和.

By the way, W * features returns a tensor of shape (4,), you will need to sum it before adding the bias.

这篇关于estimator.predict 引发“ValueError: None values not supported"；的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！