我正在尝试在tensorflow中创建自己的Estimator函数，而不是使用DNNRegression函数来无法更改超参数。我正在关注这个tensorflow.org教程：
https://www.tensorflow.org/extend/estimators
我也从tensorflow.org页面获得了数据。这是我的代码，带有相应的错误。
非常感谢你的帮助！
`from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import itertools
import pandas as pd
import tensorflow as tf
import numpy as np
from tensorflow.contrib.learn.python.learn.estimators import model_fn as model_fn_lib`
COLUMNS = ["crim", "zn", "indus", "nox", "rm", "age",
"dis", "tax", "ptratio", "medv"]
FEATURES = ["crim", "zn", "indus", "nox", "rm",
"age", "dis", "tax", "ptratio"]
LABEL = "medv"
training_set = pd.read_csv("boston_train.csv",skipinitialspace=True,skiprows=1,names=COLUMNS)
test_set =pd.read_csv("boston_test.csv",skipinitialspace=True,skiprows=1,names=COLUMNS)
prediction_set = pd.read_csv("boston_predict.csv",skipinitialspace=True,skiprows=1,names=COLUMNS)
x_training_set = training_set.ix[:,0:9]
x_training_set2 = x_training_set.values
y_training_set = training_set.ix[:,9]
y_training_set2 = y_training_set.values
# Set model params
model_params = {"learning_rate": LEARNING_RATE}
# Instantiate Estimator
nn = tf.contrib.learn.Estimator(model_fn=model_fn, params=model_params)
def model_fn(features, targets, mode, params):
h_1 = tf.nn.relu(features,10)
h_2 = tf.nn.relu(h_1, 10)
output_layer = tf.contrib.layers.fully_connected((h_2, 1), activation_fn=None)
predictions_dict = {"pred": output_layer}
# Calculate loss using mean squared error
loss = tf.metrics.root_mean_squared_error(tf.cast(targets, tf.float32), predictions)
# Calculate root mean squared error as additional eval metric
eval_metric_ops = {"rmse":tf.metrics.root_mean_squared_error(tf.cast(targets, tf.float32), predictions)}
train_op = tf.contrib.layers.optimize_loss(loss=loss, global_step=tf.contrib.framework.get_global_step(),learning_rate=params["learning_rate"],optimizer="SGD")
return model_fn_lib.ModelFnOps(mode=mode,predictions=predictions_dict,loss=loss,train_op=train_op,eval_metric_ops=eval_metric_ops)
nn.fit(x=x_training_set2, y=y_training_set2,input_fn=None, steps=200)
当我运行最后一行时出现错误，如下所示：
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\python\util\deprecation.py:247: FutureWarning: comparison to `None` will result in an elementwise object comparison in the future.
equality = a == b
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-91-8d36dcccfcd6> in <module>()
----> 1 nn.fit(x=x_training_set2, y=y_training_set2,input_fn=None, steps=200)
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
278 _call_location(), decorator_utils.get_qualified_name(func),
279 func.__module__, arg_name, date, instructions)
--> 280 return func(*args, **kwargs)
281 new_func.__doc__ = _add_deprecated_arg_notice_to_docstring(
282 func.__doc__, date, instructions)
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in fit(self, x, y, input_fn, steps, batch_size, monitors, max_steps)
408 _verify_input_args(x, y, input_fn, None, batch_size)
409 if x is not None:
--> 410 SKCompat(self).fit(x, y, batch_size, steps, max_steps, monitors)
411 return self
412
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in fit(self, x, y, batch_size, steps, max_steps, monitors)
1351 steps=steps,
1352 max_steps=max_steps,
-> 1353 monitors=all_monitors)
1354 return self
1355
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
278 _call_location(), decorator_utils.get_qualified_name(func),
279 func.__module__, arg_name, date, instructions)
--> 280 return func(*args, **kwargs)
281 new_func.__doc__ = _add_deprecated_arg_notice_to_docstring(
282 func.__doc__, date, instructions)
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in fit(self, x, y, input_fn, steps, batch_size, monitors, max_steps)
424 hooks.append(basic_session_run_hooks.StopAtStepHook(steps, max_steps))
425
--> 426 loss = self._train_model(input_fn=input_fn, hooks=hooks)
427 logging.info('Loss for final step: %s.', loss)
428 return self
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in _train_model(self, input_fn, hooks)
932 features, labels = input_fn()
933 self._check_inputs(features, labels)
--> 934 model_fn_ops = self._call_legacy_get_train_ops(features, labels)
935 ops.add_to_collection(ops.GraphKeys.LOSSES, model_fn_ops.loss)
936 all_hooks.extend([
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in _call_legacy_get_train_ops(self, features, labels)
1001
1002 def _call_legacy_get_train_ops(self, features, labels):
-> 1003 train_ops = self._get_train_ops(features, labels)
1004 if isinstance(train_ops, model_fn_lib.ModelFnOps): # Default signature
1005 return train_ops
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in _get_train_ops(self, features, labels)
1160 `ModelFnOps` object.
1161 """
-> 1162 return self._call_model_fn(features, labels, model_fn_lib.ModeKeys.TRAIN)
1163
1164 def _get_eval_ops(self, features, labels, metrics):
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in _call_model_fn(self, features, labels, mode)
1131 if 'model_dir' in model_fn_args:
1132 kwargs['model_dir'] = self.model_dir
-> 1133 model_fn_results = self._model_fn(features, labels, **kwargs)
1134
1135 if isinstance(model_fn_results, model_fn_lib.ModelFnOps):
<ipython-input-74-fb3e83994074> in model_fn(features, targets, mode, params)
1 def model_fn(features, targets, mode, params):
2
----> 3 h_1 = tf.nn.relu(features,10)
4 h_2 = tf.nn.relu(h_1, 10)
5 output_layer = tf.contrib.layers.fully_connected((h_2, 1), activation_fn=None)
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py in relu(features, name)
2148 A `Tensor`. Has the same type as `features`.
2149 """
-> 2150 result = _op_def_lib.apply_op("Relu", features=features, name=name)
2151 return result
2152
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py in apply_op(self, op_type_name, name, **keywords)
373 inputs = []
374 input_types = []
--> 375 with g.as_default(), ops.name_scope(name) as scope:
376
377 # Perform input type inference
C:\Users\pinouche\Anaconda3\lib\contextlib.py in __enter__(self)
57 def __enter__(self):
58 try:
---> 59 return next(self.gen)
60 except StopIteration:
61 raise RuntimeError("generator didn't yield") from None
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py in name_scope(name, default_name, values)
4218 values = []
4219 g = _get_graph_from_inputs(values)
-> 4220 with g.as_default(), g.name_scope(n) as scope:
4221 yield scope
4222 # pylint: enable=g-doc-return-or-yield
C:\Users\pinouche\Anaconda3\lib\contextlib.py in __enter__(self)
57 def __enter__(self):
58 try:
---> 59 return next(self.gen)
60 except StopIteration:
61 raise RuntimeError("generator didn't yield") from None
C:\Users\pinouche\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py in name_scope(self, name)
2905 # Scopes created in the root must match the more restrictive
2906 # op name regex, which constrains the initial character.
-> 2907 if not _VALID_OP_NAME_REGEX.match(name):
2908 raise ValueError("'%s' is not a valid scope name" % name)
2909 try:
TypeError: expected string or bytes-like object