我收到了这个错误：
UnimplementedError (see above for traceback): Cast string to float is not supported
[[node dnn/input_from_feature_columns/input_layer/Gender/ToFloat (defined at neuralnetwork_1.py:39) = Cast[DstT=DT_FLOAT, SrcT=DT_STRING, Truncate=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](dnn/input_from_feature_columns/input_layer/Gender/ExpandDims)]]
当我尝试运行我的神经网络时 . 我试图解决它，但找不到任何解决方案 . 真的很感激有人可以弄清楚为什么会出现这种错误 . 我相信这与我的数据集和功能有关，但我不知道 .
neuralnetwork_1.py：
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import tensorflow as tf
import livercancer_data
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=100, type=int, help='batch size')
parser.add_argument('--train_steps', default=1000, type=int,
help='number of training steps')
def main(argv):
args = parser.parse_args(argv[1:])
# Fetch the data
(train_x, train_y), (test_x, test_y) = livercancer_data.load_data()
# Feature columns describe how to use the input.
my_feature_columns = []
for key in train_x.keys():
my_feature_columns.append(tf.feature_column.numeric_column(key=key))
# Build 2 hidden layer DNN with 10, 10 units respectively.
classifier = tf.estimator.DNNClassifier(
feature_columns=my_feature_columns,
# Two hidden layers of 10 nodes each.
hidden_units=[22, 22],
# The model must choose between 3 classes.
n_classes=2)
# Train the Model.
classifier.train(
input_fn=lambda:livercancer_data.train_input_fn(train_x, train_y,
args.batch_size),
steps=args.train_steps)
# Evaluate the model.
eval_result = classifier.evaluate(
input_fn=lambda:livercancer_data.eval_input_fn(test_x, test_y,
args.batch_size))
print('\nTest set accuracy: {accuracy:0.3f}\n'.format(**eval_result))
# Generate predictions from the model
expected = ['Yes', 'No', 'Yes']
predict_x = {
'Age': [46, 39, 60],
'Gender': [1, 0, 0],
'TB': [1.4, 1.6, 19.6],
'DB': [0.4, 0.8, 9.5],
'Alkphos': [298, 230, 466],
'Sgpt': [509, 88, 46],
'Sgot': [623, 74, 52],
'TP': [3.6, 8, 6.1],
'ALB': [1, 4, 2],
'AGRatio': [0.3, 1, 0.4],
}
predictions = classifier.predict(
input_fn=lambda:livercancer_data.eval_input_fn(predict_x,
labels=None,
batch_size=args.batch_size))
template = ('\nPrediction is "{}" ({:.1f}%), expected "{}"')
for pred_dict, expec in zip(predictions, expected):
class_id = pred_dict['class_ids'][0]
probability = pred_dict['probabilities'][class_id]
print(template.format(livercancer_data.SPECIES[class_id],
100 * probability, expec))
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
tf.app.run(main)
livercancer_data.py：
import pandas as pd
import tensorflow as tf
TRAIN_URL = "file:///Users/andyjiang/Desktop/Neural%20Network/livercancer_trainset.csv"
TEST_URL = "file:///Users/andyjiang/Desktop/Neural%20Network/livercancer_testset.csv"
CSV_COLUMN_NAMES = ['Age', 'Gender', 'TB', 'DB', 'Alkphos', 'Sgpt', 'Sgot', 'TP', 'ALB', 'AGRatio', 'Diagonsis']
DIAGONSIS = ['Yes', 'No']
def maybe_download():
train_path = tf.keras.utils.get_file(TRAIN_URL.split('/')[-1], TRAIN_URL)
test_path = tf.keras.utils.get_file(TEST_URL.split('/')[-1], TEST_URL)
return train_path, test_path
def load_data(y_name='Diagonsis'):
"""Returns the iris dataset as (train_x, train_y), (test_x, test_y)."""
train_path, test_path = maybe_download()
train = pd.read_csv(train_path, names=CSV_COLUMN_NAMES, header=0)
train_x, train_y = train, train.pop(y_name)
test = pd.read_csv(test_path, names=CSV_COLUMN_NAMES, header=0)
test_x, test_y = test, test.pop(y_name)
return (train_x, train_y), (test_x, test_y)
def train_input_fn(features, labels, batch_size):
"""An input function for training"""
# Convert the inputs to a Dataset.
dataset = tf.data.Dataset.from_tensor_slices((dict(features), labels))
# Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(1000).repeat().batch(batch_size)
# Return the dataset.
return dataset
def eval_input_fn(features, labels, batch_size):
"""An input function for evaluation or prediction"""
features=dict(features)
if labels is None:
# No labels, use only features.
inputs = features
else:
inputs = (features, labels)
# Convert the inputs to a Dataset.
dataset = tf.data.Dataset.from_tensor_slices(inputs)
# Batch the examples
assert batch_size is not None, "batch_size must not be None"
dataset = dataset.batch(batch_size)
# Return the dataset.
return dataset
# The remainder of this file contains a simple example of a csv parser,
# implemented using the `Dataset` class.
# `tf.parse_csv` sets the types of the outputs to match the examples given in
# the `record_defaults` argument.
CSV_TYPES = [[0], [0], [0.0], [0.0], [0], [0], [0], [0.0], [0.0], [0.0], [0]]
def _parse_line(line):
# Decode the line into its fields
fields = tf.decode_csv(line, record_defaults=CSV_TYPES)
# Pack the result into a dictionary
features = dict(zip(CSV_COLUMN_NAMES, fields))
# Separate the label from the features
label = features.pop('Diagonsis')
return features, label
def csv_input_fn(csv_path, batch_size):
# Create a dataset containing the text lines.
dataset = tf.data.TextLineDataset(csv_path).skip(1)
# Parse each line.
dataset = dataset.map(_parse_line)
# Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(1000).repeat().batch(batch_size)
# Return the dataset.
return dataset
完全错误：
Caused by op 'dnn/input_from_feature_columns/input_layer/Gender/ToFloat', defined at:
File "neuralnetwork_1.py", line 82, in <module>
tf.app.run(main)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "neuralnetwork_1.py", line 39, in main
steps=args.train_steps)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 354, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1207, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1237, in _train_model_default
features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1195, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/canned/dnn.py", line 486, in _model_fn
shared_state_manager=shared_state_manager)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/canned/dnn.py", line 300, in _dnn_model_fn
logits = logit_fn(features=features, mode=mode)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/canned/dnn.py", line 109, in dnn_logit_fn
return dnn_model(features, mode)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 757, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/estimator/canned/dnn.py", line 204, in call
net = self._input_layer(features)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 333, in __call__
from_template=True)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 368, in __call__
return self._call_func(args, kwargs)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 311, in _call_func
result = self._func(*args, **kwargs)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 222, in _internal_input_layer
return _get_logits()
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 201, in _get_logits
trainable=trainable)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2500, in _get_dense_tensor
return inputs.get(self)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2289, in get
transformed = column._transform_feature(self) # pylint: disable=protected-access
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2475, in _transform_feature
return math_ops.to_float(input_tensor)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 732, in to_float
return cast(x, dtypes.float32, name=name)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 677, in cast
x = gen_math_ops.cast(x, base_type, name=name)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 1659, in cast
"Cast", x=x, DstT=DstT, Truncate=Truncate, name=name)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/Users/andyjiang/project/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
self._traceback = tf_stack.extract_stack()
UnimplementedError (see above for traceback): Cast string to float is not supported
[[node dnn/input_from_feature_columns/input_layer/Gender/ToFloat (defined at neuralnetwork_1.py:39) = Cast[DstT=DT_FLOAT, SrcT=DT_STRING, Truncate=false, _device="/job:localhost/replica:0/task:0/device:CPU:0"](dnn/input_from_feature_columns/input_layer/Gender/ExpandDims)]]
数据集：