0

我尝试对我的数据使用 tensorflow 联合学习工具。我有两个从 csv 文件中获得的数据集（dataset 和 dataset2），其中前 15 列是特征，最后一列是标签。我将我的 pandas 数据框转换为 tensorflow 数据集。但是，在迭代器中，有一个奇怪的类型错误。我是 tensrflow 的新手并发送代码：任何帮助将不胜感激。提前致谢。

from __future__ import absolute_import, division, print_function
from sklearn.preprocessing import MinMaxScaler
from keras.models import Model

import collections
import numpy as np
import tensorflow as tf
import tensorflow_federated as tff
from numpy import loadtxt
from keras.models import Sequential
from keras.layers import Dense
from numpy import loadtxt
from keras.models import Sequential
from keras.layers import Dense
import pandas as pd


X_train= pd.read_csv('./daily_frames_HR.csv')



values = X_train.values

values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# frame as supervised learning

train = values[:, :]
# split into input and outputs
X, y = train[:, :-2], train[:, -1]


def create_compiled_keras_model():
  model = tf.keras.models.Sequential([
    tf.keras.layers.Dense(
      12, activation=tf.nn.softmax, kernel_initializer='zeros', input_dim=15)])

  return model

def model_fn():
  keras_model = create_compiled_keras_model()

  keras_model.compile(loss='binary_crossentropy', optimizer='sgd', metrics= 
   ['SparseCategoricalAccuracy'])
  X_train = pd.read_csv('./daily_frames_HR.csv')

  values = X_train.values

  values = values.astype('float32')
  # normalize features
  scaler = MinMaxScaler(feature_range=(0, 1))
  scaled = scaler.fit_transform(values)
  # frame as supervised learning

  train = values[:, :]
  # split into input and outputs
  X, y = train[:, :-2], train[:, -1]

  sample_batch = collections.OrderedDict([('x', X), ('y', y)])
  return tff.learning.from_compiled_keras_model(keras_model, sample_batch)


  iterative_process = tff.learning.build_federated_averaging_process(model_fn)

  state = iterative_process.initialize()

  X2_train= pd.read_csv('./lab_frames_HR.csv')
  values2 = X2_train.values

  values2 = values2.astype('float32')
  # normalize features
  scaler = MinMaxScaler(feature_range=(0, 1))
  scaled = scaler.fit_transform(values2)
  # frame as supervised learning

  train2 = values2[:, :]
  # split into input and outputs
  X2, y2 = train2[:, :-2], train2[:, -1]

  X2=pd.DataFrame(X2)
  y2=pd.DataFrame(y2)

  X=pd.DataFrame(X)
  y=pd.DataFrame(y)


dataset = tf.data.Dataset.from_tensor_slices((X2.values, y2.values))

dataset2= tf.data.Dataset.from_tensor_slices((X.values, y.values))


list = [dataset, dataset2]

state, metrics = iterative_process.next(state, list)
print('round  1, metrics={}'.format(metrics))

错误信息如下：

回溯（最近一次通话）：文件“/home/affectech/Desktop/Fed_son/Fed_son.py”，第 117 行，处于状态，metrics = iterative_process.next(state, list) 文件“/home/affectech/Desktop/Fed_son /venv/lib/python3.6/site-packages/tensorflow_federated/python/core/impl/utils/function_utils.py”，第 666 行，调用中 arg = pack_args（self._type_signature.parameter，args，kwargs，context）文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core/impl/utils/function_utils .py”，第 424 行，在 pack_args 上下文中）文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core/impl/utils/function_utils.py”，行346，在pack_args_into_anonymous_tuple result_elements.append((name, context.ingest(arg_value, elem_type))) 文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core/ impl/reference_executor.py”，第 629 行，在摄取中返回 to_representation_for_type(arg, type_spec, _handle_callable) 文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core/impl/reference_executor.py”，第 241 行，to_representation_for_type 中的 v 值文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages /tensorflow_federated/python/core/impl/reference_executor.py”，第 241 行，in for v in value File “/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core /impl/reference_executor.py”，第 200 行，to_representation_for_type 中的 v 值文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core/impl/reference_executor. py”，第 200 行，在值文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core/impl/reference_executor.py”中，第 192 行，在 to_representation_for_type callable_handler) 文件“/home/affectech/Desktop/Fed_son/venv/lib/python3.6/site-packages/tensorflow_federated/python/core/impl/reference_executor.py”，第 165 行，在 to_representation_for_type '类型规范 { }.'.format(inferred_type_spec, type_spec)) TypeError：值表示的张量类型float32[15]与类型spec float32[?,15]不匹配。

进程以退出代码 1 结束

4

2 回答 2

2

看起来调用iterative_process.next(state, list)期望数据集列表 ( list) 是批处理数据集的列表。1如果您不希望每批有多个示例，批量大小甚至可以是。

batch_size = 1
list = [dataset.batch(batch_size), dataset2.batch(batch_size)]

print(iterative_process.next.type_signature)使用和可以打印不同对象的类型。tf.data.experimental.get_structure(dataset)

于 2019-10-22T12:37:32.820 回答
0

我看到的一个问题是

X, y = train[:, :-2], train[:, -1]

您在这里丢失了最后一个功能列，它应该是

X, y = train[:, :-1], train[:, -1]

使这个脚本令人困惑的是函数体中train,X和的重新定义。y该程序永远不会遇到您发布的错误，因为X2它没有被使用的时间定义。作为一般规则，我建议不要重用变量名，这将使您更容易调试程序。

然后，当您抱怨某物的形状时，请在错误发生之前将其（或其中的一部分）打印出来，这将有助于诊断出问题所在。

于 2019-10-21T18:20:06.730 回答