ValueError: setting an array element with a sequence.

Question

import tensorflow as tf
import numpy as np
import wfdb
import pandas as pd
import ast
from matplotlib import pyplot as plt
import keras.backend as K


def load_raw_data(df, sampling_rate, path):
    if sampling_rate == 100:
        data = [wfdb.rdsamp(path+f) for f in df.filename_lr]
    else:
        data = [wfdb.rdsamp(path+f) for f in df.filename_hr]
    data = np.array([signal for signal, meta in data])
    return data

path = ''
sampling_rate = 100

# load and convert annotation data
Y = pd.read_csv('ptbxl_database.csv', index_col='ecg_id')
Y.scp_codes = Y.scp_codes.apply(lambda x: ast.literal_eval(x))
# Load raw signal data
X = load_raw_data(Y, sampling_rate, path)

# Load scp_statements.csv for diagnostic aggregation
agg_df = pd.read_csv('scp_statements.csv', index_col=0)
agg_df = agg_df[agg_df.diagnostic == 1]

def aggregate_diagnostic(y_dic):
    tmp = []
    for key in y_dic.keys():
        if key in agg_df.index:
            tmp.append(agg_df.loc[key].diagnostic_class)
    return list(set(tmp))

# Apply diagnostic superclass
Y['diagnostic_superclass'] = Y.scp_codes.apply(aggregate_diagnostic)

# Split data into train and test
test_fold = 10
# Train
X_train = X[np.where(Y.strat_fold != test_fold)]
y_train = Y[(Y.strat_fold != test_fold)].diagnostic_superclass
# Test
X_test = X[np.where(Y.strat_fold == test_fold)]
y_test = Y[Y.strat_fold == test_fold].diagnostic_superclass
# tenserflow 训练
print(X_test , y_test)
print(type(y_test))
print(type(X_test))
# <class 'pandas.core.series.Series'>
# <class 'numpy.ndarray'>

#该数据类型
y_train = y_train.astype(int[2])
y_test = y_test.astype(int[2])

X_train = tf.convert_to_tensor(X_train)
X_test = tf.convert_to_tensor(X_test)



# artificial intelligence and the training
model = tf.keras.models.Sequential([
    # 卷积层
    tf.keras.layers.Conv1D(filters = 96,
                           kernel_size = 3,
                           padding = "same"),
    tf.keras.layers.BatchNormalization(),
    tf.keras.layers.Activation("relu"),
    tf.keras.layers.AveragePooling1D(pool_size = 4,
                                     padding = "valid"),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128,activation = "sigmoid",
                          kernel_regularizer = tf.keras.regularizers.l1()),
    tf.keras.layers.Dense(5, activation = "sigmoid",
                          kernel_regularizer = tf.keras.regularizers.l2())
])

model.compile(optimizer="nadam",
              loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
              metrics = ["sparse_categorical_accuracy"])

model.fit(X_train,y_train,
          batch_size = 64,
          epochs = 10000,
          validation_data = (X_test, y_test),
          validation_freq = 1)

history = model.fit(X_train,y_train,
          batch_size = 64,
          epochs = 10000,
          validation_data = (X_test, y_test))
model.summary()

# 可视化
acc=history.history['sparse_categorical_accuaracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss=history.history['loss']
val_loss = history.history['val_loss']

plt.subplot(1,2,1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label='Validation Accuracy')
plt.title('Training and Validation Accurcy')
plt.legend()

plt.subplot(1,2,1)
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label='Validation Loss')
plt.title('Training and Validation Loss')
plt.legend()
plt.show()

这段代码的输出是

[[[-0.145 -0.097  0.049 ... -0.452 -0.269 -0.032]
  [-0.115 -0.083  0.032 ... -0.339 -0.246 -0.041]
  [-0.064 -0.06   0.005 ... -0.188 -0.199 -0.04 ]
  ...
  [ 0.23   0.292  0.063 ...  0.443  0.362  0.222]
  [ 0.251  0.319  0.067 ...  0.498  0.405  0.261]
  [ 0.338  0.361  0.023 ...  0.515  0.447  0.299]]

 [[ 0.182  0.196  0.013 ...  0.413  0.279  0.284]
  [ 0.23   0.309  0.079 ...  0.524  0.4    0.402]
  [ 0.125 -0.092 -0.217 ... -0.002  0.022  0.181]
  ...
  [-0.076 -0.085 -0.009 ... -0.02  -0.01   0.032]
  [-0.048 -0.067 -0.019 ...  0.007  0.002  0.008]
  [-0.04  -0.053 -0.013 ...  0.032  0.022  0.015]]

 [[ 0.036  0.025 -0.011 ...  0.082  0.067 -0.014]
  [ 0.054  0.044 -0.01  ...  0.11   0.091  0.003]
  [ 0.095  0.09  -0.005 ...  0.143  0.123  0.035]
  ...
  [-0.261 -0.018  0.242 ... -0.039 -0.066 -0.082]
  [-0.049 -0.039  0.01  ... -0.043 -0.064 -0.2  ]
  [ 0.071 -0.047 -0.118 ... -0.049 -0.067 -0.082]]

 ...

 [[-0.045 -0.055 -0.01  ... -0.145 -0.165 -0.124]
  [-0.045 -0.055 -0.01  ... -0.142 -0.161 -0.119]
  [-0.042 -0.056 -0.013 ... -0.136 -0.154 -0.111]
  ...
  [ 0.03   0.147  0.117 ... -0.038 -0.101 -0.116]
  [ 0.059  0.158  0.099 ... -0.001 -0.09  -0.107]
  [ 0.076  0.158  0.082 ...  0.017 -0.077 -0.098]]

 [[-0.059 -0.023  0.036 ...  0.096  0.031 -0.014]
  [-0.033  0.007  0.04  ...  0.127  0.056  0.007]
  [-0.004  0.036  0.04  ...  0.184  0.108  0.041]
  ...
  [-0.029 -0.029  0.    ... -0.072 -0.123 -0.173]
  [-0.07  -0.063  0.007 ... -0.115 -0.119 -0.224]
  [-0.015 -0.048 -0.033 ... -0.121 -0.121 -0.209]]

 [[-0.031 -0.001  0.03  ...  0.048  0.024 -0.001]
  [-0.015  0.015  0.03  ...  0.051  0.024  0.   ]
  [-0.007  0.018  0.025 ...  0.064  0.021 -0.002]
  ...
  [-0.109 -0.054  0.055 ... -0.057 -0.082 -0.09 ]
  [-0.091 -0.067  0.024 ...  0.003 -0.047 -0.085]
  [ 0.013 -0.237 -0.249 ...  0.336  0.267  0.112]]] ecg_id
9        [NORM]
38       [NORM]
40       [NORM]
57       [NORM]
59       [NORM]
          ...  
21809    [NORM]
21812      [CD]
21818    [NORM]
21819      [CD]
21826      [MI]
Name: diagnostic_superclass, Length: 2198, dtype: object
<class 'pandas.core.series.Series'>
<class 'numpy.ndarray'>

但后面报ValueError: setting an array element with a sequence.该怎么处理啊

Answer 1

引自免费微信小程序：皆我百晓生

这个问题是在尝试将TensorFlow的tensor转换为数组时出现的。错误“ValueError: setting an array element with a sequence”意味着你正在尝试将一个序列（如列表或数组）赋值给numpy数组的单个元素位置。这是因为你的数据集数据（numpy数组）与模型输入（TensorFlow tensor）的数据类型不匹配。你的数据集中的数据看起来是二维的，而你的模型期望的是一维输入数据。这意味着你需要在训练模型之前将数据集转换为一维。为此，你可以通过如下代码对输入数据进行reshape处理。下面的代码将数据展平并赋值给 X_train 和 X_test：

X_train = X_train.reshape(-1, 1)  # 将数据展平并添加到训练集
X_test = X_test.reshape(-1, 1)  # 将数据展平并添加到测试集

这样处理后，你就可以将处理后的数据输入到模型中了。请注意，这样做会使得数据的形状改变，因此在应用这种处理方式时需要谨慎。如果输入数据的结构很重要并且需要在处理时保留其形状信息，你可能需要采用不同的方法来处理这个问题。你可能需要重新审视你的数据和模型输入的结构以确保两者之间的匹配。希望这个答案能帮到你解决问题！如果还有其他问题，欢迎继续提问。