TypeError：将形状转换为 TensorShape 时出错：int() 参数必须是字符串、类似字节的对象或数字，而不是"元组"。在蟒蛇中

Question

我在运行下面的代码时遇到了这个错误，我在网上找到了关于定义机器学习模型的代码：

raise TypeError("Error converting %s to a TensorShape: %s." % (arg_name, e))
TypeError: Error converting shape to a TensorShape: int() argument must be a string, a
bytes-like object or a number, not 'tuple'.

import pandas as pd
import numpy  as np
customers = pd.read_csv('EcommerceCustomers.csv')
X = customers[['Avg. Session Length', 'Time on App', 'Time on Website','Length of Membership']].values
y = customers['Yearly Amount Spent'].values
from sklearn.model_selection import train_test_split
X_training, X_testing, Y_training, Y_testing = train_test_split(X, y, test_size=0.30, random_state=101)
Y_training= np.reshape(Y_training, (-1, 1))
Y_testing= np.reshape(Y_testing, (-1, 1))
from sklearn.preprocessing import MinMaxScaler
X_scaler = MinMaxScaler(feature_range=(0, 1))
Y_scaler = MinMaxScaler(feature_range=(0, 1))
X_scaled_training = X_scaler.fit_transform(X_training)
Y_scaled_training = Y_scaler.fit_transform(Y_training)
X_scaled_testing = X_scaler.fit_transform(X_testing)
Y_scaled_testing = Y_scaler.fit_transform(Y_testing)
print(X_scaled_testing.shape)
print(Y_scaled_testing.shape)
print("Note: Y values were scaled by multiplying by {:.10f} and adding {:.4f}".format(Y_scaler.scale_[0], Y_scaler.min_[0]))
from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(50, input_dim=, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss="mean_squared_error", optimizer="adam")

错误发生在以下行：

model.add(Dense(50, input_dim=, activation='relu'))`

造成这种问题的原因是什么？我试了很多例子，但都找不到解决办法。

Answer 1

在您的代码中，这一行有一个拼写错误：

model.add(Dense(50, input_dim=, activation='relu'))

参数input_dim应该是计划提供给该层的阵列的形状(展平)。实际上，我建议使用input_shape。

试试这个：

model.add(Dense(50, input_shape=X[0].shape, activation='relu'))

看看keras参考文档

Answer 2

此行将导致语法错误。Dense(50, input_dim=, activation='relu')

In [1]: Dense(50, input_dim=, activation='relu')
File "<ipython-input-2-ed8b4d6f4769>", line 1
Dense(50, input_dim=, activation='relu')
^
SyntaxError: invalid syntax

调用keras.layers.Dense时不能将input_dim留空，必须传递input_dim或input_shape。

model.add(Dense(50, input_dim=(16, ), activation='relu'))

Answer 3

我在tensorflow 2.0和新keras中遇到了同样的问题，我使用了input_dim参数，但我应该执行input_shape:

model_1.add(Dense(10, activation='relu', input_shape=(50,50,3)))