如何解决"TypeError:添加的层必须是类Layer的实例."在Python中 [英] How to fix "TypeError: The added layer must be an instance of class Layer." in Python

问题描述

我已经写了那种神经网络的小东西.问题是我经常收到该错误消息:

I have written that little helloworld-kind of neural network. The problem is that I constantly get that error which says:

"Traceback (most recent call last):
  File "C:/Users/Pigeonnn/PycharmProjects/Noss/Network.py", line 21, in <module>
    model.add(keras.layers.InputLayer(input_shape))
  File "C:\Users\Pigeonnn\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\training\checkpointable\base.py", line 442, in _method_wrapper
    method(self, *args, **kwargs)
  File "C:\Users\Pigeonnn\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\sequential.py", line 145, in add
    'Found: ' + str(layer))
TypeError: The added layer must be an instance of class Layer. Found: <keras.engine.input_layer.InputLayer object at 0x0000015EDB394DA0>"

这是我的代码:

import keras
import numpy as np
from sklearn.model_selection import train_test_split
import pandas as pd
from sklearn.utils import shuffle
import tensorflow as tf

seed = 10
np.random.seed(seed)

dataset = np.loadtxt("dataset2.csv",delimiter=',',skiprows=1)
dataset = shuffle(dataset)

X = dataset[:,2:]
Y = dataset[:,1]

(X_train,X_test,Y_train,Y_test) = train_test_split(X, Y, test_size=0.15, random_state=seed)
input_shape = (13,)

model = tf.keras.models.Sequential()
model.add(keras.layers.InputLayer(input_shape))
model.add(keras.layers.core.Dense(128, activation='relu'))
model.add(keras.layers.core.Dense(128, activation='relu'))
model.add(keras.layers.core.Dense(4, activation='sigmoid'))

model.compile(optimizer='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])

model.fit(X_train,Y_train,epochs=20)

经过一些调整(更改损失函数，删除tf模型)，我有另一个错误，这次是:

after some tweaks(changing loss function, removing tf model), I have another error, this time its:

Traceback (most recent call last):
  File "C:/Users/Pigeonnn/PycharmProjects/Noss/Network.py", line 28, in 
    model.fit(X_train,Y_train,epochs=20)
  File "C:\Users\Pigeonnn\AppData\Local\Programs\Python\Python37\lib\site-packages\keras\engine\training.py", line 952, in fit
    batch_size=batch_size)
  File "C:\Users\Pigeonnn\AppData\Local\Programs\Python\Python37\lib\site-packages\keras\engine\training.py", line 789, in _standardize_user_data
    exception_prefix='target')
  File "C:\Users\Pigeonnn\AppData\Local\Programs\Python\Python37\lib\site-packages\keras\engine\training_utils.py", line 138, in standardize_input_data
    str(data_shape))
ValueError: Error when checking target: expected dense_3 to have shape (4,) but got array with shape (1,)

推荐答案

您正在使用不兼容的tf.keras和keras模块.仅使用一个并保持一致.

You are using both tf.keras and keras modules, which are not compatible. Use only one and be consistent.

这篇关于如何解决"TypeError:添加的层必须是类Layer的实例."在Python中的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！