Keras中的目标阵列形状

Question

我试图建立一个模型，对网络攻击（DDoS或良性攻击）进行分类。为此，我使用了来自https://www.unb.ca/cic/datasets/ids-2017.html的“ISCX 2017”数据集。一切都很顺利，直到我符合模型

我收到这个错误ValueError: A target array with shape (180568, 80) was passed for an output of shape (None, 8, 80) while using as loss `categorical_crossentropy`. This loss expects targets to have the same shape as the output.

我在网上找不到关于如何解决它的任何信息。我是Keras的新手，我将非常感谢任何指导或建议

这是我的代码片段

import os
import math
import numpy as np
import pandas as pd
import tensorflow as tf
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, MinMaxScaler, StandardScaler, RobustScaler
from tensorflow import keras
from numpy import mean
from numpy import std
layers = keras.layers


from keras.models import Sequential
from keras.layers import Dense, Conv1D, Conv2D, MaxPool1D, Dropout, Lambda, MaxPooling1D, Flatten, GlobalAveragePooling1D
from tensorflow.keras import datasets, layers, models
from tflearn.layers.normalization import local_response_normalization
from keras.layers import Dropout

# The next step is to split training and testing data. For this we will use sklearn function train_test_split().
features_train, features_test, labels_train, labels_test = train_test_split(features, labels, test_size=.2)

features_train.shape, features_test.shape, labels_train.shape, labels_test.shape 

((180568, 80), (45143, 80), (180568,), (45143,))



n_timesteps, n_features, n_outputs = features_train.shape[0], features_train.shape[1], labels_train.shape[0]

X_train = np.zeros((180568, 80, 1))
y_train = np.zeros((180568, 80))
n_timesteps, n_features, n_outputs = X_train.shape[1], X_train.shape[2], y_train.shape[1]
n_samples = 1000

X = np.random.uniform(0,1, (n_samples, n_timesteps, n_features))
y = pd.get_dummies(np.random.randint(0,n_outputs, n_samples)).values

model = tf.keras.models.Sequential([
tf.keras.layers.Conv1D(input_shape=(n_timesteps, n_features), activation='relu', kernel_size=2, filters=32),
tf.keras.layers.MaxPooling1D(strides=3),
#tf.nn.local_response_normalization((1, 1, 1, 1), depth_radius=5, bias=1, alpha=1, beta=0.5, name=None),
tf.keras.layers.LayerNormalization(axis=1),
tf.keras.layers.Conv1D(input_shape=(n_timesteps, n_features), activation='relu', kernel_size=2, filters=64),
tf.keras.layers.MaxPooling1D(strides=3), # also GlobalMaxPooling1D() is ok
tf.keras.layers.LayerNormalization(axis=1),
tf.keras.layers.Dense(80, activation='softmax')
]) 


model.compile('adam', 'categorical_crossentropy', metrics=['accuracy'])
model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d (Conv1D)              (None, 79, 32)            96        
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 26, 32)            0         
_________________________________________________________________
layer_normalization (LayerNo (None, 26, 32)            52        
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 25, 64)            4160      
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 8, 64)             0         
_________________________________________________________________
layer_normalization_1 (Layer (None, 8, 64)             16        
_________________________________________________________________
dense (Dense)                (None, 8, 80)             5200      
=================================================================
Total params: 9,524
Trainable params: 9,524
Non-trainable params: 0
______________________________

model.fit(X_train, y_train, epochs=10, verbose=1)