You need to enable JavaScript to run this app. Keras训练LSTM分类模型时验证集准确率始终为0的问题
优惠活动
大模型
产品
解决方案
定价
更多

Keras训练LSTM分类模型时验证集准确率始终为0的问题

项目基本情况
  • 基于Python、Keras框架搭建了极简结构的LSTM数据集分类模型,网络仅包含3个组成部分:1个输入层、1个LSTM隐藏层、1个Dense输出层。
  • 使用的数据集为模拟采集的测量序列:总样本99组,其中63组用于训练,36组用于测试;单组样本包含3个采集通道,每个通道有19200个采样点。
  • 参照Keras官方输入层的规范说明,我确认网络可正常接收3D输入张量的形状配置为x=(63,19200,3)、y=(36,19200,3)(若需了解数据类型的更多细节,可随时补充)。
项目代码

整体代码逻辑非常简单,目前仍在整理优化过程中,核心代码如下:

import numpy as np
import matplotlib.pyplot as plt
from sklearn.utils import shuffle
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Input
from keras.layers import Dropout
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from keras import initializers
from keras import optimizers

# 固定随机种子保证结果可复现
np.random.seed(1)

# 加载数据(维度说明:X_test (36,19200,3), y_test (36,3), X_train (63,19200,3), y_train (63,3))
(X_test, y_test), (X_train, y_train) = np.load('path.npy',allow_pickle=True)
data = [(X_test, y_test), (X_train, y_train)]

# 手动拆分验证集
x_val = X_train[-10:]
y_val = y_train[-10:]
X_train = X_train[:-10]
y_train = y_train[:-10]

# 搭建模型
model = Sequential()
model.add(Input(shape=(19200,3)))
model.add(LSTM(50, name = 'LSTM', activation='tanh',recurrent_activation='tanh', kernel_initializer=initializers.RandomNormal(mean=0.0, stddev=0.05, seed=1), bias_initializer=initializers.zeros()))
model.add(Dense(1, name = 'Saida', activation='sigmoid', kernel_initializer=initializers.RandomNormal(mean=0.0, stddev=0.05, seed=1), bias_initializer=initializers.zeros()))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
history = model.fit(X_train, y_train, epochs=20, batch_size=12, shuffle=True, validation_data=(x_val, y_val))

# 模型最终评估
scores = model.evaluate(X_test, y_test, verbose=1)
print("Accuracy: %.2f%%" % (scores[1]*100))
运行输出结果

模型结构摘要

Model: "sequential_8"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
LSTM (LSTM)                  (None, 50)                10800     
_________________________________________________________________
Saida (Dense)                (None, 1)                 51        
=================================================================
Total params: 10,851
Trainable params: 10,851
Non-trainable params: 0
_________________________________________________________________
None

训练与评估日志

Epoch 1/20
5/5 [==============================] - 17s 3s/step - loss: 0.6866 - accuracy: 0.6792 - val_loss: 0.6956 - val_accuracy: 0.0000e+00
Epoch 2/20
5/5 [==============================] - 20s 4s/step - loss: 0.6814 - accuracy: 0.8113 - val_loss: 0.6979 - val_accuracy: 0.0000e+00
Epoch 3/20
5/5 [==============================] - 21s 4s/step - loss: 0.6915 - accuracy: 0.7925 - val_loss: 0.7002 - val_accuracy: 0.0000e+00
Epoch 4/20
5/5 [==============================] - 24s 5s/step - loss: 0.6810 - accuracy: 0.7925 - val_loss: 0.7025 - val_accuracy: 0.0000e+00
Epoch 5/20
5/5 [==============================] - 25s 5s/step - loss: 0.6828 - accuracy: 0.7925 - val_loss: 0.7048 - val_accuracy: 0.0000e+00
Epoch 6/20
5/5 [==============================] - 24s 5s/step - loss: 0.6703 - accuracy: 0.8302 - val_loss: 0.7072 - val_accuracy: 0.0000e+00
Epoch 7/20
5/5 [==============================] - 24s 5s/step - loss: 0.6787 - accuracy: 0.7925 - val_loss: 0.7095 - val_accuracy: 0.0000e+00
Epoch 8/20
5/5 [==============================] - 26s 5s/step - loss: 0.6963 - accuracy: 0.7547 - val_loss: 0.7117 - val_accuracy: 0.0000e+00
Epoch 9/20
5/5 [==============================] - 25s 5s/step - loss: 0.6776 - accuracy: 0.7925 - val_loss: 0.7141 - val_accuracy: 0.0000e+00
Epoch 10/20
5/5 [==============================] - 25s 5s/step - loss: 0.6640 - accuracy: 0.8302 - val_loss: 0.7164 - val_accuracy: 0.0000e+00
Epoch 11/20
5/5 [==============================] - 24s 5s/step - loss: 0.6626 - accuracy: 0.8491 - val_loss: 0.7187 - val_accuracy: 0.0000e+00
Epoch 12/20
5/5 [==============================] - 24s 5s/step - loss: 0.6504 - accuracy: 0.8491 - val_loss: 0.7210 - val_accuracy: 0.0000e+00
Epoch 13/20
5/5 [==============================] - 24s 5s/step - loss: 0.6729 - accuracy: 0.7925 - val_loss: 0.7233 - val_accuracy: 0.0000e+00
Epoch 14/20
5/5 [==============================] - 24s 5s/step - loss: 0.6602 - accuracy: 0.8302 - val_loss: 0.7257 - val_accuracy: 0.0000e+00
Epoch 15/20
5/5 [==============================] - 25s 5s/step - loss: 0.6857 - accuracy: 0.7547 - val_loss: 0.7281 - val_accuracy: 0.0000e+00
Epoch 16/20
5/5 [==============================] - 23s 5s/step - loss: 0.6630 - accuracy: 0.8113 - val_loss: 0.7305 - val_accuracy: 0.0000e+00
Epoch 17/20
5/5 [==============================] - 25s 5s/step - loss: 0.6633 - accuracy: 0.7925 - val_loss: 0.7328 - val_accuracy: 0.0000e+00
Epoch 18/20
5/5 [==============================] - 24s 5s/step - loss: 0.6600 - accuracy: 0.8302 - val_loss: 0.7352 - val_accuracy: 0.0000e+00
Epoch 19/20
5/5 [==============================] - 25s 5s/step - loss: 0.6670 - accuracy: 0.8113 - val_loss: 0.7374 - val_accuracy: 0.0000e+00
Epoch 20/20
5/5 [==============================] - 24s 5s/step - loss: 0.6534 - accuracy: 0.8302 - val_loss: 0.7399 - val_accuracy: 0.0000e+00
2/2 [==============================] - 1s 314ms/step - loss: 0.7171 - accuracy: 0.4167
Accuracy: 41.67%
当前遇到的核心问题
  • 损失值偏高,下降速度极慢
  • 训练准确率存在波动,最终长期稳定在0.7925或0.8113的固定值
  • 验证集准确率完全不随其他指标变化产生任何响应,全程保持为0
已开展的排查与调整操作

为解决问题,此前已尝试如下调整,均未起到作用:

  • 更换优化器、网络各层的激活函数、权重初始化方式
  • 调整训练轮次(曾尝试延长至100轮,无改善)
  • 调整批量大小
  • 分别使用Keras内置方法、Python原生方法打乱训练数据

目前仅剩输入张量形状调整未尝试,但根据前期测试,当前形状配置是唯一能让输入层正常接收3D数组的方案。

这是我第一次在社区提问,非英语母语使用者,若有信息表述不清的地方敬请谅解。


内容的提问来源于stack exchange,提问作者Matheus Zimmermann

相关产品推荐
方舟 Agent Plan

超全模态模型 × Harness 升级,最新支持 Deepseek-V4.1-Flash、GLM-5.3 系列、Doubao-Seedream-5.0-pro、Kimi-K3 (部分), 限时 9.9 元起

最近更新时间:2026.10.27 05:06:04