CNN输入层数据维度问题？

  • Z时代
  • 2024-02-07
  • 分类：IT

为社么加了输入数据一维还是报错
CNN输入层数据维度问题？

import numpy as np
import librosa
import soundfile
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D
from keras.optimizer_v1 import Adam
import tensorflow as tf
def load_audio_data(file_path):
    audio, sample_rate = librosa.load(file_path, res_type='kaiser_fast')
    mfccs = librosa.feature.mfcc(y=audio, sr=sample_rate, n_mfcc=40)
    mfccs_processed = np.mean(mfccs.T,axis=0)
    return mfccs_processed
#CNN
def build_model():
    model = Sequential()
    model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(40, 1)))
    model.add(MaxPooling2D((2, 2)))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(1, activation='linear')) # 输出层
    model.compile(loss='mean_squared_error', optimizer=Adam())
    return model
# 训练模型
def train_model(model, X_train, y_train):
    model.fit(X_train,y_train,batch_size=128, epochs=10)
audiopath="E:\BaiduNetdiskDownload\yy\kel.wav"
audiodata=load_audio_data(audiopath)
X_train = np.array([audiodata])# 这里只使用一段音频作为训练数据，实际应用中需要更多数据
print(X_train)
X_train= tf.expand_dims(X_train, axis=-1)
y_train =1
# 构建并训练模型
model = build_model()
train_model(model, X_train, y_train)

回答：

conv2d 需要至少 4 维，这里加了一维后也还不够

以上是 CNN输入层数据维度问题？ 的全部内容， 来源链接： utcz.com/p/939049.html

回到顶部