时间戳

首页 > 解决方案 > 1D CNN keras 形状错误

python - 1D CNN keras 形状错误

问题描述

我正在尝试将一维 CNN 拟合到我的数据中。数据由 MEL 频率组成，具有以下特征：

X_train.shape = (68251, 99)
y_train_hot.shape = (68251, 35)<-- one hot encoding with 35 output classes

当我尝试训练模型时，我收到以下代码的此值错误：

ValueError: Error when checking input: expected conv1d_5_input to have 3 dimensions, but got array with shape (68251, 99)


#hyperparameters
input_dimension = 68251
learning_rate = 0.0025
momentum = 0.85
hidden_initializer = random_uniform(seed=1)
dropout_rate = 0.2
# create model
model = Sequential()
model.add(Convolution1D(nb_filter=32, filter_length=3, input_shape=X_train.shape, activation='relu'))
model.add(Convolution1D(nb_filter=16, filter_length=1, activation='relu'))
model.add(Flatten())
model.add(Dropout(dropout_rate))
model.add(Dense(128, input_dim=input_dimension, kernel_initializer=hidden_initializer, activation='relu'))
model.add(Dropout(dropout_rate))
model.add(Dense(64, kernel_initializer=hidden_initializer, activation='relu'))
model.add(Dense(2, kernel_initializer=hidden_initializer, activation='softmax'))

sgd = SGD(lr=learning_rate, momentum=momentum)
model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['acc'])
model.fit(X_train, y_train_hot, epochs=5, batch_size=128)
predictions = model.predict_proba(X_test)

ans = pd.DataFrame(predictions)
ans = ans[0]

当我将 X_train 和 X_test 分别重塑为 (68251, 99, 1) 和 (17063, 99, 1) 时，出现以下错误：

ValueError: Input 0 is incompatible with layer conv1d_7: expected ndim=3, found ndim=4

标签： pythonkerasconv-neural-networkshapes

解决方案

编辑
这次我实际上编译了你的模型，发现了一些问题并纠正了它们：

# create model
model = Sequential()
model.add(Convolution1D(nb_filter=32, filter_length=3, input_shape=(99, 1), activation='relu'))
model.add(Convolution1D(nb_filter=16, filter_length=1, activation='relu'))
model.add(Flatten())
model.add(Dropout(0.2))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(64, activation='relu'))
model.add(Dense(35, activation='softmax'))


model.compile(loss='binary_crossentropy', optimizer='sgd', metrics=['acc'])
model.fit(X_train, y_train_hot, epochs=5, batch_size=128)

您的输出是 2 并且应该是 35，因为您有 35 个输出类，您的第一个 Dense 不需要 input_dim 因为形状将由前一层推断，并且输入形状是错误的。
希望这可以帮助

推荐阅读