keras分类问题，model.fit命令出错

Question

'I want to solve a classification problem by keras.model, but after running model.fit I face to a dimension error. I have run following code:'

print(X_train.shape)
print(y_train.shape)

'output:'

(2588, 39436)
(2588, 6)

model = keras.Sequential(
    [
        keras.Input(shape=(39436,1)),
        layers.Conv1D(32, kernel_size=3, strides=5, activation="relu"),
        layers.MaxPooling1D(pool_size=10),
        layers.Conv1D(64, kernel_size=3, strides=5, activation="relu"),
        layers.MaxPooling1D(pool_size=10),
        layers.Flatten(),
        layers.Dropout(0.5),
        layers.Dense(num_classes, activation="softmax"),
    ]
)

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

'After running following code, '

model.fit(X_train, y_train, batch_size=128, epochs=15, validation_split=0.3)

'I give this error:'

ValueError：在用户代码中：

ValueError: Input 0 of layer sequential_1 is incompatible with the layer: : expected min_ndim=3, found ndim=2. Full shape received: [None, 39436]

'It would be appreciated if you guide me what would be the issue?'

Answer 1

根据错误消息，您的输入数组的形状为 [None, 39436]。但是，在您的 Input 层中，您传入一个形状 [39436, 1]，它与 [None, 39436, 1] 匹配，其中 None 代表样本维度。这是抛出的错误。

您需要通过以下任一方式匹配形状：

1.重塑输入数据 以具有 [samples, 39436, 1] 的形状，保持模型架构不变。

可以这样做（假设 train_X 是您的输入特征）：

train_X = np.expand_dims(train_X, axis=2)

np.expand_dims 在数组形状的索引 2 处向数组添加一个新维度。所以在这里它将 [samples, 39436] 重塑为 [samples, 39436, 1].

参考：NumPy docs for expand_dims

或

2。更改 input_shape 参数在 Input 层接受形状 [39436,]，以匹配您的数据。

keras分类问题，model.fit命令出错

keras classification problem, error in model.fit command

classification

keras

tensorflow