Question

我正在使用带有TF后端的keras来构建一个简单的Conv1d网络。数据具有以下形状：

train feature shape: (33960, 3053, 1)
train label shape: (33960, 686, 1)

我使用以下方法构建模型：

def create_conv_model():

    inp =  Input(shape=(3053, 1))
    conv = Conv1D(filters=2, kernel_size=2)(inp)
    pool = MaxPool1D(pool_size=2)(conv)
    flat = Flatten()(pool)
    dense = Dense(686)(flat)
    model = Model(inp, dense)
    model.compile(loss='mse', optimizer='adam')

    return model

模型摘要：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 3053, 1)           0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 3052, 2)           6         
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 1526, 2)           0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 3052)              0         
_________________________________________________________________
dense_1 (Dense)              (None, 686)               2094358   
=================================================================
Total params: 2,094,364
Trainable params: 2,094,364
Non-trainable params: 0

运行时

model.fit(x=train_feature,
    y=train_label_categorical,
    epochs=100,
    batch_size=64,
    validation_split=0.2,
    validation_data=(test_feature,test_label_categorical),
    callbacks=[tensorboard,reduce_lr,early_stopping])

我收到以下非常常见的错误：

ValueError: Error when checking input: expected input_1 to have 3 dimensions, but got array with shape (8491, 3053)

我已经检查了有关此常见问题的几乎所有帖子，但一直找不到解决方案。我究竟做错了什么？我不明白发生了什么。形状(8491, 3053)来自哪里？

任何帮助将不胜感激，我无法解决这个问题。

Answer 1

将validation_data=(test_feature,test_label_categorical)函数中的model.fit更改为

validation_data=(np.expand_dims(test_feature, -1),test_label_categorical)

该模型期望形状为(8491, 3053, 1)的验证功能，但是在上面的代码中，您正在提供形状(8491, 3053)。

Keras Conv1d输入形状：检查输入时出错

1 个答案: