时间戳

首页 > 解决方案 > 检查目标时出错：预期 conv2d 有 4 个维度，但得到了具有形状的数组

python-3.x - 检查目标时出错：预期 conv2d 有 4 个维度，但得到了具有形状的数组

问题描述

我已经建立了一个 Keras ConvLSTM 神经网络，我想根据一系列 10 个时间步长预测前一帧：

model = Sequential()
model.add(ConvLSTM2D(filters=128, kernel_size=(3, 3),
                   input_shape=(None, img_size, img_size, Channels),
                   padding='same', return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(filters=64, kernel_size=(3, 3),
                   padding='same', return_sequences=True))
model.add(BatchNormalization())

model.add(ConvLSTM2D(filters=64, kernel_size=(3, 3),
                   padding='same', return_sequences=False))
model.add(BatchNormalization())


model.add(Conv2D(filters=1, kernel_size=(3, 3),
               activation='sigmoid',
               padding='same', data_format='channels_last', name='conv2d'))


model.compile(loss='binary_crossentropy', optimizer='adadelta')

训练：

data_train_x:(10, 10, 62, 62, 12)
data_train_y:(10, 1, 62, 62, 1)


model.fit(data_train_x, data_train_y, batch_size=10, epochs=1, 
validation_split=0.05)

但我收到以下错误：

ValueError: Error when checking target: expected conv2d to have 4 dimensions, but got array with shape (10, 1, 62, 62, 1)

这是“model.summary()”的结果：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv_lst_m2d_4 (ConvLSTM2D)  (None, None, 62, 62, 128) 645632    
_________________________________________________________________
batch_normalization_3 (Batch (None, None, 62, 62, 128) 512       
_________________________________________________________________
conv_lst_m2d_5 (ConvLSTM2D)  (None, None, 62, 62, 64)  442624    
_________________________________________________________________
batch_normalization_4 (Batch (None, None, 62, 62, 64)  256       
_________________________________________________________________
conv_lst_m2d_6 (ConvLSTM2D)  (None, 62, 62, 64)        295168    
_________________________________________________________________
batch_normalization_5 (Batch (None, 62, 62, 64)        256       
_________________________________________________________________
conv2d (Conv2D)              (None, 62, 62, 1)         577       
=================================================================
Total params: 1,385,025
Trainable params: 1,384,513
Non-trainable params: 512
_________________________________________________________________

这个模型是另一个模型的修改版本，编译没有错误，与之前模型的变化只是最后两层。以前是这样的：

model.add(ConvLSTM2D(filters=64, kernel_size=(3, 3),
                   padding='same', return_sequences=True))
model.add(BatchNormalization())


model.add(Conv3D(filters=1, kernel_size=(3, 3, 3),
               activation='sigmoid',
               padding='same', data_format='channels_last', name='conv3d'))

我进行此更改是因为我想获得表单的 4 维输出（samples、output_row、output_col、filters）

标签： python-3.xtensorflowkerasconv-neural-networkrecurrent-neural-network

解决方案

错误信息很清楚。模型期望输出等级为 4，但您传递的输出等级为 5。在将 data_train_y 的第二维输入模型之前，先压缩它。

data_train_y = tf.squeeze(data_train_y, axis=1)

推荐阅读