如何在keras中获取输入并行层

Question

我正在尝试建立一个模型来对 12 导联 ECG 信号进行分类。我想要的是，每条线索首先通过不同的 conv1D 层，然后我想将它们全部连接起来。我不知道如何在将输入提供给模型时拆分输入。这是我尝试过的方法，但出现错误：


input = keras.Input(shape=(1000, 12))

conv1=(layers.Conv1D(32,(7),activation='relu'))
conv1=conv1(input[:,:,0])

conv2=(layers.Conv1D(32,(7),activation='relu'))
conv2=conv2(input[:,:,1])

conv3=(layers.Conv1D(32,(7),activation='relu'))
conv3=conv3(input[:,:,2])

conv4=(layers.Conv1D(32,(7),activation='relu'))
conv4=conv4(input[:,:,3])

conv5=(layers.Conv1D(32,(7),activation='relu'))
conv5=conv5(input[:,:,4])

conv6=(layers.Conv1D(32,(7),activation='relu'))
conv6=conv6(input[:,:,5])

conv7=(layers.Conv1D(32,(7),activation='relu'))
conv7=conv7(input[:,:,6])

conv8=(layers.Conv1D(32,(7),activation='relu'))
conv8=conv8(input[:,:,7])

conv9=(layers.Conv1D(32,(7),activation='relu'))
conv9=conv9(input[:,:,8])

conv10=(layers.Conv1D(32,(7),activation='relu'))
conv10=conv10(input[:,:,9])

conv11=(layers.Conv1D(32,(7),activation='relu'))
conv11=conv11(input[:,:,10])

conv12=(layers.Conv1D(32,(7),activation='relu'))
conv12=conv12(input[:,:,11])

conv13=tf.keras.layers.concatenate([conv1,conv2,conv3,conv4,conv5,conv6,conv7,conv8,conv9,conv10,conv11,conv12], axis=2)

错误说：


ValueError: Input 0 of layer conv1d_6 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 1000]

谁能帮我解决这个问题？

Answer 1

错误消息解释了错误，input[:,:,11] 将张量从 3 维折叠到 2 维，因此您需要使用 input[:,:,11:12] 或 tf.expand_dims(input[:,:,11], axis=-1) 来保留最后一个维度。

import tensorflow as tf
from tensorflow.keras.layers import Conv1D

n_layers = 12
n_filters = 32
k = 7
activation_fn = 'relu'


input = tf.keras.Input(shape=(1000, n_layers))
layers = {
    f'conv{i}': Conv1D(n_filters, (k), activation=activation_fn) for i in range(n_layers)
}

channels = [layers[f'conv{i}'](input[:,:,i:i+1]) for i in range(n_layers)]

convcat = tf.keras.layers.concatenate(channels, axis=2)

如何在keras中获取输入并行层

How to take input parallel layers in keras

python

conv-neural-network

keras

tensorflow