如何选择一维信号的张量形状？由于张量形状，我一直得到VlaueError

Question

我试图为一维信号建立CNN模型，但我无法理解等级错误。

我的程序是这样的：

#Weights
def init_weights(shape):
    init_random_dist = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(init_random_dist)


#Bias
def init_bias(shape):
    init_bias = tf.constant(0.1,shape=shape)
    return tf.Variable(init_bias)

def conv1d(x,W):
    #x is input accelration data and W is corresponding weight
    x = tf.cast(x, tf.float32)
    tf.nn.conv1d(x,W,stride=1,padding='VALID')

def convolution_layer(input_x,shape):
    w = init_weights(shape)
    b = init_bias([shape[3]])
    return tf.nn.relu(conv1d(input_x,w)+b)

• 现在占位符 x = tf.placeholder(tf.float32,shape=[1,1,200,1]) y_true = tf.placeholder(tf.float32,shape=[None,6])

当使用con_layer_1 = convolution_layer(x,shape=[1,20,1,32])创建第一层时，我得到了等级ValueError，这是我无法执行的。错误声明是：

ValueError: Shape must be rank 4 but is rank 5 for 'conv1d_20/Conv2D' (op: 'Conv2D') with input shapes: [1,1,1,200,1], [1,1,20,1,32].

Answer 1

nn.conv1d的输入和权重形状不正确。nn.conv1d的输入形状应该是大小：[ batch_size, input_length, input_channels]，权重矩阵应该是[filter_size, inputs_channels, output_channels]大小。因此，您需要将代码更改为：

def convolution_layer(input_x,shape):
   w = init_weights(shape)
   b = init_bias([shape[2]])
   return tf.nn.relu(conv1d(input_x,w)+b)

x = tf.placeholder(tf.float32,shape=[1,200,1])

y_true = tf.placeholder(tf.float32,shape=[None,6])

con_layer_1 = convolution_layer(x,shape=[20,1,32]) 

注意:您应该尝试使用You来处理权重分配等问题。