2017-02-15 155 views
3

我试图使用tensorflow用于实现dcgan并遇到了这个错误:Tensorflow错误:ValueError异常:形状必须是同等级别,但2个和1个从合并形状1与其他形状

ValueError: Shapes must be equal rank, but are 2 and 1 
From merging shape 1 with other shapes. for 'generator/Reshape/packed' (op: 'Pack') with input shapes: [?,2048], [100,2048], [2048]. 

据iv收集它表明我的张量形状是不同的,但我不明白我需要改变,以解决这个错误。我相信,这个错误在这些方法之间的某处挂起:

首先,我使用创建的方法的占位符:

self.z = tf.placeholder(tf.float32, [None,self.z_dimension], name='z') 
self.z_sum = tf.histogram_summary("z", self.z) 

self.G = self.generator(self.z) 

然后最后一条语句调用生成方法,该方法使用重塑通过改变张量:

self.z_ = linear(z,self.gen_dimension * 8 * sample_H16 * sample_W16, 'gen_h0_lin', with_w=True) 

self.h0 = tf.reshape(self.z_,[-1, sample_H16, sample_W16,self.gen_dimension * 8]) 

h0 = tf.nn.relu(self.gen_batchnorm1(self.h0)) 

如果它帮助这里是我的线性方法:

def linear(input_, output_size, scope=None, stddev=0.02, bias_start=0.0, with_w=False): 
shape = input_.get_shape().as_list() 

with tf.variable_scope(scope or "Linear"): 
    matrix = tf.get_variable("Matrix", [shape[1], output_size], tf.float32,tf.random_normal_initializer(stddev=stddev)) 
    bias = tf.get_variable("bias", [output_size],initializer=tf.constant_initializer(bias_start)) 
    if with_w: 
    return tf.matmul(input_, matrix) + bias, matrix, bias 
    else: 
    return tf.matmul(input_, matrix) + bias 

编辑:

我也使用这些占位符:

self.inputs = tf.placeholder(tf.float32, shape=[self.batch_size] + image_dimension, name='real_images') 
    self.gen_inputs = tf.placeholder(tf.float32, shape=[self.sample_size] + image_dimension, name='sample_inputs') 
    inputs = self.inputs 
    sample_inputs = self.gen_inputs 

回答

4

linear(z, self.gen_dimension * 8 * sample_H16 * sample_W16, 'gen_h0_lin', with_w=True)将返回元组(tf.matmul(input_, matrix) + bias, matrix, bias)。因此,self.z_由元组分配,而不是唯一的一个tf张量。

只需将linear(z, self.gen_dimension * 8 * sample_H16 * sample_W16, 'gen_h0_lin', with_w=True)更改为linear(z, self.gen_dimension * 8 * sample_H16 * sample_W16, 'gen_h0_lin', with_w=False)即可。

+0

干杯!成功了! – Volken

相关问题