Tensorflow ValueError:Cannot feed value of shape (40, 24, 24, 4) for Tensor u'real_images:0', which has shape '(40, 24, 24, 3)'

Question

尝试实现 DCGAN 时，我在尝试使用我的训练函数时收到此错误消息：

ValueError: Cannot feed value of shape (40, 24, 24, 4) for Tensor u'real_images:0', which has shape '(40, 24, 24, 3)'

尝试使用线路时出现此错误：

_,summary_str = self.sess.run([dis_optim, self.dis_sum],feed_dict = {self.inputs: batch_images, self.z: batch_z})

关于张量为何不同的任何想法？下面我附上了我认为错误所在的代码：

real_images 占位符（self.colour_dim 为 3）：

image_dimension = [self.input_H,self.input_H, self.colour_dim]

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

发生错误的段：

for idx in xrange(0, batch_idxs):

    batch_files = data[idx * config.batch_size:(idx +1) * config.batch_size]
    batch = [getImage(batch_file,resize_h=self.output_H,resize_w=self.output_W) for batch_file in batch_files]

    batch_images = np.array(batch).astype(np.float32)
    print(batch_images)

    batch_z = np.random.uniform(-1, 1, [config.batch_size, self.z_dimension]).astype(np.float32)

    # discriminator
    _,summary_str = self.sess.run([dis_optim, self.dis_sum],feed_dict = {self.inputs: batch_images, self.z: batch_z})
    self.writer.add_summary(summary_str, counter)

使用的getImage和imread函数：

def imread(path):
    return scipy.misc.imread(path).astype(np.float)

def getImage(im_path, resize_h, resize_w):
  image = imread(im_path)
  return transform(image, resize_h, resize_w)

谢谢大家！

Answer 1

看起来您的图像加载函数正在为您提供 RGBA 图像，而网络需要 RGB 图像。将 feed dict 中的 batch_images 替换为 batch_images[:,:,:,:3] 应该是一个简单的修补程序，您还可以查看您的加载功能是否支持直接为您提供 RGB 图像。