Tensorflow 错误“shape Tensorshape() must have rank 1" [英] Tensorflow error "shape Tensorshape() must have rank 1"

问题描述

import tensorflow as tf
import numpy as np
import os
from PIL import Image
cur_dir = os.getcwd()

def modify_image(image):
  #resized = tf.image.resize_images(image, 180, 180, 3)
   image.set_shape([32,32,3])
   flipped_images = tf.image.flip_up_down(image)
   return flipped_images

def read_image(filename_queue):
  reader = tf.WholeFileReader()
  key,value = reader.read(filename_queue)
  image = tf.image.decode_jpeg(value)
  return key,image

def inputs():
 filenames = ['standard_1.jpg', 'standard_2.jpg' ]
 filename_queue = tf.train.string_input_producer(filenames)
 filename,read_input = read_image(filename_queue)
 reshaped_image = modify_image(read_input)
 reshaped_image = tf.cast(reshaped_image, tf.float32)
 label=tf.constant([1])
 return reshaped_image,label

def weight_variable(shape):
 initial = tf.truncated_normal(shape, stddev=0.1)
 return tf.Variable(initial)

def bias_variable(shape):
 initial = tf.constant(0.1, shape=shape)
 return tf.Variable(initial)

def conv2d(x, W):
 return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
 return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                    strides=[1, 2, 2, 1], padding='SAME')

x = tf.placeholder(tf.float32, shape=[None,32,32,3])
y_ = tf.placeholder(tf.float32, shape=[None, 1])
image,label=inputs()
image=tf.reshape(image,[-1,32,32,3])
label=tf.reshape(label,[-1,1])
image_batch=tf.train.batch([image],batch_size=2)
label_batch=tf.train.batch([label],batch_size=2)

W_conv1 = weight_variable([5, 5, 3, 32])
b_conv1 = bias_variable([32])

image_4d=x_image = tf.reshape(image, [-1,32,32,3])

h_conv1 = tf.nn.relu(conv2d(image_4d, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([8 * 8 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 8*8*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 2])
b_fc2 = bias_variable([2])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy= -tf.reduce_sum(tf.cast(image_batch[1],tf.float32)*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

for i in range(20000):
 sess.run(train_step,feed_dict={x:image_batch[0:1],y_:label_batch[0:1]})

我正在尝试在我自己的 [32x32x3] 图像尺寸的图像上运行 tensorflow 卷积模型.在训练期间，图像被正确读取并被分配给占位符.在运行 train_step 操作期间出现问题.当我执行图表时，我收到以下错误.

I am trying to run the tensorflow convolutional model over my own images of dimension of[32x32x3] images. The images are being read properly and are being assigned to the placeholder, during training. The problem arises during running the train_step op. When I execute the graph I get the following error.

TensorShape([Dimension(2), Dimension(1), Dimension(32), Dimension(32), Dimension(3)]) must have rank 1

但是当我看到此处的示例时，图像的形式为[batch_size,height,width,depth] 仅限张量.这个例子工作正常.我错过了什么吗?

But when I see the example here, the images are in the form of [batch_size,height,width,depth] tensors only. And this example works fine. Am I missing anything?

推荐答案

我认为错误来自这一行:

I think the error is coming from this line:

cross_entropy= -tf.reduce_sum(tf.cast(image_batch[1],tf.float32)*tf.log(y_conv))

image_batch 是一个 5-D 张量，形状为 [2, 1, 32, 32, 3]，其中 2 是 batch_size> tf.train.batch() 的参数，并且 1 是由较早的 image = tf.reshape(image, [-1, 32, 32, 3]) 添加代码>.(注意这种重塑是不必要的，因为 tf.train.batch() 已经添加了一个批次维度，您最终不得不撤销稍后构造 image_4d 时的重塑效果).

image_batch is a 5-D tensor, with shape [2, 1, 32, 32, 3], where 2 is the batch_size argument to tf.train.batch(), and the 1 was added by the earlier image = tf.reshape(image, [-1, 32, 32, 3]). (N.B. This reshape is unnecessary, since tf.train.batch() already adds a batch dimension, and you end up having to undo the effect of the reshape when you later construct image_4d).

在 TensorFlow 中，切片操作(即 image_batch[1])的灵活性略低于 NumPy.切片中指定的维度数必须等于张量的等级:即您必须指定所有五个维度才能使其工作.您可以指定 image_batch[1, :, :, :, :] 以获取 image_batch 的 4-D 切片.

In TensorFlow, the slicing operation (i.e. image_batch[1]) is slightly less flexible than in NumPy. The number of dimensions specified in the slice must be equal to the rank of the tensor: i.e. you must specify all five dimensions for this to work. You could specify image_batch[1, :, :, :, :] to get a 4-D slice of image_batch.

不过，我注意到您的程序中存在其他一些问题:

I noticed a few other issues in your program, however:

1. cross_entropy 计算看起来很奇怪.通常，这使用预测标签并将其与已知的标签进行比较，而不是图像数据.

1. The cross_entropy calculation seems strange. Typically this uses a predicted label and compares it to the known label, as opposed to the image data.

训练步骤的提要似乎没有效果，因为占位符 x 和 y_ 在您的程序中未使用.此外，您似乎在提供一个 tf.Tensor(实际上，一个非法的 image_batch 切片)，因此在您执行该语句时会失败.如果您打算使用 Feed，您应该输入包含输入数据的 NumPy 数组.

The feed on the training step seems to have no effect, because placeholders x and y_ are unused in your program. Furthermore, you appear to be feeding a tf.Tensor (indeed, an illegal slice of image_batch), so this will fail when you execute that statement. If you intend to use feeding, you should feed in NumPy arrays holding the input data.

如果您不使用喂食——即使用程序中显示的 tf.WholeFileReader—您需要调用 tf.train.start_queue_runners() 才能开始.否则你的程序将挂起，等待输入.

If you're not using feeding—i.e. using the tf.WholeFileReader as shown in your program—you will need to call tf.train.start_queue_runners() to get started. Otherwise your program will hang, waiting for input.

这篇关于Tensorflow 错误“shape Tensorshape() must have rank 1"的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！