Python 在处理CNN中的维度错误时遇到问题

我是tensorflow的新手，正在尝试脱离mnist数据集，尝试一些不同的东西。我正在使用情感数据集，似乎无法修改代码以成功运行在此数据集上。对于那些想复制我作品的人，我找到了经过处理的图像和标签。您将在ck+scaled文件夹中找到图像，在processed文件夹中找到标签

我们正在处理265幅大小为[256 x 256]的图像

这是我的代码：

import os
import tensorflow as tf
import sys
import urllib
import numpy as np
from PIL import Image
import glob
train = []
for filename in glob.glob('/Users/madhavthaker/Documents/CSCI63/Final Project/face-emoticon-master/data/ck+_scaled/*.png'): #assuming gif
    img=np.asarray(Image.open(filename))
    img_flat = img.reshape(img.size)
    train.append(img_flat)

### MNIST EMBEDDINGS ###
ckp_labels = [5, 0, 3, 5, 4, 0, 1, 3, 5, 4, 0, 3, 5, 0, 1, 5, 4, 0, 0, 0, 2, 1, 3, 5, 0, 3, 5, 1, 3, 5, 0, 3, 5, 4, 0, 3, 5, 3, 1, 1, 0, 4, 5, 2, 1, 5, 3, 5, 1, 5, 3, 1, 5, 1, 5, 0, 1, 5, 3, 5, 1, 3, 0, 1, 5, 2, 3, 1, 5, 3, 1, 3, 1, 5, 3, 2, 5, 3, 1, 5, 3, 4, 0, 5, 0, 3, 1, 3, 2, 5, 1, 3, 5, 1, 5, 4, 0, 3, 1, 5, 1, 2, 5, 1, 3, 5, 3, 5, 1, 3, 5, 5, 3, 1, 1, 3, 4, 1, 5, 4, 1, 5, 0, 1, 3, 5, 2, 3, 5, 5, 3, 5, 1, 0, 1, 5, 3, 0, 5, 1, 0, 3, 5, 0, 3, 5, 3, 1, 4, 5, 1, 3, 5, 1, 3, 1, 3, 5, 1, 5, 0, 3, 5, 1, 1, 4, 1, 5, 1, 4, 1, 0, 1, 3, 5, 5, 0, 1, 0, 5, 4, 0, 5, 3, 5, 3, 5, 1, 3, 5, 2, 0, 5, 2, 0, 5, 2, 3, 4, 3, 2, 5, 1, 5, 0, 3, 0, 1, 3, 5, 0, 1, 3, 5, 0, 4, 3, 3, 1, 4, 2, 1, 3, 5, 5, 3, 0, 3, 1, 5, 5, 0, 3, 5, 3, 2, 5, 3, 4, 7, 7, 7, 7, 7, 7, 7, 7, 0, 2, 4, 0, 7, 2, 0, 7, 0, 7, 2, 4, 4, 0, 2, 4, 7, 2]

if sys.version_info[0] >= 3:
  from urllib.request import urlretrieve
else:
  from urllib import urlretrieve

LOGDIR = 'log3/'
GITHUB_URL ='https://raw.githubusercontent.com/mamcgrath/TensorBoard-TF-Dev-Summit-Tutorial/master/'

### MNIST EMBEDDINGS ###
mnist = tf.contrib.learn.datasets.mnist.read_data_sets(train_dir=LOGDIR + 'data', one_hot=True)
### Get a sprite and labels file for the embedding projector ###
urlretrieve(GITHUB_URL + 'labels_1024.tsv', LOGDIR + 'labels_1024.tsv')
urlretrieve(GITHUB_URL + 'sprite_1024.png', LOGDIR + 'sprite_1024.png')

# Add convolution layer
def conv_layer(input, size_in, size_out, name="conv"):
  with tf.name_scope(name):
    #w = tf.Variable(tf.zeros([5, 5, size_in, size_out]), name="W")
    #b = tf.Variable(tf.zeros([size_out]), name="B")
    w = tf.Variable(tf.truncated_normal([4, 4, size_in, size_out], stddev=0.1), name="W")
    b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
    conv = tf.nn.conv2d(input, w, strides=[1, 1, 1, 1], padding="SAME")
    act = tf.nn.relu(conv + b)
    tf.summary.histogram("weights", w)
    tf.summary.histogram("biases", b)
    tf.summary.histogram("activations", act)
    return tf.nn.max_pool(act, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")


# Add fully connected layer
def fc_layer(input, size_in, size_out, name="fc"):
  with tf.name_scope(name):
    w = tf.Variable(tf.truncated_normal([size_in, size_out], stddev=0.1), name="W")
    b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
    act = tf.nn.relu(tf.matmul(input, w) + b)
    tf.summary.histogram("weights", w)
    tf.summary.histogram("biases", b)
    tf.summary.histogram("activations", act)
    return act


def mnist_model(learning_rate, use_two_conv, use_two_fc, hparam):

  tf.reset_default_graph()
  tf.set_random_seed(1)
  sess = tf.Session()

  # Setup placeholders, and reshape the data
  x = tf.placeholder(tf.float32, shape=[None, 256*256], name="x")
  x_image = tf.reshape(x, [-1, 256, 256, 1])
  tf.summary.image('input', x_image, 3)
  y = tf.placeholder(tf.float32, shape=[None, ], name="labels")

  if use_two_conv:
    conv1 = conv_layer(x_image, 1, 32, "conv1")
    conv_out = conv_layer(conv1, 32, 64, "conv2")
  else:
    conv1 = conv_layer(x_image, 1, 64, "conv")
    conv_out = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")

  flattened = tf.reshape(conv_out, [-1, 16 * 16 * 16])


  if use_two_fc:
    fc1 = fc_layer(flattened, 16 * 16 * 16, 40, "fc1")
    embedding_input = fc1
    embedding_size = 40
    logits = fc_layer(fc1, 40, 1, "fc2")
  else:
    embedding_input = flattened
    embedding_size = 7*7*64
    logits = fc_layer(flattened, 7*7*64, 10, "fc")

  with tf.name_scope("xent"):
    xent = tf.reduce_mean(
        tf.nn.softmax_cross_entropy_with_logits(
            logits=logits, labels=y), name="xent")
    tf.summary.scalar("xent", xent)

  with tf.name_scope("train"):
    train_step = tf.train.AdamOptimizer(learning_rate).minimize(xent)

  with tf.name_scope("accuracy"):
    correct_prediction = tf.equal(tf.argmax(logits, -1), tf.argmax(y, -1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    tf.summary.scalar("accuracy", accuracy)

  summ = tf.summary.merge_all()


  embedding = tf.Variable(tf.zeros([1024, embedding_size]), name="test_embedding")
  assignment = embedding.assign(embedding_input)
  saver = tf.train.Saver()

  sess.run(tf.global_variables_initializer())
  writer = tf.summary.FileWriter(LOGDIR + hparam)
  writer.add_graph(sess.graph)

  config = tf.contrib.tensorboard.plugins.projector.ProjectorConfig()
  embedding_config = config.embeddings.add()
  embedding_config.tensor_name = embedding.name
  embedding_config.sprite.image_path = LOGDIR + 'sprite_1024.png'
  embedding_config.metadata_path = LOGDIR + 'labels_1024.tsv'
  # Specify the width and height of a single thumbnail.
  embedding_config.sprite.single_image_dim.extend([256, 256])
  tf.contrib.tensorboard.plugins.projector.visualize_embeddings(writer, config)

  for i in range(300):
    if i % 5 == 0:
      [train_accuracy, s] = sess.run([accuracy, summ], feed_dict={x: train, y: ckp_labels})
      writer.add_summary(s, i)
      print ("train accuracy:", train_accuracy)
    sess.run(train_step, feed_dict={x: train, y: ckp_labels})

def make_hparam_string(learning_rate, use_two_fc, use_two_conv):
  conv_param = "conv2" if use_two_conv else "conv1"
  fc_param = "fc2" if use_two_fc else "fc1"
  return "lr_%.0E%s%s" % (learning_rate, conv_param, fc_param)

def main():
  # You can try adding some more learning rates
  #for learning_rate in [1E-3, 1E-4, 1E-5]:
  for learning_rate in [1E-4]:

    # Include "False" as a value to try different model architectures
    #for use_two_fc in [True, False]:
    for use_two_fc in [True]:
      #for use_two_conv in [True, False]:
      for use_two_conv in [True]:
        # Construct a hyperparameter string for each one (example: "lr_1E-3fc2conv2")
        hparam = make_hparam_string(learning_rate, use_two_fc, use_two_conv)
        print('Starting run for %s' % hparam)
        sys.stdout.flush() # this forces print-ed lines to show up.

        # Actually run with the new settings
        mnist_model(learning_rate, use_two_fc, use_two_conv, hparam)


if __name__ == '__main__':
  main()

下面是我收到的错误：

InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[16960,1] labels_size=[1,265]
     [[Node: xent/SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](xent/Reshape, xent/Reshape_1)]]

---

真正让我困惑的是为什么我的logits形状是[16960,1]。任何帮助都将不胜感激。

首先，y应该是形状（批次大小）：（在您的情况下是（265）；也许它也可以与（265，1）一起工作）

由于y不在一个热编码中，您必须使用

tf.nn.sparse\u softmax\u cross\u entropy\u和\u logits

，而不是

softmax\u cross\u entropy\u和\u logits

然后：在第二个conv层（和最大池数）的末尾，映像大小为（256x256）/2/2=（64,64）。使用64个深度，每个样本可以获得64*64*64个值。但是你可以做

展平=tf.重塑（conv_out，[-1，16*16*16]）

，这给了你一个形状张量

[265*2^6，16*16*16]

（265*2^6=16960，这就是它的来源）。将其替换为

展平=tf.重塑（conv_out，[-1,64*64*64]）

此外，

logits=fc_层（fc1，40，1，“fc2”）

也是一个错误，您应该有

logits=fc_层（fc1，40，num_类，“fc2”）

，并且您似乎有

num_类=8

这些更改应该为您提供形状的logit（265，num\u类），这是您想要的

tf.nn.sparse\u softmax\u cross\u entropy\u with\u logits

---

对于use_two_fc或use_two_conv为false的情况，您还需要进行其他更改，我会让您解决这些问题。你真的应该在每一步对所有张量的形状更加小心，如果有必要，打印它们以检查它们是否真的是你想要的。也许可以使用更多的变量，如num_classes_uu\u batch_size等，以确保事情的连贯性，并使其更具可读性。

嘿，你的评论帮助我解决了最初的问题，我专注于寻找有关如何为CNN设置维度的更多信息。现在，我将conv中的过滤器更改为（17,17），并将展平改为

展平=tf。重塑（conv_out，[-1,55*55*64]）

。我的数学检查出来了，但我得到了以下错误：

InvalidArgumentError（回溯见上文）：重塑的输入是一个值为6553600的张量，但请求的形状需要193600的倍数。但它最终会使用
[-1,64*64*64]
。很抱歉，我不明白你到底改变了什么。如果你吃了你的问题或者用你当前的代码开始一个新的问题，也许会更清楚
y = tf.placeholder(tf.float32, shape=[None], name="labels")