tensorflow logits 和标签必须相同大小

Question

我对 tensorflow 和 python 还很陌生，目前正在尝试修改 MNIST 以获取 240x320x3 图像的专家教程。我有 2 个 .py 脚本

tfrecord_rereader.py

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

data_path = 'train.tfrecords'  # address to save the hdf5 file

def read_data():
    with tf.Session() as sess:
        feature = {'train/image': tf.FixedLenFeature([], tf.string),
                   'train/label': tf.FixedLenFeature([], tf.int64)}

        # Create a list of filenames and pass it to a queue
        filename_queue = tf.train.string_input_producer([data_path], num_epochs=1)

        # Define a reader and read the next record
        reader = tf.TFRecordReader()
        _, serialized_example = reader.read(filename_queue)

        # Decode the record read by the reader
        features = tf.parse_single_example(serialized_example, features=feature)

        # Convert the image data from string back to the numbers
        image = tf.decode_raw(features['train/image'], tf.float32)

        # Cast label data into int32
        label = tf.cast(features['train/label'], tf.int32)

        # Reshape image data into the original shape
        image = tf.reshape(image, [240, 320, 3])

    sess.close()
    return image, label

def next_batch(image, label, batchSize):
    imageBatch, labelBatch = tf.train.shuffle_batch([image, label], batch_size=batchSize, capacity=30, num_threads=1,
                                            min_after_dequeue=10)
    return imageBatch, labelBatch

train.py

import tensorflow as tf
from random import shuffle
import glob
import sys
#import cv2
from tfrecord_reader import read_data, next_batch
import argparse # For passing arguments
import numpy as np
import math
import time

IMAGE_WIDTH = 240
IMAGE_HEIGHT = 320
IMAGE_DEPTH = 3
IMAGE_SIZE = 240*320*3
NUM_CLASSES = 5
BATCH_SIZE = 50

# Creates a weight tensor sized by shape
def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

# Creates a bias tensor sized by shape
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')

def main(argv):
    # Perform training
    x = tf.placeholder(tf.float32, [None, IMAGE_SIZE])    # 240*320=76800
    W = tf.Variable(tf.zeros([IMAGE_SIZE, NUM_CLASSES]))
    b = tf.Variable(tf.zeros([NUM_CLASSES]))
    y = tf.matmul(x, W) + b

    # Define loss and optimizer
    y_ = tf.placeholder(tf.float32, [None, NUM_CLASSES])  # Desired output

    # First convolutional layer
    W_conv1 = weight_variable([5, 5, IMAGE_DEPTH, 32])
    b_conv1 = bias_variable([32])

    x_image = tf.reshape(x, [-1, IMAGE_WIDTH, IMAGE_HEIGHT, IMAGE_DEPTH])

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

    # Second convolutional layer
    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)

    # First fully connected layer
    W_fc1 = weight_variable([60 * 80 * 64, 1024])
    b_fc1 = bias_variable([1024])

    # Flatten the layer
    h_pool2_flat = tf.reshape(h_pool2, [-1, 60 * 80 * 64])
    h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

    # Drop out layer
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    # Second fully connected layer
    W_fc2 = weight_variable([1024, NUM_CLASSES])
    b_fc2 = bias_variable([NUM_CLASSES])

    # Output layer
    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
    # print(y_conv.shape)
    # print(y_conv.get_shape)

    # Get the loss
    cross_entropy = tf.reduce_mean(
        tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))

    # Minimize the loss
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

    # Read all data from tfrecord file
    imageList, labelList = read_data()
    imageBatch, labelBatch = next_batch(imageList, labelList, BATCH_SIZE)

    correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    with tf.Session() as sess:
        sess.run(tf.local_variables_initializer())
        sess.run(tf.global_variables_initializer())

        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(coord=coord)

        train_images, train_labels = sess.run([imageBatch, labelBatch])
        train_images = np.reshape(train_images, (-1, IMAGE_SIZE))
        train_labels = np.reshape(train_labels, (-1, NUM_CLASSES))

        sess.run(train_step, feed_dict = {x: train_images, y_: train_labels, keep_prob: 1.0})

        coord.request_stop()
        coord.join(threads)
    sess.close()

if __name__ == '__main__':
  parser = argparse.ArgumentParser()
  FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

当我运行程序时，我得到了

InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[50,5] labels_size=[10,5]
     [[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](Reshape_2, Reshape_3)]]

我已经对这个问题进行了几个小时的搜索，但看不出为什么 logits 与标签大小不匹配。如果我将批量大小更改为 10，标签大小将变为 [2,5]，就好像它总是被 5 整除一样。有人可以帮我吗？

Answer 1

您的标签很可能是单个整数值而不是单热向量，因此您的 labelBatch 是一个大小为 [50] 的向量，其中包含单个数字，例如“1”或“4”。现在，当您使用 train_labels = np.reshape(train_labels, (-1, NUM_CLASSES)) 重塑它们时 您正在将形状更改为 [10, 5]。

tf.nn.softmax_cross_entropy_with_logits 函数期望标签是标签的“单热”编码（这意味着 3 的标签转换为大小为 5 的向量，位置 3 为 1，其他位置为 0）。您可以使用tf.nn.one_hot 函数实现此目的，但更简单的方法是使用设计用于处理这些单值标签的tf.nn.sparse_softmax_cross_entropy_with_logits 函数。为此，您需要更改以下行：

y_ = tf.placeholder(tf.float32, [None]) # Desired output

cross_entropy = tf.reduce_mean( tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))

并摆脱train_labels = np.reshape(train_labels, (-1, NUM_CLASSES)) 行。

（顺便说一句，这种方式读取数据时实际上不需要使用占位符——直接使用输出张量即可。）