tensorflow错误“引发ValueError(”形状%s和%s不兼容“%(self,other))ValueError:形状(?,5)和(5,)不兼容”

时间:2017-11-25 02:20:33

标签: tensorflow

我尝试使用tensorflow 1.4.0对原始记录进行分类。 这个过程如下。

拳头:读取图像和标签,并将“tfrecord”格式输出到文件中。 第二:阅读记录和培训

写tfrecord脚本是

!/usr/bin/env python3
#coding:utf-8

import argparse
import os
import random

import numpy as np
from PIL import Image
import tensorflow as tf

def make_example(label_index, image):
    return tf.train.Example(features = tf.train.Features(feature={
        'label_index': tf.train.Feature(int64_list=tf.train.Int64List(value=[label_index])),
        'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image]))
        }))

def write_tfrecord(dataset, outputfilepath):
    writer = tf.python_io.TFRecordWriter(outputfilepath)
    for label_of_one_hot, image in dataset:
        ex = make_example(label_of_one_hot, image)
        writer.write(ex.SerializeToString())
    writer.close()

def importingargs():
    parser = argparse.ArgumentParser("tensorflow exampe")
    parser.add_argument("--datafolderpath", "-df", help="datafolderpath")
    parser.add_argument("--filepath", "-f", help="filepath", required=True)
    parser.add_argument("--labelfilepath", "-lf", help="label filepath")
    parser.add_argument("--outputfolderpath", "-of", help="outputfolderpath of tf records")
    parser.add_argument("--seed", "-s", type=int, required=False, default=0)
    args = parser.parse_args()

    return args.filepath, args.datafolderpath, args.labelfilepath, args.outputfolderpath, args.seed


def load_data(filepath, datafolderpath, labelfilepath):
    with open(labelfilepath, "r") as rf:
        labellist = [ line.strip() for line in rf.readlines() ]

    with open(filepath,  "r") as rf:
        filepathlist = [ line.strip() for line in rf.readlines() ]


    alldatasets = list()
    for filepath in filepathlist:
        imagefilepath = os.path.join(datafolderpath, filepath)
        # image = open(imagefilepath).read()
        img_obj = Image.open(imagefilepath).convert("L")
        img = np.array(img_obj)
        w, h = img.shape
        print(w, h)
        print(w*h)
        img = img.reshape(w*h).tostring()
        print(type(img))
        filename = filepath.split(os.path.sep)[-1]
        label = filename.split(".")[0].split("_")[1]
        index = labellist.index(label) +1
        print(index)
        alldatasets.append([ index, img ])
    return alldatasets

def splitdata(datasets):
    random.shuffle(datasets)
    train_indexes = [ 0, int(len(datasets) * 0.8 ) ]
    valid_indexes = [ train_indexes[-1], int(len(datasets) * 0.9 ) ]
    test_indexes = [ valid_indexes[-1], int(len(datasets)) ]

    train_data = datasets[train_indexes[0]:train_indexes[1]]
    valid_data = datasets[valid_indexes[0]:valid_indexes[1]]
    test_data = datasets[test_indexes[0]:test_indexes[1]]

    print("train num: %d" % len(train_data))
    print("test  num: %d" % len(test_data))
    print("valid num: %d" % len(valid_data))

    return train_data, valid_data, test_data

def main():
    filepath, datafolderpath, labelfilepath, outputfolderpath, seed = importingargs()
    random.seed(seed)
    alldatasets = load_data(filepath, datafolderpath, labelfilepath)
    train_data, valid_data, test_data = splitdata(alldatasets)
    train_outputfilepath = os.path.join(outputfolderpath, "train.tfrecord")
    valid_outputfilepath = os.path.join(outputfolderpath, "valid.tfrecord")
    test_outptufilepath = os.path.join(outputfolderpath, "test.tfrecord")

    write_tfrecord(train_data, train_outputfilepath)
    write_tfrecord(valid_data, valid_outputfilepath)
    write_tfrecord(test_data, test_outptufilepath)

if __name__ == "__main__":
    main()

load_dataset文件导入train.py

#!/usr/bin/env python3
#coding:utf-8

import argparse
import os

import numpy as np
from PIL import Image
import tensorflow as tf

def read_tfrecord(inputfilepath):
    print("read record")
    reader = tf.TFRecordReader()
    filename_que = tf.train.string_input_producer([inputfilepath])
    key, value = reader.read(filename_que)
    features  = tf.parse_single_example(value,features = {
            'label_index': tf.FixedLenFeature([], tf.string),
            'image': tf.FixedLenFeature([], tf.string)
            })

    images = tf.decode_raw(features['image'], tf.float32)
    images.set_shape([32*32])
    images = tf.cast(images, tf.float32) * (1. / 255)
    # images = tf.reshape(images, [-1])
    labels = tf.decode_raw(features['label_index'], tf.int32)
    # labels = tf.cast(features['label_index'], tf.int64)
    # labels.set_shape([5])
    print("call one hot")
    label_index_one_hot = tf.one_hot(labels, 5)
    label_index_one_hot.set_shape([5])
    return images, label_index_one_hot

培训脚本

import os
import random

import tensorflow as tf

import load_datasets
import datasets
import make_datasets

print("def input and output")
images = tf.placeholder(tf.float32, shape=[None, 32*32])
labels = tf.placeholder(tf.int32, shape=[None, 5])


print("def layers")
x = tf.placeholder(tf.float32, [ None, 32*32 ])
y_ = tf.placeholder(tf.float32, [None, 5 ])

# W1 = tf.Variable(tf.zeros([ 32*32, 500 ]))
# b1 = tf.Variable(tf.zeros([ 500 ]))

# W2 = tf.Variable(tf.zeros([ 500, 5 ]))
# b2 = tf.Variable(tf.zeros([ 5 ]))

print("def function")
# h1 = tf.matmul(x, W1) + b1
# y = tf.matmul(h1, W2) + b2

W = tf.Variable(tf.zeros([ 32*32, 5 ]))
b = tf.Variable(tf.zeros([ 5 ]))
y = tf.matmul(x, W) + b

print("def leraning model")
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y))
train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)

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


print("load train dataset")
trainfilepath = "../03tfrecords/train.tfrecord"
images, labels = load_datasets.read_tfrecord(trainfilepath)
input_queue = tf.train.slice_input_producer( [images, labels ], num_epochs=10, shuffle=False )
image_batch, label_batch = tf.train.batch( [images, labels], batch_size=10)

print("load test dataset")
testfilepath = "../03tfrecords/test.tfrecord"
test_image, test_label = load_datasets.read_tfrecord(testfilepath)
img_test_batch, label_test_batch = tf.train.batch([test_image,test_label],batch_size=16)

with tf.Session() as sess:
    print("init layer value")
    sess.run(tf.global_variables_initializer())
    print("start training")
    tf.train.start_queue_runners(sess)
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(sess=sess, coord=coord)
    try:
        while not coord.should_stop():
            for i in range(0, 10):
                print("train num %d" % (i+1))
                imgs, labels = sess.run([image_batch, label_batch])
                sess.run(train_step, feed_dict={x:imgs, y_: labels})

                imgs_test, labels_text = sess.run([img_test_batch, label_test_batch])
                print(sess.run(accuracy, feed_dict={x:imgs_test, y_:labels_text}))


    finally:
        coord.request_stop()
        coord.join(threads)

制作tfrecords效果很好,但在训练脚本中,会发生错误。

Traceback (most recent call last):
  File "/home/omori/.pyenv/versions/tensorflow-py3/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 576, in merge_with
    self.assert_same_rank(other)
  File "/home/omori/.pyenv/versions/tensorflow-py3/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 621, in assert_same_rank
    other))
ValueError: Shapes (?, 5) and (5,) must have the same rank

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "train.py", line 45, in <module>
    images, labels = load_datasets.read_tfrecord(trainfilepath)
  File "/home/omori/tensorflow_example/01src/load_datasets.py", line 30, in read_tfrecord
    label_index_one_hot.set_shape([5])
  File "/home/omori/.pyenv/versions/tensorflow-py3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 407, in set_shape
    self._shape = self._shape.merge_with(shape)
  File "/home/omori/.pyenv/versions/tensorflow-py3/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py", line 582, in merge_with
    raise ValueError("Shapes %s and %s are not compatible" % (self, other))
ValueError: Shapes (?, 5) and (5,) are not compatible

我搜索了很多网站,但我无法得到解决方案。 我怎么解决呢?

1 个答案:

答案 0 :(得分:0)

decode_raw

Returns:

A Tensor of type out_type. A Tensor with one more dimension than the input bytes. The added 
dimension will have size equal to the length of the elements of bytes divided by the number 
of bytes to represent out_type.

所以在你的read_tfrecord函数中

labels = tf.decode_raw(features['label_index'], tf.int32)

labels一个超额维度。您可以使用

解决此问题
label_index_one_hot = tf.one_hot(labels[0], 5)

(请注意添加的[0]

我必须承认,我不明白添加的维度是什么。