训练时的ValueError Tensorflow：设置序列的数组元素

Question

我被ValueError困在训练过程中。 以下是详细信息：

我做了如下标志。如下面

flags = tf.app.flags 
FLAGS = flags.FLAGS 

flags.DEFINE_string('train', 'train.txt', 'File name of train data') 
flags.DEFINE_string('test', 'test.txt', 'File name of train data') 
flags.DEFINE_string('train_dir', '/tmp/data', 'Directory to put the training data.') 
flags.DEFINE_integer('max_steps', 200, 'Number of steps to run trainer.') 
flags.DEFINE_integer('batch_size', 10, 'Batch size' 
        'Must divide evenly into the dataset sizes.') 
flags.DEFINE_float('learning_rate', 1e-4, 'Initial learning rate.') 

此外训练过程：

if 1==1: 
     # Tensor for images 
    images_placeholder = tf.placeholder("float", shape=(None, IMAGE_PIXELS)) 
     # Tensor for labels 
     labels_placeholder = tf.placeholder("float", shape=(None, NUM_CLASSES)) 
     # dropout rate 
     keep_prob = tf.placeholder("float") 

     # call inference() 
     logits = inference(images_placeholder, keep_prob) 
     # call loss() 
     loss_value = loss(logits, labels_placeholder) 
     # call training() 
     train_op = training(loss_value, FLAGS.learning_rate) 
     # calculate accuract 
     acc = accuracy(logits, labels_placeholder) 

     # prepare for saving 
     saver = tf.train.Saver() 
     # make Session 
     sess = tf.Session() 
     # initialize variables 
     sess.run(tf.initialize_all_variables()) 
     # values on TensorBoard 
     summary_op = tf.merge_all_summaries() 
     summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph_def) 

     # Training process 
     for step in range(FLAGS.max_steps): 
      for i in range(len(train_image)/FLAGS.batch_size): 
       # batch_size 
       batch = FLAGS.batch_size*i 
       # define data in placeholder by feed dict 
       sess.run(train_op, feed_dict={ 
       images_placeholder:train_image[batch:batch+FLAGS.batch_size], 
     labels_placeholder: train_label[batch:batch+FLAGS.batch_size], 
       keep_prob: 0.5}) 

当运行此代码我面临下面的错误。如何解决这个问题呢？

File "CNN_model.py", line 230, in <module> 
    images_placeholder: train_image[batch:batch+FLAGS.batch_size],labels_placeholder: train_label[batch:batch+FLAGS.batch_size],keep_prob: 0.5}) 
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 334, in run 
    np_val = np.array(subfeed_val, dtype=subfeed_t.dtype.as_numpy_dtype) 
ValueError: setting an array element with a sequence. 

---

我添加代码周围train_image和train_label如下。

NUM_CLASSES = 5 
IMAGE_SIZE = 599 
IMAGE_PIXELS = IMAGE_SIZE*1*128 

f = open("song_features.json") 
data = json.load(f) 
data = np.array(data) 

flatten_data = [] 
flatten_label = [] 


for line in range(len(data)): 
    for_flat = np.array(data[line]) 
    flatten_data.append(for_flat.flatten().tolist()) 

    #label made as 1-of-K 
    tmp = np.zeros(NUM_CLASSES) 
    tmp[int(random.randint(0,4))] = 1 
     flatten_label.append(tmp) 

    #1 line training data 
    train_image = np.asarray(flatten_data) 
    train_label = np.asarray(flatten_label) 

我构建这个模型。

Answer 1

时TensorFlow在feed_dict的值转换成致密NumPy的ndarrays这引发异常，并且将依靠什么在你train_image和train_label对象。

这些错误的常见原因是当Feed值为衣衫褴褛的列表：即列表的列表，其中列表具有不同的尺寸。例如：

>>> train_image = [[1., 2., 3.], [4., 5.]] 
>>> np.array(train_image, dtype=np.float32) 
Traceback (most recent call last): 
    File "<stdin>", line 1, in <module> 
ValueError: setting an array element with a sequence. 

---

编辑：感谢您分享代码来构建train_image和train_label。我怀疑问题在于train_image的创建，如果flatten_data的元素对于每个示例可以具有不同的长度。尝试进行以下修改以确认此：train_image = np.asarray(flatten_data, dtype=np.float32)。如果您获得相同的ValueError，则需要填充或裁剪各个行，以便它们具有IMAGE_PIXELS元素。