我将数据保存到tfrecord文件中。它有1000个样本和2个特征（一个输入另一个输出）。输入是形状[1,20]和输出[1,10]。它们都是由扁平的numpy数组创建的。我正在尝试从他们创建批次，所以我可以使用它们来训练我的网络，但我无法弄清楚如何。
这是我培训网络的代码
learning_rate = 0.01
epochs = 2
batch_size = 200 #total 5 batches
dataSize = 1000
dataset = rd.getData()
x = tf.placeholder(shape=(None,20), dtype=tf.float32)
y = tf.placeholder(shape=(None,10), dtype=tf.float32)
w1 = tf.Variable(tf.random_normal([20, 20], stddev=0.03))
w2 = tf.Variable(tf.random_normal([20, 20], stddev=0.03))
w3 = tf.Variable(tf.random_normal([20, 20], stddev=0.03))
w4 = tf.Variable(tf.random_normal([20, 20], stddev=0.03))
w5 = tf.Variable(tf.random_normal([20, 10], stddev=0.03))
b1 = tf.Variable(tf.random_normal([20]))
b2 = tf.Variable(tf.random_normal([20]))
b3 = tf.Variable(tf.random_normal([20]))
b4 = tf.Variable(tf.random_normal([20]))
b5 = tf.Variable(tf.random_normal([10]))
out1 = tf.add(tf.matmul(x, w1), b1)
out1 = tf.tanh(out1)
out2 = tf.add(tf.matmul(out1, w2), b2)
out2 = tf.tanh(out2)
out3 = tf.add(tf.matmul(out2, w3), b3)
out3 = tf.tanh(out3)
out4 = tf.add(tf.matmul(out3, w4), b4)
out4 = tf.tanh(out4)
out5 = tf.add(tf.matmul(out4, w5), b5)
finalOut = tf.tanh(out5)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=finalOut))
optimiser = tf.train.RMSPropOptimizer(learning_rate=learning_rate).minimize(cost)
# finally setup the initialisation operator
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
# initialise the variables
sess.run(init_op)
total_batch = int(dataSize / batch_size)
for epoch in range(epochs):
iterator = dataset.make_one_shot_iterator()
avg_cost = 0
for i in range(total_batch):
#create batch
batch_y = []
batch_x = []
for counter in range(0,batch_size):
uv, z = iterator.get_next()
batch_x.append(uv)
batch_y.append(z)
_, c = sess.run([optimiser, cost],
feed_dict={x: batch_x, y: batch_y})
avg_cost += c / total_batch
print("Epoch:", (epoch + 1), "cost =", "{:.3f}".format(avg_cost))
这是我从中获取数据的文件。
def decode(serialized_example):
features = tf.parse_single_example(
serialized_example,
features={'uv': tf.FixedLenFeature([1,20], tf.float32),
'z': tf.FixedLenFeature([1,10], tf.float32)})
return features['uv'], features['z']
def getData():
filename = ["train.tfrecords"]
dataset = tf.data.TFRecordDataset(filename).map(decode)
return dataset
错误：
Traceback (most recent call last):
File "network.py", line 102, in <module>
feed_dict={x: batch_x, y: batch_y})
File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py", line 889, in run
run_metadata_ptr)
File "C:\Users\User\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\client\session.py", line 1089, in _run
np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
File "C:\Users\User\AppData\Roaming\Python\Python36\site-packages\numpy\core\numeric.py", line 531, in asarray
return array(a, dtype, copy=False, order=order)
ValueError: setting an array element with a sequence.
在看了其他问题之后，我想也许我的批次应该是ndarray还是什么？但我无法弄清楚如何将我的数据集导入该表单。我甚至无法在没有迭代器的情况下使用我的数据。任何指导都会很棒！谢谢
请尝试以下操作，看看是否有帮助。
tf.parse_single_example没有收到批量维度。从而，
features = tf.parse_single_example(
serialized_example,
features={'uv': tf.FixedLenFeature([20], tf.float32),
'z': tf.FixedLenFeature([10], tf.float32)})
print(sess.run(next_element))运行3次，但next_element只宣布一次。同样，在您的代码中，不需要在for循环下运行dataset.make_one_shot_iterator()和iterator.get_next()。数据集声明可以放在getData()的最开头或内部，以便于理解。# read file
dataset = tf.data.TFRecordDataset(filename)
# parse each instance
dataset = dataset.map(your_parser_fun, num_parallel_calls=num_threads)
# preprocessing, e.g. scale to range [0, 1]
dataset = dataset.map(some_preprocessing_fun)
# shuffle
dataset = dataset.shuffle(buffer_size)
# form batch and epoch
dataset = dataset.batch(batch_size)
dataset = dataset.repeat(num_epoch)
iterator = dataset.make_one_shot_iterator()
# get a batch
x_batch, y_batch = self.iterator.get_next()
# do calculations
...