我为TensorFlow序列分类获得了以下代码（请参阅此问题末尾的代码）：
https://gist.github.com/danijar/c7ec9a30052127c7a1ad169eeb83f159
我需要修改代码来解决我的二进制序列分类问题。
我的训练输入是一个csv文件（非常大），csv文件的格式是：
binary_sequence(fixed sequence length of 100),result
1>0>1>1>0>0>0>0>...>0,1
0>1>0>1>0>0>0>0>...>0,0
...
0>1>0>1>0>0>0>0>...>0,0
我需要训练一个分类器来分类新的binary_sequences。
我的测试输入也是类似格式的csv文件。
非常感谢能为我的问题修改以下代码提出建议的任何人！
# Example for my blog post at:
# https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/
import functools
import sets
import tensorflow as tf
def lazy_property(function):
attribute = '_' + function.__name__
@property
@functools.wraps(function)
def wrapper(self):
if not hasattr(self, attribute):
setattr(self, attribute, function(self))
return getattr(self, attribute)
return wrapper
class SequenceClassification:
def __init__(self, data, target, dropout, num_hidden=200, num_layers=3):
self.data = data
self.target = target
self.dropout = dropout
self._num_hidden = num_hidden
self._num_layers = num_layers
self.prediction
self.error
self.optimize
@lazy_property
def prediction(self):
# Recurrent network.
network = tf.contrib.rnn.GRUCell(self._num_hidden)
network = tf.contrib.rnn.DropoutWrapper(
network, output_keep_prob=self.dropout)
network = tf.contrib.rnn.MultiRNNCell([network] * self._num_layers)
output, _ = tf.nn.dynamic_rnn(network, self.data, dtype=tf.float32)
# Select last output.
output = tf.transpose(output, [1, 0, 2])
last = tf.gather(output, int(output.get_shape()[0]) - 1)
# Softmax layer.
weight, bias = self._weight_and_bias(
self._num_hidden, int(self.target.get_shape()[1]))
prediction = tf.nn.softmax(tf.matmul(last, weight) + bias)
return prediction
@lazy_property
def cost(self):
cross_entropy = -tf.reduce_sum(self.target * tf.log(self.prediction))
return cross_entropy
@lazy_property
def optimize(self):
learning_rate = 0.003
optimizer = tf.train.RMSPropOptimizer(learning_rate)
return optimizer.minimize(self.cost)
@lazy_property
def error(self):
mistakes = tf.not_equal(
tf.argmax(self.target, 1), tf.argmax(self.prediction, 1))
return tf.reduce_mean(tf.cast(mistakes, tf.float32))
@staticmethod
def _weight_and_bias(in_size, out_size):
weight = tf.truncated_normal([in_size, out_size], stddev=0.01)
bias = tf.constant(0.1, shape=[out_size])
return tf.Variable(weight), tf.Variable(bias)
def main():
# We treat images as sequences of pixel rows.
train, test = sets.Mnist()
_, rows, row_size = train.data.shape
num_classes = train.target.shape[1]
data = tf.placeholder(tf.float32, [None, rows, row_size])
target = tf.placeholder(tf.float32, [None, num_classes])
dropout = tf.placeholder(tf.float32)
model = SequenceClassification(data, target, dropout)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for epoch in range(10):
for _ in range(100):
batch = train.sample(10)
sess.run(model.optimize, {
data: batch.data, target: batch.target, dropout: 0.5})
error = sess.run(model.error, {
data: test.data, target: test.target, dropout: 1})
print('Epoch {:2d} error {:3.1f}%'.format(epoch + 1, 100 * error))
if __name__ == '__main__':
main()