我正在尝试在一个长时间序列中检测微事件。为此，我将训练一个LSTM网络。
数据。 每个时间样本的输入是11个不同的特征，这些特征经过某种程度的归一化以适应0-1范围。输出将是两个类别之一。
批处理。 由于存在巨大的类别不平衡，我将数据提取为每批60个时间样本，其中至少有5个始终属于类别1，其余属于类别2。这样，类别不平衡从150:1减少到约12:1。然后，我随机化了所有批次的顺序。
模型。 我尝试训练一个LSTM，初始配置为3个不同的单元和5个延迟步骤。我期望微事件至少在3个时间步长的序列中出现。
问题： 当我尝试训练网络时，它会很快收敛到认为所有样本都属于多数类。当我实现加权损失函数时，在某个阈值处，它会转而认为所有样本都属于少数类。我怀疑（尽管不是专家）我的LSTM单元没有学习，或者我的配置有问题？
以下是我实现的代码。我希望有人能告诉我
- 我的实现是否正确？
- 导致这种行为的其他可能原因是什么？
ar_model.py
import numpy as npimport tensorflow as tffrom tensorflow.models.rnn import rnnimport ar_configconfig = ar_config.get_config()class ARModel(object): def __init__(self, is_training=False, config=None): # Config if config is None: config = ar_config.get_config() # Placeholders self._features = tf.placeholder(tf.float32, [None, config.num_features], name='ModelInput') self._targets = tf.placeholder(tf.float32, [None, config.num_classes], name='ModelOutput') # Hidden layer with tf.variable_scope('lstm') as scope: lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(config.num_hidden, forget_bias=0.0) cell = tf.nn.rnn_cell.MultiRNNCell([lstm_cell] * config.num_delays) self._initial_state = cell.zero_state(config.batch_size, dtype=tf.float32) outputs, state = rnn.rnn(cell, [self._features], dtype=tf.float32) # Output layer output = outputs[-1] softmax_w = tf.get_variable('softmax_w', [config.num_hidden, config.num_classes], tf.float32) softmax_b = tf.get_variable('softmax_b', [config.num_classes], tf.float32) logits = tf.matmul(output, softmax_w) + softmax_b # Evaluate ratio = (60.00 / 5.00) class_weights = tf.constant([ratio, 1 - ratio]) weighted_logits = tf.mul(logits, class_weights) loss = tf.nn.softmax_cross_entropy_with_logits(weighted_logits, self._targets) self._cost = cost = tf.reduce_mean(loss) self._predict = tf.argmax(tf.nn.softmax(logits), 1) self._correct = tf.equal(tf.argmax(logits, 1), tf.argmax(self._targets, 1)) self._accuracy = tf.reduce_mean(tf.cast(self._correct, tf.float32)) self._final_state = state if not is_training: return # Optimize optimizer = tf.train.AdamOptimizer() self._train_op = optimizer.minimize(cost) @property def features(self): return self._features @property def targets(self): return self._targets @property def cost(self): return self._cost @property def accuracy(self): return self._accuracy @property def train_op(self): return self._train_op @property def predict(self): return self._predict @property def initial_state(self): return self._initial_state @property def final_state(self): return self._final_statear_train.py
import osfrom datetime import datetimeimport numpy as npimport tensorflow as tffrom tensorflow.python.platform import gfileimport ar_networkimport ar_configimport ar_readerconfig = ar_config.get_config()def main(argv=None): if gfile.Exists(config.train_dir): gfile.DeleteRecursively(config.train_dir) gfile.MakeDirs(config.train_dir) train()def train(): train_data = ar_reader.ArousalData(config.train_data, num_steps=config.max_steps) test_data = ar_reader.ArousalData(config.test_data, num_steps=config.max_steps) with tf.Graph().as_default(), tf.Session() as session, tf.device('/cpu:0'): initializer = tf.random_uniform_initializer(minval=-0.1, maxval=0.1) with tf.variable_scope('model', reuse=False, initializer=initializer): m = ar_network.ARModel(is_training=True) s = tf.train.Saver(tf.all_variables()) tf.initialize_all_variables().run() for batch_input, batch_target in train_data: step = train_data.iter_steps dict = { m.features: batch_input, m.targets: batch_target } session.run(m.train_op, feed_dict=dict) state, cost, accuracy = session.run([m.final_state, m.cost, m.accuracy], feed_dict=dict) if not step % 10: test_input, test_target = test_data.next() test_accuracy = session.run(m.accuracy, feed_dict={ m.features: test_input, m.targets: test_target }) now = datetime.now().time() print ('%s | Iter %4d | Loss= %.5f | Train= %.5f | Test= %.3f' % (now, step, cost, accuracy, test_accuracy)) if not step % 1000: destination = os.path.join(config.train_dir, 'ar_model.ckpt') s.save(session, destination)if __name__ == '__main__': tf.app.run()ar_config.py
class Config(object): # Directories train_dir = '...' ckpt_dir = '...' train_data = '...' test_data = '...' # Data num_features = 13 num_classes = 2 batch_size = 60 # Model num_hidden = 3 num_delays = 5 # Training max_steps = 100000def get_config(): return Config()更新后的架构：
# Placeholdersself._features = tf.placeholder(tf.float32, [None, config.num_features, config.num_delays], name='ModelInput')self._targets = tf.placeholder(tf.float32, [None, config.num_output], name='ModelOutput')# Weightsweights = { 'hidden': tf.get_variable('w_hidden', [config.num_features, config.num_hidden], tf.float32), 'out': tf.get_variable('w_out', [config.num_hidden, config.num_classes], tf.float32)}biases = { 'hidden': tf.get_variable('b_hidden', [config.num_hidden], tf.float32), 'out': tf.get_variable('b_out', [config.num_classes], tf.float32)}#Layer inwith tf.variable_scope('input_hidden') as scope: inputs = self._features inputs = tf.transpose(inputs, perm=[2, 0, 1]) # (BatchSize,NumFeatures,TimeSteps) -> (TimeSteps,BatchSize,NumFeatures) inputs = tf.reshape(inputs, shape=[-1, config.num_features]) # (TimeSteps,BatchSize,NumFeatures -> (TimeSteps*BatchSize,NumFeatures) inputs = tf.add(tf.matmul(inputs, weights['hidden']), biases['hidden'])#Layer hiddenwith tf.variable_scope('hidden_hidden') as scope: inputs = tf.split(0, config.num_delays, inputs) # -> n_steps * (batchsize, features) cell = tf.nn.rnn_cell.BasicLSTMCell(config.num_hidden, forget_bias=0.0) self._initial_state = cell.zero_state(config.batch_size, dtype=tf.float32) outputs, state = rnn.rnn(cell, inputs, dtype=tf.float32)#Layer outwith tf.variable_scope('hidden_output') as scope: output = outputs[-1] logits = tf.add(tf.matmul(output, weights['out']), biases['out'])回答：
