我正在建立一个基于此链接的回归神经网络：intro to RNN in Tensorflow 但是当我尝试运行它时，测试集的精确度保持在19.1％，列车和验证集的准确度相似。
根据我的理解，看起来网络根本没有更新权重和偏差，但我无法理解原因。
这是我正在运行的代码：
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.
cells = []
for _ in range(self._num_layers):
cell = tf.contrib.rnn.GRUCell(self._num_hidden) # Or LSTMCell(num_units)
cell = tf.contrib.rnn.DropoutWrapper(
cell, output_keep_prob=1.0 - self.dropout)
cells.append(cell)
network = tf.contrib.rnn.MultiRNNCell(cells)
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)
batch_size = 5000
epochs = 20
def main():
length = 5
features_size = 55
num_classes = 2
data = tf.placeholder(tf.float32, [None, length, features_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())
graph = []
for epoch in range(epochs):
epoch_loss = 0
i = 0
if epoch % 3 == 0:
random_x = np.random.permutation(train_x)
random_y = np.random.permutation(train_y)
# while i < len(train_x):
while i < 100000:
start = i
end = i + batch_size
batch_x = random_x[start:end]
batch_y = random_y[start:end]
# batch_x = train_x[start:end]
# batch_y = train_y[start:end]
sess.run(model.optimize, {data: batch_x, target: batch_y, dropout: 0.5})
i += batch_size
print('epoch {} completed'.format(epoch + 1))
if epoch % 5 == 0:
train_errors = []
while i < len(train_x):
start = i
end = i + 100000
batch_train_x = train_x[start:end]
batch_train_y = train_y[start:end]
train_errors.append(sess.run(model.error, {data: batch_train_x, target: batch_train_y, dropout: 1}))
i += 100000
train_error = np.mean(train_errors)
test_error = sess.run(model.error, {data: test_x, target: test_y, dropout: 1})
validation_error = sess.run(model.error,
{data: validation_x, target: validation_y, dropout: 1})
print('Epoch {:2d} error {:3.1f}%, loss:'.format(epoch + 1, 100 * test_error), epoch_loss)
print([epoch + 1, train_error, test_error, None, validation_error])
graph.append([epoch + 1, train_error, test_error, None, validation_error])
if __name__ == '__main__':
print('initialising model...')
main()
这是对此链接可用的修改（当我尝试时，它有完全相同的问题）：RNN sequence clasification。这是我运行代码时得到的输出：
epoch 0 completed
Epoch 1 error 19.1%, loss: 0
[1, 0.19120942, 0.19113493, None, 0.18927938]
epoch 1 completed
epoch 2 completed
epoch 3 completed
epoch 4 completed
epoch 5 completed
Epoch 6 error 19.1%, loss: 0
[6, 0.19120942, 0.19113493, None, 0.18927938]
epoch 6 completed
epoch 7 completed
epoch 8 completed
epoch 9 completed
epoch 10 completed
Epoch 11 error 19.1%, loss: 0
[11, 0.19120942, 0.19113493, None, 0.18927938]
epoch 11 completed
epoch 12 completed
epoch 13 completed
epoch 14 completed
epoch 15 completed
Epoch 16 error 19.1%, loss: 0
[16, 0.19120942, 0.19113493, None, 0.18927938]
epoch 16 completed
epoch 17 completed
epoch 18 completed
epoch 19 completed
这个问题的原因是什么？