验证和培训期间TensorFlow中的批量标准化
我认为在使用批量标准化进行验证时，我犯了一些错误。这是因为验证损失不会减少，验证错误总是1.0
我非常感谢能帮助你做好准备。
我的TensorFlow模型声明如下
import tensorflow as tf
class OverFeatAccurateBase(object):
def __init__(self, minibatch, numclasses):
self._numclasses = numclasses
self._trainmode = tf.placeholder(tf.bool)
self._logits = self._buildmodel(minibatch)
@property
def numclasses(self):
return self._numclasses
@property
def mode(self):
return self._trainmode
@property
def logits(self):
return self._logits
def _bn(self, input, is_training, name):
out = tf.layers.batch_normalization(input, fused=True, renorm=True, training=is_training,
reuse=tf.AUTO_REUSE,
name=name)
return out
def _buildmodel(self, minibatch):
out = tf.layers.conv2d(minibatch, filters=96,
kernel_size=[7, 7],
strides=[2, 2],
padding='valid',
data_format='channels_first',
activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='conv1')
out = tf.layers.batch_normalization(out, axis=1, renorm=True, fused=True, name='batchnorm1', training=self.mode)
out = tf.layers.max_pooling2d(out, pool_size=[3, 3],
strides=[3, 3],
padding='valid',
data_format='channels_first',
name='pool1')
out = tf.layers.conv2d(out, filters=256,
kernel_size=[7, 7],
strides=[1, 1],
padding='valid',
data_format='channels_first',
activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='conv2')
out = tf.layers.batch_normalization(out, axis=1, renorm=True, fused=True, name='batchnorm2', training=self.mode)
out = tf.layers.max_pooling2d(out, pool_size=[2, 2],
strides=[2, 2],
padding='valid',
data_format='channels_first',
name='pool2')
out = tf.layers.conv2d(out, filters=512,
kernel_size=[3, 3],
strides=[1, 1],
padding='same',
data_format='channels_first',
activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='conv3')
out = tf.layers.batch_normalization(out, axis=1, renorm=True, fused=True, name='batchnorm3', training=self.mode)
out = tf.layers.conv2d(out, filters=512,
kernel_size=[3, 3],
strides=[1, 1],
padding='same',
data_format='channels_first',
activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='conv4')
out = tf.layers.batch_normalization(out, axis=1, renorm=True, fused=True, name='batchnorm4', training=self.mode)
out = tf.layers.conv2d(out, filters=1024,
kernel_size=[3, 3],
strides=[1, 1],
padding='same',
data_format='channels_first',
activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='conv5')
out = tf.layers.batch_normalization(out, axis=1, renorm=True, fused=True, name='batchnorm5', training=self.mode)
out = tf.layers.conv2d(out, filters=1024,
kernel_size=[3, 3],
strides=[1, 1],
padding='same',
data_format='channels_first',
activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='conv6')
out = tf.layers.batch_normalization(out, axis=1, renorm=True, fused=True, name='batchnorm6', training=self.mode)
out = tf.layers.max_pooling2d(out, pool_size=[3, 3],
strides=[3, 3],
padding='valid',
data_format='channels_first',
name='pool3')
out = tf.layers.flatten(out, name='flatten')
out = tf.layers.dense(out, units=4096, activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='full1'
)
out = tf.layers.batch_normalization(out, axis=-1, renorm=True, fused=True, name='batchnorm7', training=self.mode)
out = tf.layers.dense(out, units=4096, activation=tf.nn.relu,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
kernel_regularizer=tf.contrib.layers.l2_regularizer(
scale=0.00001),
reuse=tf.AUTO_REUSE,
name='full2'
)
out = tf.layers.batch_normalization(out, axis=-1, renorm=True, fused=True, name='batchnorm8', training=self.mode)
logits = tf.layers.dense(out, units=self.numclasses,
kernel_initializer=tf.initializers.random_normal(
stddev=0.01,
seed=0),
bias_initializer=tf.initializers.constant(0),
reuse=tf.AUTO_REUSE,
name='output'
)
return logits
为了执行图表，我执行以下操作（查看完整代码，go here）
有效
[loss, top1, top5, epoch, summaries_val,
top1_update, top5_update], feed_dict={net.mode: False, netmode: False})
训练
_, loss_value, top1_err, top5_err, eph, summaries, _, _, _ = sess.run(
[update_ops, loss, top1, top5, epoch, summaries_train, train_op,
top1_update,
top5_update], feed_dict={net.mode: True, netmode: True})
在上面的行中，net是类OverFeatAccurateBase的对象
netmode是一个占位符，其值决定是从训练集还是验证集中读取数据。
1 个答案:
答案 0 :(得分：1)
我已经下载了您提供的数据集并检查了图像。我发现在验证集中，标签是无序的。所以检查数据。
在标签索引= 1的训练集中，有三个例子：
在标签索引= 1的验证集中，有三个示例：
相关问题
- Estimator培训期间的验证
- Tensorflow批量规范导致培训损失和验证损失之间的不平衡？
- Keras Batchnormalization，培训数据集的培训和评估结果不同
- 设置＆＃34; training = False＆＃34; ＆＃34; tf.layers.batch_normalization＆＃34;培训将获得更好的验证结果
- tf.layers.batch_normalization中“可训练”和“训练”标志的重要性
- 验证和培训期间TensorFlow中的批量标准化
- 为什么设置training = True时tf.layers.batch_normalization表现良好，在测试阶段设置training = False时执行异常？
- Keras BatchNorm层在训练和推理过程中给出了奇怪的结果
- 为什么批标准化层需要张量流中的“训练”参数，但组标准化不需要
- tf.layers.batch_normalization（training = False）时，验证集似乎未使用更新的模型权重
最新问题
- 我写了这段代码，但我无法理解我的错误
- 我无法从一个代码实例的列表中删除 None 值，但我可以在另一个实例中。为什么它适用于一个细分市场而不适用于另一个细分市场？
- 是否有可能使 loadstring 不可能等于打印？卢阿
- java中的random.expovariate()
- Appscript 通过会议在 Google 日历中发送电子邮件和创建活动
- 为什么我的 Onclick 箭头功能在 React 中不起作用？
- 在此代码中是否有使用“this”的替代方法？
- 在 SQL Server 和 PostgreSQL 上查询，我如何从第一个表获得第二个表的可视化
- 每千个数字得到
- 更新了城市边界 KML 文件的来源？