Question

我正在训练以下模型：

with slim.arg_scope(inception_arg_scope(is_training=True)):
    logits_v, endpoints_v = inception_v3(all_v, num_classes=25, is_training=True, dropout_keep_prob=0.8,
                     spatial_squeeze=True, reuse=reuse_variables, scope='vis')
    logits_p, endpoints_p = inception_v3(all_p, num_classes=25, is_training=True, dropout_keep_prob=0.8,
                     spatial_squeeze=True, reuse=reuse_variables, scope='pol')
    pol_features = endpoints_p['pol/features']
    vis_features = endpoints_v['vis/features']

eps = 1e-08
loss = tf.sqrt(tf.maximum(tf.reduce_sum(tf.square(pol_features - vis_features), axis=1, keep_dims=True), eps))

# rest of code
saver = tf.train.Saver(tf.global_variables())

，其中

def inception_arg_scope(weight_decay=0.00004,
                    batch_norm_decay=0.9997,
                    batch_norm_epsilon=0.001, is_training=True):
normalizer_params = {
    'decay': batch_norm_decay,
    'epsilon': batch_norm_epsilon,
    'is_training': is_training
}
normalizer_fn = tf.contrib.layers.batch_norm

# Set weight_decay for weights in Conv and FC layers.
with slim.arg_scope([slim.conv2d, slim.fully_connected],
                    weights_regularizer=slim.l2_regularizer(weight_decay)):
    with slim.arg_scope([slim.batch_norm, slim.dropout], is_training=is_training):
        with slim.arg_scope(
                [slim.conv2d],
                weights_initializer=slim.variance_scaling_initializer(),
                activation_fn=tf.nn.relu,
                normalizer_fn=normalizer_fn,
                normalizer_params=normalizer_params) as sc:
            return sc

和inception_V3定义为here。我的模型训练很好，损失从60到小于1.但是当我想在另一个文件中测试模型时：

with slim.arg_scope(inception_arg_scope(is_training=False)):
    logits_v, endpoints_v = inception_v3(all_v, num_classes=25, is_training=False, dropout_keep_prob=0.8,
                     spatial_squeeze=True, reuse=reuse_variables, scope='vis')
    logits_p, endpoints_p = inception_v3(all_p, num_classes=25, is_training=False, dropout_keep_prob=0.8,
                     spatial_squeeze=True, reuse=reuse_variables, scope='pol')

它给了我无意义的结果，或者更确切地说，对于所有列车和测试样本，损失是1e-8。当我更改is_training=True时，它会提供更多逻辑结果，但损失仍大于训练阶段（即使我正在测试训练数据）我对VGG16也有同样的问题。当我使用不带batch_norm的VGG和使用batch_norm时为0％时，我的测试精度为100％。

我在这里缺少什么？谢谢，

Answer 1

我遇到了同样的问题并解决了。使用slim.batch_norm时，请务必使用slim.learning.create_train_op代替tf.train.GradientDecentOptimizer(lr).minimize(loss)或其他优化工具。试试它是否有效！

测试时Tensorflow batch_norm无法正常工作（is_training = False）

1 个答案: