初始值与我在tensorflow中设置的值非常不同

时间:2016-06-02 10:51:46

标签: machine-learning tensorflow deep-learning

我使用像这样的初始张量创建一个神经网络

tensor_dict = {
    'model_conv1_weights': tf.get_variable('model_conv1_weights',
        shape=[4, 4, 1, 64],
        initializer=tf.truncated_normal_initializer(mean=10.0, stddev=2.0))
    'model_conv1_biases': tf.get_variable('model_conv1_biases',
        shape=[64],
        initializer=tf.truncated_normal_initializer(mean=2.0, stddev=1.0))
    'model_conv2_weights': tf.get_variable('model_conv2_weights',
        shape=[4, 4, 64, 32],
        initializer=tf.truncated_normal_initializer(mean=10.0, stddev=2.0))
    'model_conv2_biases': tf.get_variable('model_conv2_biases',
        shape=[32],
        initializer=tf.truncated_normal_initializer(mean=2.0, stddev=1.0))
}

但是当我开始训练模型时,这些张量的初始值与我配置的非常不同。

snapshot of tensorboard http://image.prntscr.com/image/b6f709143de44dedb16448d83f0f6b11.png

之前有没有人遇到过这个问题?

0 个答案:

没有答案