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?