下面是常见的 mnist RNN模型,很奇怪的是,我们发现参数只用在了从lstm至输出层之间,而从输入层到lstm(隐层)之间却并没有参数,还能够正常运行!关键代码用红色标出了!请问是怎么回事?
# -*- coding: utf-8 -*-
"""Created on Thu Jan 11 08:56:10 2018
@author: Administrator
"""
from tensorflow.contrib import rnn
import numpy as np
import tensorflow as tf
c=np.load('C:/Users/Administrator/Desktop/jm00train.npy')
d=np.load('C:/Users/Administrator/Desktop/jm00label.npy')
jm00train=c[:140000]
jm00test=c[140000:]
c=np.float32(c)
jm00trainlabel=d[:140000]
jm00trainlabelonehot=tf.one_hot(jm00trainlabel,7)
jm00testlabel=d[140000:]
jm00testlabelonehot=tf.one_hot(jm00testlabel,7)
n_inputs=38
max_time=50
lstm_size=20
n_classes=7