回答此问题可获得 20 贡献值,回答如果被采纳可获得 50 分。
<p>我有tensorflow 1x(不是keras)中的自动编码器模型,我正在尝试在训练后将模型拆分为编码器和解码器</p>
<p>两者的作用域相同
我有3个占位符</p>
<pre><code>self.X = tf.placeholder(shape=[None, vox_res64, vox_res64, vox_res64, 1], dtype=tf.float32)
self.Z = tf.placeholder(shape=[None,500], dtype=tf.float32)
self.Y = tf.placeholder(shape=[None, vox_rex256, vox_rex256, vox_rex256, 1], dtype=tf.float32)
with tf.variable_scope('aeu'):
self.lfc=self.encoder(self.X)
self.Y_pred, self.Y_pred_modi = self.decoder(self.lfc)
</code></pre>
<p>编码器和解码器如下</p>
<pre><code> def encoder(self,X):
with tf.device('/gpu:'+GPU0):
X = tf.reshape(X,[-1, vox_res64,vox_res64,vox_res64,1])
c_e = [1,64,128,256,512]
s_e = [0,1 , 1, 1, 1]
layers_e = []
layers_e.append(X)
for i in range(1,5,1):
layer = tools.Ops.conv3d(layers_e[-1],k=4,out_c=c_e[i],str=s_e[i],name='e'+str(i))
layer = tools.Ops.maxpool3d(tools.Ops.xxlu(layer, label='lrelu'), k=2,s=2,pad='SAME')
layers_e.append(layer)
### fc
[_, d1, d2, d3, cc] = layers_e[-1].get_shape()
d1=int(d1); d2=int(d2); d3=int(d3); cc=int(cc)
lfc = tf.reshape(layers_e[-1],[-1, int(d1)*int(d2)*int(d3)*int(cc)])
lfc = tools.Ops.xxlu(tools.Ops.fc(lfc, out_d=500,name='fc1'), label='relu')
print (d1)
print(cc)
return lfc
def decoder(self,Z):
with tf.device('/gpu:'+GPU0):
lfc = tools.Ops.xxlu(tools.Ops.fc(Z, out_d=2*2*2*512, name='fc2'), label='relu')
lfc = tf.reshape(lfc, [-1,2,2,2,512])
c_d = [0,256,128,64]
s_d = [0,2,2,2]
layers_d = []
layers_d.append(lfc)
for j in range(1,4,1):
layer = tools.Ops.deconv3d(layers_d[-1],k=4,out_c=c_d[j],str=s_d[j],name='d'+str(len(layers_d)))
layer = tools.Ops.xxlu(layer, label='relu')
layers_d.append(layer)
###
layer = tools.Ops.deconv3d(layers_d[-1],k=4,out_c=1,str=2,name='dlast')
print("****************************",layer)
###
Y_sig = tf.nn.sigmoid(layer)
Y_sig_modi = tf.maximum(Y_sig,0.01)
return Y_sig, Y_sig_modi
</code></pre>
<p>当我在训练后尝试使用模型时</p>
<pre><code>
X = tf.get_default_graph().get_tensor_by_name("Placeholder:0")
Z = tf.get_default_graph().get_tensor_by_name("Placeholder_1:0")
Y_pred = tf.get_default_graph().get_tensor_by_name("aeu/Sigmoid:0")
lfc = tf.get_default_graph().get_tensor_by_name("aeu/Relu:0")
</code></pre>
<p>获取潜在代码工作正常</p>
<pre><code> lc = sess.run(lfc, feed_dict={X: x_sample})
</code></pre>
<p>现在我想使用潜在的代码作为输入解码器我得到错误,我必须填写X(占位符)</p>
<pre><code> y_pred = sess.run(Y_pred, feed_dict={Z: lc})
</code></pre>
<p>我怎么能分裂到编码器-解码器?
我只搜了几遍,就找到了凯拉斯的例子</p>