问题描述
我知道这个问题在 stackoverflow 和 github 中已经多次提到,但在我的情况下似乎没有任何问题可以解决。我正在尝试使用 tensorflow_probability 模式的变分自动编码器。在使用 model.fit
方法训练模型时,我看到在第一个 epoch 期间,有一个警告 Gradient Do not exist for the weights and biases variables of the decoder when minimizing the loss
。莫名其妙的部分是从第二个时代开始,一切似乎都很正常并且得到了输出。任何帮助将不胜感激解决此问题。为了完整起见,提供了解码器和警告。
dec_klreg = Sequential([
InputLayer(input_shape=[latent_size])]+
[Dense(unit,activation='relu') for unit in units[::-1]]+
[Dense(2*input_shape),tfpl.distributionLambda(
lambda t: tfd.MultivariatenormalDiag(
loc=t[...,:input_shape],scale_diag = tf.math.exp(t[...,input_shape:])
)
)
])
这是摘要。
Model: "sequential_4"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_16 (Dense) (None,8) 24
_________________________________________________________________
dense_17 (Dense) (None,16) 144
_________________________________________________________________
dense_18 (Dense) (None,32) 544
_________________________________________________________________
dense_19 (Dense) (None,100) 3300
_________________________________________________________________
distribution_lambda_3 (distr multiple 0
=================================================================
Total params: 4,012
Trainable params: 4,012
Non-trainable params: 0
这是适合的方法:
vae_klreg = tf.keras.Model(inputs = enc_klreg.input,outputs = dec_klreg(enc_klreg.output))
vae_klreg.compile(optimizer= tf.keras.optimizers.Adam(learning_rate=0.001),loss = loss_mcmc_klreg)
history = vae_klreg.fit(x_train,epochs=100,batch_size=1000,validation_split=0.1)
**enc_klreg 是编码器。
这里是警告:
Epoch 1/100
WARNING:tensorflow:Gradients do not exist for variables ['dense_16/kernel:0','dense_16/bias:0','dense_17/kernel:0','dense_17/bias:0','dense_18/kernel:0','dense_18/bias:0','dense_19/kernel:0','dense_19/bias:0'] when minimizing the loss.
WARNING:tensorflow:Gradients do not exist for variables ['dense_16/kernel:0','dense_19/bias:0'] when minimizing the loss.
9/9 [==============================] - 1s 39ms/step - loss: 1858.8081 - val_loss: 458.4520
Epoch 2/100
9/9 [==============================] - 0s 6ms/step - loss: 411.9823 - val_loss: 273.5398
Epoch 3/100
9/9 [==============================] - 0s 6ms/step - loss: 281.3841 - val_loss: 208.0804
解决方法
暂无找到可以解决该程序问题的有效方法,小编努力寻找整理中!
如果你已经找到好的解决方法,欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@)