Python Keras：海关损失原因“；必须为占位符张量“输入值”；

我正试图按照Keras存储库中的步骤在Keras中构建一个可变自动编码器。以下是我的设置：

from keras.layers import Dense, Input, merge, concatenate, Dense, LSTM, Lambda, Flatten, Reshape
from keras import backend as K
from keras.models import Model
from keras.losses import mse
import numpy as np

class VAE:
  def __init__(self, n_verts=15, n_dims=3, n_layers=3, n_units=128, latent_dim=2):
    self.n_verts = n_verts
    self.n_dims = n_dims
    self.n_layers = n_layers
    self.n_units = n_units
    self.latent_dim = latent_dim
    self.encoder = self.build_encoder()
    self.decoder = self.build_decoder()
    inputs = Input((self.n_verts, self.n_dims))
    outputs = self.decoder(self.encoder(inputs)[2])
    self.model = Model(inputs, outputs, name='vae')
    self.model.compile(optimizer='adam', loss=self.get_loss)

  def build_encoder(self):
    i = Input(shape=(self.n_verts, self.n_dims), name='encoder_input')
    h = i
    h = Flatten()(h)
    h = Dense(self.n_units, activation='relu')(h)
    for idx in range(1, self.n_layers, 1):
      h = Dense(self.n_units // (2*idx), activation='relu')(h)
    self.z_mean = Dense(self.latent_dim, name='z_mean')(h)
    self.z_log_var = Dense(self.latent_dim, name='z_log_var')(h)
    # use reparameterization trick to factor stochastic node out of gradient flow
    self.z = Lambda(self.sample, output_shape=(self.latent_dim,), name='z')([self.z_mean, self.z_log_var])
    return Model(i, [self.z_mean, self.z_log_var, self.z], name='encoder')

  def sample(self, args):
    '''
    Reparameterization trick by sampling from an isotropic unit Gaussian.
      @arg (tensor): mean and log of variance of Q(z|X)
      @returns z (tensor): sampled latent vector
    '''
    z_mean, z_log_var = args
    batch = K.shape(z_mean)[0]
    dim = K.int_shape(z_mean)[1]
    # by default, random_normal has mean = 0 and std = 1.0
    epsilon = K.random_normal(shape=(batch, dim))
    return z_mean + K.exp(0.5 * z_log_var) * epsilon

  def build_decoder(self):
    i = Input(shape=(self.latent_dim,), name='z_sampling')
    h = i
    for idx in range(1, self.n_layers, 1):
      h = Dense(self.n_units//(2*(self.n_layers-idx)), activation='relu')(h)
    h = Dense(self.n_units, activation='relu')(h)
    h = Dense(self.n_verts * self.n_dims, activation='sigmoid')(h)
    o = Reshape((self.n_verts, self.n_dims))(h)
    return Model(i, o, name='decoder')

  def get_loss(self, inputs, outputs):
    reconstruction_loss = mse(inputs, outputs)
    reconstruction_loss *= self.n_verts * self.n_dims
    return reconstruction_loss # this works fine
    kl_loss = 1 + self.z_log_var - K.square(self.z_mean) - K.exp(self.z_log_var)
    kl_loss = K.sum(kl_loss, axis=-1)
    kl_loss *= -0.5
    vae_loss = K.mean(reconstruction_loss + kl_loss) # todo: make this balance parameterizable
    return vae_loss # this doesn't

  def train(self, X, predict='frame', n_epochs=10000):
    for idx in range(n_epochs):
      i = np.random.randint(0, X.shape[1]-1) # sample idx
      frame = np.expand_dims( X[:,i:i+1,:].squeeze(), axis=0) # shape = 1 sample, v verts, d dims
      next_frame = np.expand_dims( X[:,i+1:i+2,:].squeeze(), axis=0)
      if predict == 'frame': loss = self.model.train_on_batch(frame, frame)
      elif predict == 'next_frame': loss = self.model.train_on_batch(frame, next_frame)
      if idx % 1000 == 0:
        print(' * training idx', idx, 'loss', loss)

X_train = np.random.rand(15, 100, 3)
vae = VAE(n_verts=15, latent_dim=2, n_layers=3, n_units=128)
vae.encoder.summary()
vae.train(X_train, n_epochs=10000, predict='frame')

这是可行的，但是如果您查看

get\u loss

函数，就会发现它返回得有点过早。如果我注释掉

return recostruction\u loss

，使loss函数返回

vae\u loss

，我会得到一个错误：

--------------------------------------------------------------------------- InvalidArgumentError                      Traceback (most recent call last) <ipython-input-7-57d76ed539a4> in <module>
     78 vae = VAE(n_verts=15, latent_dim=2, n_layers=3, n_units=128)
     79 vae.encoder.summary()
---> 80 vae.train(X_train, n_epochs=10000, predict='frame')

<ipython-input-7-57d76ed539a4> in train(self, X, predict, n_epochs)
     70       frame = np.expand_dims( X[:,i:i+1,:].squeeze(), axis=0) # shape = 1 sample, v verts, d dims
     71       next_frame = np.expand_dims( X[:,i+1:i+2,:].squeeze(), axis=0)
---> 72       if predict == 'frame': loss = self.model.train_on_batch(frame, frame)
     73       elif predict == 'next_frame': loss = self.model.train_on_batch(frame, next_frame)
     74       if idx % 1000 == 0:

~/anaconda/envs/3.5/lib/python3.5/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)    1215     ins = x + y + sample_weights    1216         self._make_train_function()
-> 1217         outputs = self.train_function(ins)    1218         return unpack_singleton(outputs)    1219 

~/anaconda/envs/3.5/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)    2713                 return self._legacy_call(inputs)    2714 
-> 2715             return self._call(inputs)    2716         else:    2717             if py_any(is_tensor(x) for x in inputs):

~/anaconda/envs/3.5/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in _call(self, inputs)    2673             fetched = self._callable_fn(*array_vals, run_metadata=self.run_metadata)    2674 else:
-> 2675             fetched = self._callable_fn(*array_vals)    2676         return fetched[:len(self.outputs)]    2677 

~/anaconda/envs/3.5/lib/python3.5/site-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)    1437           ret = tf_session.TF_SessionRunCallable(    1438               self._session._session, self._handle, args, status,
-> 1439               run_metadata_ptr)    1440         if run_metadata:    1441           proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

~/anaconda/envs/3.5/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
    526             None, None,
    527             compat.as_text(c_api.TF_Message(self.status.status)),
--> 528             c_api.TF_GetCode(self.status.status))
    529     # Delete the underlying status object from memory otherwise it stays alive
    530     # as there is a reference to status from this from the traceback due to

InvalidArgumentError: You must feed a value for placeholder tensor 'encoder_input_6' with dtype float and shape [?,15,3]     [[{{node encoder_input_6}}]]

-------------------------------------------------------------中的InvalidArgumentError回溯（最近一次调用last）
78 vae=vae（n_顶点=15，潜在尺寸=2，n_层=3，n_单位=128）
79 vae.encoder.summary（）
--->80 vae.列车（X_列车，n_时代=10000，预测=帧）
列车内（自我、X、预测、n_时代）
70帧=np.展开尺寸（X[：，i:i+1，：].挤压（），轴=0）#形状=1个样本，v顶点，d尺寸
71下一帧=np。展开尺寸（X[：，i+1:i+2，：].squence（），轴=0）
--->72如果预测='frame'：损失=self.model.train\u on\u批次（frame，frame）
73 elif predict==“下一帧”：loss=self.model.train\u on\u批处理（帧，下一帧）
74如果idx%1000==0：
~/anaconda/envs/3.5/lib/python3.5/site-packages/keras/engine/training.py in-train-on-on-u批（self，x，y，sample-u-weight，class-u-weight）1215 ins=x+y+sample-u-weights 1216 self.\u-make-u-train-u-u函数（）
->1217输出=自列车功能（ins）1218返回解包单体（输出）1219
~/anaconda/envs/3.5/lib/python3.5/site-packages/keras/backend/tensorflow\u backend.py in\uuuuuuu调用\uuuuuuu（self，输入）2713返回self.\u legacy\u调用（输入）2714
->2715返回self.\u调用（输入）2716其他：2717如果py\u有（是输入中x的张量（x））：
~/anaconda/envs/3.5/lib/python3.5/site-packages/keras/backend/tensorflow\u backend.py in.\u call（self，inputs）2673 fetched=self.\u callable\u fn（*array\u vals，run\u metadata=self.run\u metadata）2674其他：
->2675 fetched=self.\u callable\u fn（*array\u vals）2676返回fetched[：len（self.outputs）]2677
~/anaconda/envs/3.5/lib/python3.5/site-packages/tensorflow/python/client/session.py in uuu-call_uu（self，*args，**kwargs）1437 ret=tf_session.tf_SessionRunCallable（1438 session.\u session，self.\u句柄，args，状态，
->1439如果运行元数据：1441 proto\u data=tf\u session.tf\u GetBuffer（运行元数据\u ptr），则运行元数据（run\u ptr）1440
~/anaconda/envs/3.5/lib/python3.5/site-packages/tensorflow/python/framework/errors\u impl.py in\uuuuuuu exit\uuuuuuuuu（self、type\u arg、value\u arg、traceback\u arg）
526没有，没有，
527兼容as_文本（c_api.TF_消息（self.status.status）），
-->528 c_api.TF_GetCode（self.status.status））
529#从内存中删除基础状态对象，否则它将保持活动状态
530#由于以下原因，在回溯中有一个状态参考：
InvalidArgumentError:必须为占位符张量'encoder_input_6'提供一个值，该值具有数据类型float和形状[？，15,3][{{{节点编码器_input_6}}]]

---

有人知道如何解决这个错误吗？任何建议都将不胜感激

啊，一旦我的变量范围正确，我就解决了这个问题：

from keras.layers import Dense, Input, merge, concatenate, Dense, LSTM, Lambda, Flatten, Reshape
from keras import backend as K
from keras.models import Model
from keras.losses import mse
import numpy as np


class VAE:
  def __init__(self, n_verts=15, n_dims=3, n_layers=3, n_units=128, latent_dim=2):
    self.input_shape = (n_verts*n_dims,)
    self.n_layers = n_layers
    self.n_units = n_units
    self.latent_dim = latent_dim
    # build the encoder and decoder
    inputs = Input(shape=self.input_shape, name='encoder_input')
    self.encoder = self.get_encoder(inputs)
    self.decoder = self.get_decoder()
    # build the VAE
    outputs = self.decoder(self.encoder(inputs)[2])
    self.model = Model(inputs, outputs, name='vae_mlp')
    # add loss and compile
    self.model.add_loss(self.get_loss(inputs, outputs))
    self.model.compile(optimizer='adam')


  def get_encoder(self, inputs):
    h = inputs
    h = Dense(self.n_units, activation='relu')(h)
    for idx in range(1, self.n_layers, 1):
      h = Dense(self.n_units // (2*idx), activation='relu')(h)
    self.z_mean = Dense(self.latent_dim, name='z_mean')(h)
    self.z_log_var = Dense(self.latent_dim, name='z_log_var')(h)
    z = Lambda(self.sampling, output_shape=(self.latent_dim,), name='z')([self.z_mean, self.z_log_var])
    encoder = Model(inputs, [self.z_mean, self.z_log_var, z], name='encoder')
    return encoder


  def sampling(self, args):
    self.z_mean, self.z_log_var = args
    batch = K.shape(self.z_mean)[0]
    dim = K.int_shape(self.z_mean)[1]
    # by default, random_normal has mean = 0 and std = 1.0
    epsilon = K.random_normal(shape=(batch, dim))
    return self.z_mean + K.exp(0.5 * self.z_log_var) * epsilon


  def get_decoder(self):
    latent_inputs = Input(shape=(self.latent_dim,), name='z_sampling')
    h = latent_inputs
    for idx in range(1, self.n_layers, 1):
      h = Dense(self.n_units//(2*(self.n_layers-idx)), activation='relu')(h)
    h = Dense(self.n_units, activation='relu')(h)
    outputs = Dense(self.input_shape[0], activation='sigmoid')(h)
    decoder = Model(latent_inputs, outputs, name='decoder')
    return decoder


  def get_loss(self, inputs, outputs):
    reconstruction_loss = mse(inputs, outputs)
    reconstruction_loss *= self.input_shape[0]
    kl_loss = 1 + self.z_log_var - K.square(self.z_mean) - K.exp(self.z_log_var)
    kl_loss = K.sum(kl_loss, axis=-1)
    kl_loss *= -0.5
    vae_loss = K.mean(reconstruction_loss + kl_loss)
    return vae_loss


# train
x_train = np.random.rand(10000, 45)
vae = VAE(n_verts=15, latent_dim=2, n_layers=3, n_units=128)
vae.model.fit(x_train[:-1000,:],
        epochs=100,
        batch_size=128,
        validation_data=(x_train[-1000:,:], None))