我正在用GRU制作GAN模型。
当我训练模型时，我得到：'ValueError：不支持任何值'。
运行train_on_batch（）函数时会引发错误。
目标是y2（数据看起来像这样。[[0. 1.] [0. 1.] ...... [0. 1。]]）
我改变了y2的数据类型，但它没有用。 这是我的代码和错误消息。
我修改了这段代码 - ＆GT;＆GT; https://github.com/kimsohyeon/KerasGAN
def build_GAN():
######### Build Generative model ... ##########
g_input = Input(shape=[100])
H = Embedding(100,256)(g_input)
H = GRU(256, dropout=0.2, recurrent_dropout=0.2)(H)
g_V = Dense(maxlen, activation='sigmoid')(H)
generator = Model(g_input,g_V)
generator.compile(loss='binary_crossentropy', optimizer='adam')
######## Build Discriminative model ... ##########
d_input = Input(shape=[maxlen])
H = Embedding(max_features, 256)(d_input)
H = GRU(256, dropout=0.2, recurrent_dropout=0.2)(H)
d_V = Dense(2, activation='softmax')(H)
discriminator = Model(d_input,d_V)
discriminator.compile(loss='categorical_crossentropy', optimizer='adam')
make_trainable(discriminator, False)
########### Build stacked GAN model ##############
gan_input = Input(shape=[100])
H = generator(gan_input)
gan_V = discriminator(H)
GAN = Model(gan_input, gan_V)
GAN.compile(loss='categorical_crossentropy', optimizer='adam')
return generator, discriminator, GAN
def train_GAN(x_train, nb_epoch, plt_frq, batch_size):
print('Train...')
# set up loss storage vector
losses = {"d":[], "g":[]}
for e in tqdm(range(nb_epoch)):
# X : real data + fake data
trainidx = random.sample(range(0,x_train.shape[0]), batch_size)
review_batch = x_train[trainidx]
noise_gen = np.random.uniform(0,1,size=[batch_size,100])
generated_reviews = generator.predict(noise_gen)
x = np.concatenate((review_batch, generated_reviews))
# y : [0,1] = positive data, [1,0] = negative data
y = np.zeros([2*batch_size,2])
y[0:batch_size,1] = 1
y[batch_size:,0] = 1
make_trainable(discriminator,True)
d_loss = discriminator.train_on_batch(x,y)
losses["d"].append(d_loss)
# train Generator-Discriminator stack on input noise to non-generated output class
noise_tr = np.random.uniform(0,1,size=[batch_size,100])
y2 = np.zeros([batch_size,2])
y2[:,1] = 1
make_trainable(discriminator,False)
g_loss = GAN.train_on_batch(noise_tr, y2)
losses["g"].append(g_loss)
---------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-43-fc66cd2b8331> in <module>()
24 generator, discriminator, GAN = build_GAN()
25
---> 26 train_GAN(xp_train, nb_epoch=100, plt_frq=25, batch_size=32)
27 map(add, performance,one_class_performance(xp_test, xn_test))
28
<ipython-input-42-b8c2dbe7b1c6> in train_GAN(x_train, nb_epoch, plt_frq, batch_size)
28 y2[:,1] = 0
29 make_trainable(discriminator,False)
---> 30 g_loss = GAN.train_on_batch(noise_tr, y2)
31 losses["g"].append(g_loss)
32
//anaconda/lib/python3.5/site-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1562 else:
1563 ins = x + y + sample_weights
-> 1564 self._make_train_function()
1565 outputs = self.train_function(ins)
1566 if len(outputs) == 1:
//anaconda/lib/python3.5/site-packages/keras/engine/training.py in _make_train_function(self)
935 self._collected_trainable_weights,
936 self.constraints,
--> 937 self.total_loss)
938 updates = self.updates + training_updates
939 # Gets loss and metrics. Updates weights at each call.
//anaconda/lib/python3.5/site-packages/keras/optimizers.py in get_updates(self, params, constraints, loss)
418
419 for p, g, m, v in zip(params, grads, ms, vs):
--> 420 m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
421 v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(g)
422 p_t = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon)
//anaconda/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py in binary_op_wrapper(x, y)
881 with ops.name_scope(None, op_name, [x, y]) as name:
882 if not isinstance(y, sparse_tensor.SparseTensor):
--> 883 y = ops.convert_to_tensor(y, dtype=x.dtype.base_dtype, name="y")
884 return func(x, y, name=name)
885
//anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, preferred_dtype)
649 name=name,
650 preferred_dtype=preferred_dtype,
--> 651 as_ref=False)
652
653
//anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype)
714
715 if ret is None:
--> 716 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
717
718 if ret is NotImplemented:
//anaconda/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
174 as_ref=False):
175 _ = as_ref
--> 176 return constant(v, dtype=dtype, name=name)
177
178
//anaconda/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name, verify_shape)
163 tensor_value = attr_value_pb2.AttrValue()
164 tensor_value.tensor.CopyFrom(
--> 165 tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
166 dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
167 const_tensor = g.create_op(
//anaconda/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape)
358 else:
359 if values is None:
--> 360 raise ValueError("None values not supported.")
361 # if dtype is provided, forces numpy array to be the type
362 # provided if possible.
ValueError: None values not supported.