Python keras模型如何仅预测一个样本？

在我的项目中，我想进行离线培训，这意味着它将以批处理方式处理样本（我设置了

batch\u size=100

在

model.fit（）

）中，我只想实时预测一个样本，因此我使用：

model.predict(x_real_time, batch_size=1)

但它显示了错误：

`ValueError: Cannot feed value of shape (1, 3) for Tensor 'input_11:0', which has shape '(165047, 3)'`

有人能告诉我怎么解决这个问题吗？谢谢

整个代码：

batch_size = int(data_num_.shape[0]/10)

original_dim = data_num_.shape[1]

latent_dim = data_num_.shape[1]*2

intermediate_dim = data_num_.shape[1]*10

nb_epoch = 10

epsilon_std = 0.001



data_untrain = data_scale.transform(df[(df['label']==cluster_num)&(df['prob']<threshold)].iloc[:,:data_num.shape[1]].values)

data_untrain_num = (int(data_untrain.shape[0]/batch_size)-1)*batch_size

data_untrain = data_untrain[:data_untrain_num,:]



x = Input(batch_shape=(batch_size, original_dim))

init_drop = Dropout(0.2, input_shape=(original_dim,))(x)

h = Dense(intermediate_dim, activation='relu')(init_drop)

z_mean = Dense(latent_dim)(h)

z_log_var = Dense(latent_dim)(h)





def sampling(args):

    z_mean, z_log_var = args

    epsilon = K.random_normal(shape=(batch_size, latent_dim), mean=0.,

                              std=epsilon_std)

    return z_mean + K.exp(z_log_var / 2) * epsilon

z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])


decoder_h = Dense(intermediate_dim, activation='relu')

decoder_mean = Dense(original_dim, activation='linear')

h_decoded = decoder_h(z)

x_decoded_mean = decoder_mean(h_decoded)





def vae_loss(x, x_decoded_mean):

    xent_loss = original_dim * objectives.mae(x, x_decoded_mean)

    kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)

    return xent_loss + kl_loss



vae = Model(x, x_decoded_mean)

vae.compile(optimizer=Adam(lr=0.01), loss=vae_loss)



train_ratio = 0.9

train_num = int(data_num_.shape[0]*train_ratio/batch_size)*batch_size

test_num = int(data_num_.shape[0]*(1-train_ratio)/batch_size)*batch_size



x_train = data_num_[:train_num,:]

x_test = data_num_[-test_num:,:]



vae.fit(x_train, x_train,

        shuffle=True,

        nb_epoch=nb_epoch,

        batch_size=batch_size,

        validation_data=(x_test, x_test))



# build a model to project inputs on the latent space

encoder = Model(x, z_mean)

x_test_predict = data_scale_.inverse_transform(vae.predict(x_test, batch_size=1))

x_test = data_scale_.inverse_transform(x_test)   

for idx in range(x_test.shape[1]):

    plt.plot(x_test[:,idx], alpha=0.3, color='red')

    plt.plot(x_test_predict[:,idx], alpha=0.3, color='blue')

    plt.show()

    plt.close()

batch\u size=int（数据\u num\u.shape[0]/10）
原始尺寸=数据数量形状[1]
潜在尺寸=数据数量形状[1]*2
中间尺寸=数据数量形状[1]*10
nb_epoch=10
εu标准=0.001
data_untrain=data_scale.transform（df[（df['label']==cluster_num）&（df['prob']]问题在于输入层。不应传入批量大小。如果要使用可变批量大小进行预测，则应传入没有批量大小的输入形状，然后只传入单个样本

因此：

请把你的全部代码放在这里好吗？模型实例化的代码和x_real_time的形状将极大地帮助我们解决你的问题。谢谢大家，我已经附上了上面的代码。是否可以通过批处理样本进行训练，并通过单一方式处理样本进行预测？因为我有更多的对于1000万个样本，我想使用mini-batch进行训练。是的，如果你不是从固定的批量开始，你仍然可以通过将批量大小传递给fit方法来进行批量训练。在拟合模型后，我运行vae.predict（x_test，batch_size=1）我显示一个错误：ValueError:无法将输入数组从shape（79397,3）广播到shape中（1,3）似乎必须正确设置批次大小。。。。
x = Input(shape=(3,))