ケラスモデルはどのようにして1つのサンプルのみを予測できますか？

Question

私のプロジェクトで

、私はそれがバッチ方法でサンプルを処理することを意味しますラインオフトレーニングを（私はmodel.fit()で

batch_size=100

を設定）やりたい、と私はリアルタイムで一つだけのサンプルを予測したいです

model.predict(x_real_time, batch_size=1) 

を、それはエラーを示しています：ので、私は使用

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

でしたいくつかの1つは、この1つを解決する方法を教えてください？おかげ

は、全体のコード：

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() 

Answer 1

問題は、入力層です。バッチサイズを渡すべきではありません。可変バッチサイズで予測する場合は、バッチサイズなしでinput_shapeを渡す必要があります。単一のサンプルを渡すだけです。

ので：

x = Input(shape=(3,))