我想知道是否可以部分訓(xùn)練神經(jīng)網(wǎng)絡(luò)的輸入。例如，假設(shè)我有輸入 256 和輸出 256 的神經(jīng)網(wǎng)絡(luò)。我要問的是是否有可能采取組，其中每個組僅包含 265 個輸入中的 16 個，以便基于單個輸入進(jìn)行預(yù)測模型獨(dú)立訓(xùn)練，然后在最終輸出中連接整個組。例如，提供了以下示例：from matplotlib import pyplot as pltimport tensorflow as tftf.reset_default_graph()x_train = [[0.,0.],[1.,1.],[1.,0.],[0.,1.]]y_train = [[0.],[0.],[1.],[1.]]x_test =  [[0.,0.],[.5,.5],[.5,0.],[0.,.5]]y_test = [[0.],[0.],[2.],[2.]]# use placeholder instead so you can have different inputsx = tf.placeholder('float32', [None, 2])y = tf.placeholder('float32',)# Layer 1 = the 2x3 hidden sigmoidm1 = tf.Variable(tf.random_uniform([2,3], minval=0.1, maxval=0.9, dtype=tf.float32))b1 = tf.Variable(tf.random_uniform([3], minval=0.1, maxval=0.9, dtype=tf.float32))h1 = tf.sigmoid(tf.matmul(x, m1) + b1)# Layer 2 = the 3x1 sigmoid outputm2 = tf.Variable(tf.random_uniform([3,1], minval=0.1, maxval=0.9, dtype=tf.float32))b2 = tf.Variable(tf.random_uniform([1], minval=0.1, maxval=0.9, dtype=tf.float32))y_out = tf.sigmoid(tf.matmul(h1, m2) + b2)### loss# loss : sum of the squares of y0 - y_outloss = tf.reduce_sum(tf.square(y - y_out))# training step : gradient decent (1.0) to minimize losstrain = tf.train.GradientDescentOptimizer(1.0).minimize(loss)# the two feed dictionariesfeeddict_train = {x: x_train, y: y_train}feeddict_test = {x: x_test, y: y_test}### training# run 500 times using all the X and Y# print out the loss and any other interesting infowith tf.Session() as sess:    sess.run(tf.global_variables_initializer())    train_loss, test_loss = [], []    for step in range(500):        loss_train, _ = sess.run([loss, train], feed_dict=feeddict_train)        train_loss.append(loss_train)        # under the same tensorflow graph (in the session), use another feed dictionary         loss_test = sess.run(loss, feed_dict=feeddict_test)        test_loss.append(loss_test)在此命令中，將獲取和訓(xùn)練loss_test = sess.run(loss, feed_dict=feeddict_test)整個輸入。feeddict_test如果我想把它分成兩組，每個組只包含可用的 4 個項目中的 2 個，然后單獨(dú)測試它們并連接輸出，這可能嗎？我怎樣才能做到這一點(diǎn)？如果可能的話，你能幫我這樣做嗎？