tensorflow shapeの整え方をお尋ねしたいです。csvのデータ形式

Question

tensorflowで12個の要素から学習を行い、restoreを行い実践データをセットした際に1×12の行列ではなくて、shape[1]のスカラー値を要求されエラーになります。shape[1]という要求は読み込みデータを

今のcsv
rank 1 shape [1,12]

[ 0.71428573,  0.85714287,  0.71428573,  0.5714286 ,  0.5714286 ,
        0.71428573,  0.5714286 ,  0.71428573,  0.71428573,  0.71428573,
        0.5714286 ,  0.71428573]

こう変えることでshape[12,1,1] shape[1]という要求を満たせるですか？
お知恵を貸してください！

[ [0.71428573],  [0.85714287],  [0.71428573],  [0.5714286] ,  [0.5714286] ,
        [0.71428573],  [0.5714286] ,  [0.71428573],  [0.71428573],  [0.71428573],
        [0.5714286] ,  [0.71428573]]

ValueError: Argument must be a dense tensor: [array([ 0.71428573,  0.85714287,  0.71428573,  0.5714286 ,  0.5714286 ,
        0.71428573,  0.5714286 ,  0.71428573,  0.71428573,  0.71428573,
        0.5714286 ,  0.71428573], dtype=float32)] - got shape [1, 12], but wanted [1].

その他のコード（問題なのはsession2のほうです）

import tensorflow as tf
import numpy
import os

cwd = os.getcwd()

SCORE_SIZE = 12
HIDDEN_UNIT_SIZE = 40
TRAIN_DATA_SIZE = 45
TACK = 1
raw_input = numpy.loadtxt(open("test.csv"), delimiter=",")
[tensor, score]  = numpy.hsplit(raw_input, [1])
[tensor_train, tensor_test] = numpy.vsplit(tensor, [TRAIN_DATA_SIZE])
[score_train, score_test] = numpy.vsplit(score, [TRAIN_DATA_SIZE])
print(score_test)
#tensorは正解データtrainは学習モデル、scoreは学習データ、testは実データ

def inference(score_placeholder):
  with tf.name_scope('hidden1') as scope:
    hidden1_weight = tf.Variable(tf.truncated_normal([SCORE_SIZE, HIDDEN_UNIT_SIZE], stddev=0.01), name="hidden1_weight")
    hidden1_bias = tf.Variable(tf.constant(0.1, shape=[HIDDEN_UNIT_SIZE]), name="hidden1_bias")
    hidden1_output = tf.nn.relu(tf.matmul(score_placeholder, hidden1_weight) + hidden1_bias)
  with tf.name_scope('output') as scope:
    output_weight = tf.Variable(tf.truncated_normal([HIDDEN_UNIT_SIZE, 1], stddev=0.01), name="output_weight")
    output_bias = tf.Variable(tf.constant(0.1, shape=[1]), name="output_bias")
    output = tf.matmul(hidden1_output, output_weight) + output_bias
  if TACK != 1:
    print("saku1")
    print(output)
  else:
    print("saku2")
    
    return tf.nn.l2_normalize(output, 0)

def loss(output, tensor_placeholder, loss_label_placeholder):
  with tf.name_scope('loss') as scope:
    loss = tf.nn.l2_loss(output - tf.nn.l2_normalize(tensor_placeholder, 0))
    tf.summary.scalar('loss_label_placeholder', loss)
  return loss

def training(loss):
  with tf.name_scope('training') as scope:
    train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss)
  return train_step



with tf.Graph().as_default():
  tensor_placeholder = tf.placeholder(tf.float32, [None, 1], name="tensor_placeholder")
  score_placeholder = tf.placeholder(tf.float32, [None, SCORE_SIZE], name="score_placeholder")
  loss_label_placeholder = tf.placeholder("string", name="loss_label_placeholder")

  feed_dict_train={
    tensor_placeholder: tensor_train,
    score_placeholder: score_train,
    loss_label_placeholder: "loss_train"
  }

  feed_dict_test={
    tensor_placeholder: tensor_test,
    score_placeholder: score_test,
    loss_label_placeholder: "loss_test"
  }

  output = inference(score_placeholder)
  loss = loss(output, tensor_placeholder, loss_label_placeholder)
  training_op = training(loss)
  summary_op =  tf.summary.merge_all()
  init = tf.global_variables_initializer()
  best_loss = float("inf")

  with tf.Session() as sess:
    summary_writer = tf.summary.FileWriter('data', graph_def=sess.graph_def)
    sess.run(init)
    for step in range(10000):
      sess.run(training_op, feed_dict=feed_dict_train)
      loss_test = sess.run(loss, feed_dict=feed_dict_test)
      if loss_test < best_loss:
        best_loss = loss_test
        best_match = sess.run(output, feed_dict=feed_dict_test)
      #if step % 100 == 0:
      #  summary_str = sess.run(summary_op, feed_dict=feed_dict_test)
      #  summary_str += sess.run(summary_op, feed_dict=feed_dict_train)
      #  summary_writer.add_summary(summary_str, step)
    
    saver=tf.train.Saver()   
    saver.save(sess,cwd+'/model.ckpt')
    print(cwd)
    print(best_match)  
    print('Saved a model.')
    sess.close()

  with tf.Session() as sess2:
  #変数の読み込み
    summary_writer = tf.summary.FileWriter('data', graph=sess2.graph)
    #sess2.run(init)
  #新しいデータ
    TRAIN_DATA_SIZE2 = 0
    test2 = numpy.loadtxt(open("one_record.csv"), delimiter=",").astype(numpy.float32)
    score3 = [test2]
    print(score3)
    saver = tf.train.Saver()
    cwd = os.getcwd()
    saver.restore(sess2,cwd + "/model.ckpt")
    best_match2 = sess2.run(inference(score3))
    print(best_match2)
    print("fin")
    sess2.close()

Answer 1

shape を調整してあげる必要があるかもですが、、、
こんな感じでしょうね。

# best_match2 = sess2.run(inference(score3))
best_match2 = sess2.run(output, feed_dict={score_placeholder: test2})

Comments

[zakio49]

output = inference(score_placeholder)に一度いれるとinference()の返り値がoutputに入るので、session内ではinferenceが実行されていないことがわかりました。
(output, feed_dict={score_placeholder:[test2]})の記法でsessionを始めないといけないみたいですね。
うまく実行することができました。ありがとうございます。