Question

我正在将模型训练为：

with tf.Graph().as_default():
        with tf.Session(config=tf.ConfigProto(allow_soft_placement = True)) as sess:
                K.set_session(sess)
                tf.train.create_global_step()
                #with tf.device('/gpu:0:'):
                m = GAReader.Model(nlayers, data.vocab_size, data.num_chars, W_init,
                        nhidden, embed_dim, dropout, train_emb,
                        char_dim, use_feat, gating_fn, words).build_network()
                m.compile(optimizer=tf.train.AdamOptimizer(0.01),
                          loss=tf.keras.losses.categorical_crossentropy,
                          metrics=[tf.keras.metrics.categorical_accuracy])
                tensorboard = TensorBoardCustom(log_dir="logs", sess=sess)
                m.fit_generator(generator=batch_loader_train, steps_per_epoch=len(batch_loader_train.batch_pool), epochs=100, callbacks=[tensorboard])

并且我定义了一个自定义回调，将keras.callbacks.Tensorboard扩展为：

class TensorBoardCustom(TensorBoard):

    def __init__(self, log_dir, sess, **kwargs):
        super(TensorBoardCustom, self).__init__(log_dir, **kwargs)
        self.sess = sess

    def on_batch_end(self, batch, logs={}):
        summary = tf.summary.merge_all()
        writer = tf.summary.FileWriter(self.log_dir)
        s = self.sess.run(summary)
        writer.add_summary(s, batch)
        writer.close()
        super(TensorBoardCustom, self).on_batch_end(batch, logs)

并且我要添加一个新的摘要：

l_docin = tf.keras.layers.Input(shape=(None,))
with tf.name_scope('summaries'):
            table = tf.contrib.lookup.index_to_string_table_from_tensor(
                    self.mapping_string, default_value="UNKNOWN")
            words = table.lookup(tf.cast(l_qin, tf.int64))
            text = tf.reduce_join(words, 1, separator=' ')
            tf.summary.text('text', text)

但是，这不起作用，并且出现以下错误：

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'input_2' with dtype float and shape [?,?]
     [[{{node input_2}} = Placeholder[dtype=DT_FLOAT, shape=[?,?], _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

有人可以解释为什么会发生这种情况以及我如何纠正它？有没有更简单/更好的方法来添加自定义摘要？

Answer 1

下面定义的

TensorFlow回调SQL> with longest as 2 (select min(hiredate) min_hiredate, 3 to_char(min(hiredate), 'dy', 'nls_date_language=english') day 4 from emp 5 ) 6 select min_hiredate, 7 day, 8 case when day in ('sat', 'sun') then 'weekend' 9 else 'weekday' 10 end result 11 from longest; MIN_HIREDA DAY RESULT ---------- ------------ ---------- 17.12.1980 wed weekday SQL>记录累积训练和评估批处理时间。它依赖于私有属性TensorBoardWithTime和TensorBoard._train_writer。它可以与TensorFlow 2.4.0rc2一起使用。

TensorBoard._val_writer

使用tf.keras.Model.fit进行训练时如何将自定义摘要添加到张量板

1 个答案: