tensorflow summary
阿新 • • 發佈：2018-08-28
var glob span add attention merge col tex ogr
定義summary
writer = tf.summary.FileWriter(logdir=self.han_config.log_path, graph=session.graph)
1.scalar存儲結果
a.先在訓練的循環外定義:
test_accuracy_summary = tf.summary.scalar(‘test_accuracy‘, self.han_model.accuracy) test_loss_summary = tf.summary.scalar(‘test_loss‘, self.han_model.loss) test_scalar= tf.summary.merge([test_accuracy_summary, test_loss_summary])
b.在session run的時候run test_scalar，獲得值，然後再添加。
writer.add_summary(summary=train_scalar_, global_step=steps)
2.histogram存儲權重，偏執。
a.先在訓練的循環外定義:
W_w_attention_word_histogram = tf.summary.histogram(‘W_w_attention_word‘, self.han_model.W_w_attention_word) W_b_attention_word_histogram = tf.summary.histogram(‘W_w_attention_word‘, self.han_model.W_b_attention_word) context_vecotor_word_histogram = tf.summary.histogram(‘context_vecotor_word‘, self.han_model.context_vecotor_word) W_w_attention_sentence_histogram= tf.summary.histogram(‘W_w_attention_sentence‘, self.han_model.W_w_attention_sentence) W_b_attention_sentence_histogram = tf.summary.histogram(‘W_b_attention_sentence‘, self.han_model.W_b_attention_sentence) context_vecotor_sentence_histogram = tf.summary.histogram(‘context_vecotor_sentence‘, self.han_model.context_vecotor_sentence) train_variable_histogram = tf.summary.merge([W_w_attention_word_histogram, W_b_attention_word_histogram, context_vecotor_word_histogram, W_w_attention_sentence_histogram, W_b_attention_sentence_histogram, context_vecotor_sentence_histogram])
b.在session run的時候run test_scalar，獲得值，然後再添加。
writer.add_summary(summary=train_variable_histogram_, global_step=steps)
tensorflow summary