TextClassifier_Transformer icon indicating copy to clipboard operation
TextClassifier_Transformer copied to clipboard

个人基于谷歌开源的BERT编写的文本分类器(基于微调方式),可自由加载NLP领域知名的预训练语言模型BERT、Bert-wwm、Roberta、ALBert以及ERNIE1.0

Results 3 TextClassifier_Transformer issues
Sort by recently updated
recently updated
newest added

input_fn = tf.estimator.export.build_raw_serving_input_receiver_fn({ 'label_ids': label_ids, 'input_ids': input_ids, 'input_mask': input_mask, 'segment_ids': segment_ids, })() 少了后面那个括号,排查了好久。。。

hello,想请教一下f1的计算方式: 您这里是这样计算的:f1 = (2 * precision[0] * recall[0] / (precision[0] + recall[0]),recall[1]),这里f1的update只用了recall,请问是怎么考虑的呢? 我觉得应该是这样:f1_update = 2 * update_op_precision * update_op_recall / (update_op_precision + update_op_recall + eps) 麻烦了,多谢多谢!