Pre-trained model: A pre-trained model is a saved network that was previously trained on a large dataset, typically on a large-scale image classification task.
从字面上看,预训练模型(pre-training model)是先通过一批语料进行模型训练,然后在这个初步训练好的模型基础上,再继续训练或者另作他用。这样的理解基本上是对的,预训练模型的训练和使用分别对应两个阶段:预训练阶段(pre-training)和 微调阶段(fune-tuning)。
Reference:
https://www.cnblogs.com/zjuhaohaoxuexi/p/16393655.html
网友评论