-
Notifications
You must be signed in to change notification settings - Fork 2.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
multi_label_classification增量训练 #559
Comments
你好!你说的增量训练是指迁移学习Fine-tune吗?如果是的话,可以参考我们的demo,https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.6/demo/multi_label_classification |
@Steffy-zxf 你好!不是利用词向量迁移学习。而是断点训练,我已经迁移学习Fine-tune训练好了模型,但需要load bestmodel后 使用新增加数据,在原模型的基础上进行训练。 |
如果是想基于之前保存的checkpoint继续训练,可以将epoch设置更大些,RunConfig中checkpoint_dir设置与之前的ckpt文件路径相同,task.finetune_and_eval()接口会自动加载ckpt文件保存的最后一个step模型参数。 |
好的!十分感谢 |
@x330930520 你好!以上错误是paddlehub低版本的bug。请升级paddlehub (1.7.1)和 paddle(1.8.1)为最新版本。重新训练之后,即可增量训练。 |
@Steffy-zxf 你好,根据https://github.com/PaddlePaddle/PaddleHub/tree/release/v1.6/demo/multi_label_classification#step1-%E5%8A%A0%E8%BD%BD%E9%A2%84%E8%AE%AD%E7%BB%83%E6%A8%A1%E5%9E%8B ,我可以直接在 |
请问下 multi_label_classification增量训练 ernie可以实现吗?已经训练好模型了,需要新增数据继续训练,需要如何修改配置
The text was updated successfully, but these errors were encountered: