wolfe
wolfe
First, i start an doccano docker. When this doccano is crashed (the database is locked, it seems overload for several annotator operation at the same time, and i don't know...
I didn't get it. I expected it should export with only one file (example: all.jsonl). This probelm is identical to https://github.com/doccano/doccano/issues/1960. It's duplicate.
I replicate this with doccano version 1.8.0 (pip (Python 3.8+)). It export two files separate (only two user in this project - which is admin.jsonl and another username.jsonl), which give...
> I want to know your original file size(MB). the media folder is almost 85MB.
从(8.28)过渡到(8.31)
9.38下标错误：应为 $$\sum^m_{j=1} \frac{\alpha_i \cdot p(x_j|\mu_i, \Sigma_i)}{\sum^k_{l=1}\alpha_l \cdot p(x_j|\mu_l,\Sigma_l)} = -\lambda \alpha_i$$
您好，关于深度迁移学习中图31（page 38）的说明，该图是引用的哪篇论文？使用的什么数据集？ 还有以下几点疑惑需要请教您： 1) 目前，迁移学习主要都是深度迁移学习方法来做吗？或者深度迁移学习与传统迁移学习方法的结合？ 2) 相比传统的迁移学习方法，深度迁移学习方法主要是在哪方面进行迁移比较有优势（数据分布 or 特征 or 子空间 ）？
非常感谢解答！👍
它这个封装的有问题 - 要使用词性标注，只需要设置一个参数就可以了（postag=True），提供模型路径会报错