svjack
As i see this module deployed with flask. And too many users use it, so how to fine tune resource allocation and schedule configuration ? And are their some common...
It seems like, the Residual Loss construct is used test data in one dictionary, so can you describe the criterion code of choose most similar image in the train data...
it seems like this project mainly support parameters selection by stats or visualization in returns or plot. But it seems some other project support strategy optimize by algorithm like: https://www.freqtrade.io/en/latest/hyperopt/...
这样自己设定的一个evaluation measurement 也比较好插入配置，而不需要改前向传播函数的基本构造。
现在模型的使用都要用args进行配置，能否把这个东西包装成类呢？ 比如说我有pandas对象直接要调用模型，还要从args里面解析出tokenizer和其它配置 重新初始化模型，并自行完成分词和其它工作。 因为现在的接口都是针对文件的，希望能直接针对对象，使用比较方便。
您好 我看了一下run_dbqa.py的代码，有一些代码不太理解。 dataset_groupby_qid.append((qid, correct_answer_orders, scores)) 是不是应该加一个缩进，到循环内执行。 dataset_groupby_qid而且类型是一个list 并没有生成dataframe并执行groupby. 在这个任务中，一般text_a的不同已经能够区分是不同的“问”的排序了，还加了个qid， 这样也有一个好处，就是可以将若干类似的句子合并成一个样本（因为groupby） 但这看似仅仅影响evaluate过程。（是否进行合并） 不知道代码是否需要改一下。
nowadays, docs with rarely interpretation is difficult to understand the algorithm, Such as bayes rule sets and other Underdogs have little references. If can provide a common introduce in interface...
I think the usage of this framework should more focus on embedding construction with other deep learning framework. such as non.Embedding in pytorch and so on. With the help of...
Thank you to release this bravo project. When i use this project on multi table db, I want to implement convenient search on column name from different tables. I want...
it is oberviously.