关于多feature的使用

tf_euler.get_dense_feature 中提供了使用多feature的接口，list形式。但在查看run_loop代码，sageEncoder->shallowEncoder 的代码中发现，首先feature_idx和feature_dim都是integer值，如何输入多值？其次，如若简单的改为DEFINE_list，在shallowEncoder中的多个条件判别处似乎均是以integer值来考虑的。

总之：如何输入多feature呢？

谢谢～～～
===================================
encoders.py ShallowEncoder
```
use_feature = feature_idx != -1
use_id = max_id != -1
use_sparse_feature = sparse_feature_idx != -1

if isinstance(feature_idx, int) and use_feature:
feature_idx = [feature_idx]
if isinstance(feature_dim, int) and use_feature:
feature_dim = [feature_dim]
```
感觉如果把feature_idx和feature_dim改成DEFINE_list形式，比如default为[-1],[0]，这里几个判断以及一个list化的操作要修改掉？

Start by tracing tf_euler.get_dense_feature through run_loop and encoders.py, especially ShallowEncoder. Check how feature_idx and feature_dim are passed and how their integer checks interact with the proposed DEFINE_list inputs. Done means the accepted multi-feature input and the required ShallowEncoder behavior are clearly established and covered by an appropriate test or documentation update.

Written by the indexing model from the issue text.