框架疑问？
Open
- Dominant language
- Python
- Stars
- 132
- Forks
- 37
- PR merge metrics
- No merged PRs in 30d
Description
1、在进入空洞卷积之前为什么有一个普通的二维卷积？是必须的吗？意义何在？
2、一般普通的在文本上的卷积输入一本是[batch,seq_len,char_dim,1],为什么在这里这个二维卷积的输入是[bacth,1,seq_len,char_dim]?
Contributor guide
No contributing guide indexed for this repository
Research direction
No file, test, or entry point is named. Start by reading the repository's Python/TensorFlow convolution implementation alongside the paper, then determine whether the issue needs an explanatory documentation change; done means clearly answering both questions with the relevant tensor-shape and architectural context.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100