Constellation Identification Based on Pre-Training Model
碩士 === 大葉大學 === 電機工程學系 === 106 === In recent years, deep learning has been used to train a single complex problem, however, insufficient data will lead to overfitting. First, this paper purpose transfer learning and geometric transformation to generate one or more data and increases the number of tr...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2018
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/235ft3 |