ICFICE 2019
Current Result Document : 2 / 2
| 한글제목(Korean Title) |
Deep Learning Method for Animal Image Classification |
| 영문제목(English Title) |
Deep Learning Method for Animal Image Classification |
| 저자(Author) |
Abdur Razzaq Fayjie
Guangxing Wang
Hyun-Chang Lee
Seong-Yoon Shin
|
| 원문수록처(Citation) |
VOL 11 NO. 01 PP. 0402 ~ 0403 (2019. 06) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
In this paper, we propose an improved deep learning method based on a small data set for animal image classification. First, CNNs are used to create training models for small data sets, and use data sets to extend the data set of training sets. Second, using a pre-trained network for large data sets such as VGG16, the bottleneck of a small data set is extracted and stored in two NumPy files as a new training data set and a test data set, finally, train fully connected networks into new datasets.
|
| 키워드(Keyword) |
Deep Learning Method
CNN
Training Model
NumPy Files
|
| 파일첨부 |
PDF 다운로드
|
