목차
728x90
Stride
- filer의 이동 간격 (보폭)을 조절하는 것
- Stride = 2
- input : \( n \times n\)
- filter : \( f \times f \)
- padding : \( p \)
- stride : \(s\)
- output : \(\left \lfloor \frac{n+2p-f}{s}+1\right \rfloor\times \left \lfloor\frac{n+2p-f}{s}+1\right \rfloor \) -> 소수로 나올시 내림
- filter가 딱맞지 않게 떨어지면 계산을 안하기 위해서 -> 보통은 딱 떨어지게 설정함
https://www.youtube.com/c/Deeplearningai
DeepLearningAI
Welcome to the official DeepLearning.AI YouTube channel! Here you can find the videos from our Coursera programs on machine learning as well as recorded events. DeepLearning.AI was founded in 2017 by machine learning and education pioneer Andrew Ng to fill
www.youtube.com
728x90
'Machine Learning > Model' 카테고리의 다른 글
| [ML] 순방향 신경망(FNN), 신경망의 설계 (0) | 2023.01.03 |
|---|---|
| [DATA] Custom Image Data 넣기 (0) | 2022.12.28 |
| [CNN] CNN 패딩 Padding (Convolution Neural Network) (2) | 2022.09.29 |
| [CNN] CNN 필터 filter (Convolutional Neural Network) (0) | 2022.09.29 |
| [ML] DBSCAN clustering Density-based spatial clustering of applicatoins with noise (0) | 2022.09.06 |
728x90
Stride
- filer의 이동 간격 (보폭)을 조절하는 것
- Stride = 2
- input : \( n \times n\)
- filter : \( f \times f \)
- padding : \( p \)
- stride : \(s\)
- output : \(\left \lfloor \frac{n+2p-f}{s}+1\right \rfloor\times \left \lfloor\frac{n+2p-f}{s}+1\right \rfloor \) -> 소수로 나올시 내림
- filter가 딱맞지 않게 떨어지면 계산을 안하기 위해서 -> 보통은 딱 떨어지게 설정함
https://www.youtube.com/c/Deeplearningai
DeepLearningAI
Welcome to the official DeepLearning.AI YouTube channel! Here you can find the videos from our Coursera programs on machine learning as well as recorded events. DeepLearning.AI was founded in 2017 by machine learning and education pioneer Andrew Ng to fill
www.youtube.com
728x90
'Machine Learning > Model' 카테고리의 다른 글
| [ML] 순방향 신경망(FNN), 신경망의 설계 (0) | 2023.01.03 |
|---|---|
| [DATA] Custom Image Data 넣기 (0) | 2022.12.28 |
| [CNN] CNN 패딩 Padding (Convolution Neural Network) (2) | 2022.09.29 |
| [CNN] CNN 필터 filter (Convolutional Neural Network) (0) | 2022.09.29 |
| [ML] DBSCAN clustering Density-based spatial clustering of applicatoins with noise (0) | 2022.09.06 |
