New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Very Deep Convolutional Networks for Large-Scale Image Recognition #33

Open

chullhwan-song opened this issue Aug 1, 2018 · 1 comment

Labels

CNN

Owner

chullhwan-song commented Aug 1, 2018

https://arxiv.org/abs/1409.1556

Owner Author

chullhwan-song commented Aug 1, 2018

Very Deep Convolutional Networks for Large-Scale Image Recognition (VGG network)

특징

CNN
224x224 input RGB image
very small 3×3 filters in all convolutional layer
case vgg16 구조
- (2 conv layer + 1 max pooling layer)x2+(3 conv layer + 1 max pooling layer)x3 + 3개의 fc layers+softmax layer
relu activate function

depth to 16–19, weight layers.

vgg 16, vgg 19
alexnet과 마찬가지로 fc layer에서 deep feature
- sparse & semantic
alexnet보다 약 10%이상의 성능 향상을 보여줌
매우 강건한 network

성능

chullhwan-song added the CNN label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment