Alex / OverFeat / VGG 中的卷积参数
2015-08-20 19:00
281 查看
研究需要,统计了一些经典CNN结构的卷积层参数。
Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. “Imagenet classification with deep convolutional neural networks.” Advances in neural information processing systems. 2012.
Sermanet, Pierre, et al. “Overfeat: Integrated recognition, localization and detection using convolutional networks.” arXiv preprint arXiv:1312.6229 (2013).
Simonyan, Karen, and Andrew Zisserman. “Very deep convolutional networks for large-scale image recognition.” arXiv preprint arXiv:1409.1556 (2014).
Alexnet
Layer | Input | Kernel | Output | Stride | Pad |
---|---|---|---|---|---|
1 | 256 * 3 * 227 * 227 | 48 * 3 * 11 * 11 | 256 * 48 * 55 * 55 | 4 | 0 |
2 | 256 * 48 * 27 * 27 | 128 * 48 * 5 * 5 | 256 * 128 * 27 * 27 | 1 | 2 |
3 | 256 * 128 * 13 * 13 | 192 * 128 * 3 * 3 | 256 * 192 * 13 * 13 | 1 | 1 |
4 | 256 * 192 * 13 * 13 | 192 * 192 * 3 * 3 | 256 * 192 * 13 * 13 | 1 | 1 |
5 | 256 * 192 * 13 * 13 | 192 * 192 * 3 * 3 | 256 * 192 * 13 * 13 | 1 | 1 |
Over Feat
Layer | Input | Kernel | Output | Stride | Pad |
---|---|---|---|---|---|
1 | 128 * 3 * 221 * 221 | 96 * 3 * 11 * 11 | 128 * 96 * 106 * 106 | 2 | 0 |
2 | 128 * 96 * 58 * 58 | 256 * 96 * 5 * 5 | 128 * 96 * 54 * 54 | 1 | 0 |
3 | 128 * 96 * 27 *27 | 512 * 96 * 3 * 3 | 128 * 512 * 27 * 27 | 1 | 1 |
4 | 128 * 512 * 27 * 27 | 1024 * 512 * 3 * 3 | 128 * 1024 * 27 * 27 | 1 | 1 |
5 | 128 * 1024 * 27 * 27 | 1024 * 1024 * 3 * 3 | 128 * 1024 * 27 * 27 | 1 | 1 |
VGG
Layer | Input | Kernel | Output | Stride | Pad |
---|---|---|---|---|---|
1 | 256 * 3 * 224 * 224 | 64 * 3 * 3 * 3 | 256 * 64 * 222 * 222 | 1 | 0 |
2 | 256 * 64 * 222 * 222 | 64 * 64 * 3 * 3 | 256 * 64 * 220 * 220 | 1 | 0 |
3 | 256 * 64 * 110 * 110 | 128 * 64 * 3 * 3 | 256 * 128 * 108 * 108 | 1 | 0 |
4 | 256 * 128 * 108 * 108 | 128 * 128 * 3 * 3 | 256 * 128 * 106 * 106 | 1 | 0 |
5 | 256 * 128 * 58 * 58 | 256 * 128 * 3 * 3 | 256 * 256 * 56 * 56 | 1 | 0 |
6 | 256 * 256 * 56 * 56 | 256 * 256 * 3 * 3 | 256 * 256 * 54 * 54 | 1 | 0 |
7 | 256 * 256 * 54 * 54 | 256 * 256 * 3 * 3 | 256 * 256 * 52 * 52 | 1 | 0 |
8 | 256 * 256 * 52 * 52 | 256 * 256 * 3 * 3 | 256 * 256 * 52 * 52 | 1 | 1 |
9 | 256 * 256 * 26 * 26 | 512 * 256 * 3 * 3 | 256 * 512 * 24 * 24 | 1 | 0 |
10 | 256 * 512 * 24 * 24 | 512 * 512 * 3 * 3 | 256 * 512 * 22 * 22 | 1 | 0 |
11 | 256 * 512 * 22 * 22 | 512 * 512 * 3 * 3 | 256 * 512 * 20 * 20 | 1 | 0 |
12 | 256 * 512 * 20 * 20 | 512 * 512 * 3 * 3 | 256 * 512 * 18 * 18 | 1 | 0 |
Output_size 与 Input_size/ Kernel_size / Padding / Stride 关系
Out_size=In_size−Kernel_size+2×Pad_sizeStride+1相关文章推荐
- UFLDL Exercise: Convolutional Neural Network
- Reducing the Dimensionality of Data with Neural Networks
- 卷积神经网络学习
- CNN: single-label to multi-label总结
- 总结:Large Scale Distributed Deep Networks
- 总结:One weird trick for parallelizing convolutional neural networks
- Deep Learning Face Attributes in the Wild
- 数字图像处理—图像滤波(中值滤波)
- FFT 快速傅里叶变换 初探
- Tiled convolutional neural networks(TCNN)
- 最受欢迎的新闻网站前15名(2014.10)
- 论文阅读_基于CNN的图像二值化_Robust Binarization for Video Text Recognition
- 在训练CNN的时候,各层back propagation的递推公式
- 对 CNN 中 dropout layer 的理解
- Caffe调参相关问题整理
- CNN
- CNN卷积神经网络推导和实现
- UFLDL上的ICA为什么一定要做PCA whiten
- 《Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification》阅读笔记与实现
- Large-scale Learning with SVM and Convolutional Nets(经典文献阅读)