1 / 4

Deep CNN with Linear Support Vector Machines

Deep CNN with Linear Support Vector Machines. 预处理. 对训练集进行 Standardization ,即 对每个像素除以均值再除以方差。. Resize. Standardization. 48×48 Image. 原始图片. 卷积神经网络. 64*10*10. 32*42*42. 3072. 32*21*21. 3072. 32*20*20. 32*10*10. 64*5*5. 3*42*42. Softmax or SVM. Input. S imilarity transformation

hazina
Télécharger la présentation

Deep CNN with Linear Support Vector Machines

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Deep CNN with Linear Support Vector Machines

  2. 预处理 对训练集进行Standardization,即 对每个像素除以均值再除以方差。 Resize Standardization 48×48 Image 原始图片

  3. 卷积神经网络 64*10*10 32*42*42 3072 32*21*21 3072 32*20*20 32*10*10 64*5*5 3*42*42 Softmax or SVM Input Similarity transformation layer Two full connected layer Pooling Pooling Convolution Pooling Convolution Convolution 0.2 drop out 这一层是在一定范围内做随机相似变换。

  4. 参考文献 • ImageNet Classification with Deep Convolutional Neural Networks • Deep Learning using Linear Support Vector Machines

More Related