1. Inner Product - fully connected layer.
2. Dropout
3. Embed - for learning embeddings of one-hot encoded vector
(takes index as input).
Caffe_CommonLayer
發表評論
所有評論
還沒有人評論，想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章
1. Inner Product - fully connected layer.
2. Dropout
3. Embed - for learning embeddings of one-hot encoded vector
(takes index as input).