1. Inner Product - fully connected layer.
2. Dropout
3. Embed - for learning embeddings of one-hot encoded vector
(takes index as input).
Caffe_CommonLayer
最新推荐文章于 2021-11-15 01:25:03 发布
1. Inner Product - fully connected layer.
2. Dropout
3. Embed - for learning embeddings of one-hot encoded vector
(takes index as input).