Reputation: 3930
I'm a little lost as to the concept of caffe.
Is it for unsupervised feature extraction, for example, by feeding a lot of images without label?
Or is it a classifier when the inputs are set of values for certain fixed feature dimension?
Upvotes: 0
Views: 148
Reputation: 105
Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by the Berkeley Vision and Learning Center (BVLC) and by community contributors.
I'd advice to have look in this link, where some useful doc., codes Caffe Algor.and examples are found:
Upvotes: 0
Reputation: 5635
Caffe is a supervised learning algorithm which extracts the features on a fixed MxN dimensional image. The labels of these images are to be passed through during the training phase. Special care is to be taken to select the training input such that objects of two classes may not be present in the same image.
Upvotes: 1