学习交流PPT
8
How to use Caffe ?
Just 4 steps!! 1. Convert data (run a script) 2. Define net (edit prototxt) 3. Define solver (edit prototxt) 4. Train (with pretrained weights) (run a script)
学习交流rview:
Caffe(Convolutional Architecture For Feature Extraction) Created by Yangqing Jia(贾扬清), UC Berkeley. Written in C++, has Python and MATLAB interface.
the function to do a given task, and the composition of every layer’s
backward computes the gradient from the loss to learn the task.
name: "LogReg" layer { name: "mnist" type: "Data" top: "data" top: "label" data_param {
学习交流PPT
5
Layer
The layer is the essence of a model and the fundamental unit of computation.
Layers convolve filters, pool, take inner products, apply nonlinearities like rectified-linear and sigmoid and other element-wise transformations, normalize, load data, and compute losses like softmax and hinge.