读一下官方tutorial：Blobs, Layers, and Nets
Blob
Caffe stores and communicates data using blobs. Blobs provide a unified memory interface holding data; e.g., batches of images, model parameters, and derivatives for optimization.
caffe通过blob存储和传递数据，blob为保持数据提供一个统一的接口，可以存储图像，模型参数，优化求导等。
既可以在CPU环境跑也可以在GPU环境跑，也就是说各州函数的代码要写两边，一遍CPU一遍GPU。
The conventional blob dimensions for batches of image data are number N x channel K x height H x width W. Blob memory is row-major in layout, so the last / rightmost dimension changes fastest. For example, in a 4D blob, the value at index (n, k, h, w) is physically located at index ((n * K + k) * H + h) * W + w.
卷积层blob，4维，标准的是（n,k,h,w）,对应batch数量，filter数量，高，宽。对非图片应用可以存2维的blob（N，D），作为全连接网络的输入输出。
Parameter blob dimensions vary according to the type and configuration of the layer. For a convolution layer with 96 filters of 11 x 11 spatial dimension and 3 inputs the blob is 96 x 3 x 11 x 11. For an inner product / fully-connected layer with 1000 output channels and 1024 input channels the parameter blob is 1000 x 1024.
参数也是通过blob表示的，比如卷积filter（也称kernel）的参数，（#c，#c_pre，f,f）.全连接网络的参数W。
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 elementwise transformations, normalize, load data, and compute losses like softmax and hinge.
layer包括的范围很广，卷积，池化，点乘，激活函数，还有其他elementwise的转化，标准化，读数据，计算loss
A layer takes input through bottom connections and makes output through top connections.
就像个pipeline一样。
Each layer type defines three critical computations: setup, forward, and backward.
每个layer都要定义3个关键的计算，设置，正向传播和反向传播（还要有CPU和GPU两个版本，要是没有GPU版本只能用CPU数据就得copy来再copy回去）
- Setup: initialize the layer and its connections once at model initialization.
- Forward: given input from bottom compute the output and send to the top.
- Backward: given the gradient w.r.t. the top output compute the gradient w.r.t. to the input and send to the bottom. A layer with parameters computes the gradient w.r.t. to its parameters and stores it internally.
Net
看到再说