如果make执行时，有“-I”或“--include-dir”参数，那么make就会在这个参数所指定的目录下去寻找。 如果目录/include（一般是：/usr/local/bin或/usr/include）存在的话，make也会去找。

如果要指定特定的Makefile，你可以使用make的“-f”和“--file”参数

在Makefile中的命令，必须要以[Tab]键开始

Data enters Caffe through data layers: they lie at the bottom of nets. Data can come from efficient databases (LevelDB or LMDB), directly from memory, or, when efficiency is not critical, from files on disk in HDF5 or common image formats. Common input preprocessing (mean subtraction, scaling, random cropping, and mirroring) is available by specifying TransformationParameters.

The BNLL (binomial normal log likelihood) layer computes the output as log(1 + exp(x)) for each input element x.

The POWER layer computes the output as (shift + scale * x) ^ power for each input element x.

specifies whether to leak the negative part by multiplying it with the slope value rather than setting it to 0.

ReLU / Rectified-Linear and Leaky-ReLU

In ACROSS_CHANNELS mode, the local regions extend across nearby channels, but have no spatial extent (i.e., they have shape local_size x 1 x 1). In WITHIN_CHANNEL mode, the local regions extend spatially, but are in separate channels (i.e., they have shape 1 x local_size x local_size). Each input value is divided by (1+(α/n)∑ix2i)β, where n is the size of each local region, and the sum is taken over the region centered at that value (zero padding is added where necessary).

whether to sum over adjacent channels (ACROSS_CHANNELS) or nearby spatial locaitons (WITHIN_CHANNEL)

the pooling method. Currently MAX, AVE, or STOCHASTIC

blobs_lr: 1 # learning rate multiplier for the filters blobs_lr: 2 # learning rate multiplier for the biases weight_decay: 1 # weight decay multiplier for the filters weight_decay: 0 # weight decay multiplier for the biases

n * c_o * h_o * w_o, where h_o = (h_i + 2 * pad_h - kernel_h) / stride_h + 1 and w_o likewise.

we restrict the connectivity of each filter to a subset of the input. Specifically, the input and output channels are separated into g groups, and the ith output group channels will be only connected to the ith input group channels.

specifies the number of pixels to (implicitly) add to each side of the input

Caffe layers and their parameters are defined in the protocol buffer definitions for the project in caffe.proto. The latest definitions are in the dev caffe.proto.

A copy and paste reference

Basic deletion options

Motion command reference

Ctrl-i: jump to your previous navigation location Ctrl-o: jump back to where you were

j: move down one line k: move up one line h: move left one character l: move right one character

A search reference /{string}: search for string t: jump up to a character f: jump onto a character *: search for other instances of the word under your cursor n: go to the next instance when you’ve searched for a string N: go to the previous instance when you’ve searched for a string ;: go to the next instance when you’ve jumped to a character ,: go to the previous instance when you’ve jumped to a character

You can then add your own comments and tags.