Caffe學習記錄

基礎

Caffe (Convolution Architecture For Feature Embedding (Extraction))
網絡各層詳細解釋 http://caffe.berkeleyvision.org/tutorial/layers.html
Questions:
1. 從中斷處開始訓練
caffe train ­solver solver.prototxt ­snapshot train_1000.solverstate
https://github.com/BVLC/caffe/wiki/Training-and-Resuming
2. 可視化卷積層

name: "myconvnet"
input: "data"
input_dim: 1
input_dim: 1
input_dim: 256
input_dim: 256
layer {
    name: "conv"
    type: "Convolution"
    bottom: "data"
    top: "conv"
    convolution_param {
    num_output: 10
    kernel_size: 3
    stride: 1
    }
weight_filler {
    type: "gaussian"
    std: 0.01
    } 
bias_filler {
    type: "constant"
    value: 0
    }
    }

$ pip insall pydot
$ sudo apt­get install graphviz libgraphviz­dev
$ pip install pygraphviz
$ python /path/to/caffe/python/draw_net.py myconvnet.prototxt  myconvnet.png
3. 什麼樣的 layer 才能它的 bottom 和 top 可以是相同的名稱？
目前只有 Relu 層它的上下層可以使用相同名稱，因爲它是 element-wise 的，所以可以使用 in-place 的操作以節省內存
http://caffe.berkeleyvision.org/tutorial/interfaces.html
4. 測試網絡
impoort sys
sys.path.insert(0, '/path/to/caffe/python')
import numpy as np
import cv2
from pylab import * #畫圖
import caffe
#initialize

caffe.set_device(1)
caffe.set_mode_gpu()    #指定使用哪一塊GPU
#指定GPU計算
model_def = 'deploy.prototxt'
model_weight = 'net.cafffemodel'    #給定網絡模型
#給定參數
net = caffe.Net(model_def, model_weight, caffe.TEST)    

#給定phase =TEST,    那麼網絡只會向前計算，不會 backpropagation
Net instance:  Mnist  http://caffe.berkeleyvision.org/gathered/examples/mnist.html

Caffe_Net_and_Visualization

name: "LogReg"
layer {
    name: "mnist"
    type: "Data"
    top: "data"
    top: "label"
    data_param {
        source: "input_leveldb"
        batch_size: 64}
    } 

layer {
    name: "ip"
    type: "InnerProduct"
    bottom: "data"
    top: "ip"
    inner_product_param {
       num_output: 2}
    } 

layer {
    name: "loss"
    type: "SoftmaxWithLoss"
    bottom: "ip"
    bottom: "label"
    top: "loss"
    }



可視化
~/caffe/python/draw_net.py yout_net.prototxt yoursave.png