Coderx7

layers {
  name: "conv1A"
  type: CONVOLUTION
  bottom: "data"
  top: "conv1A"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {

Coderx7

Caffe + Ubuntu 12.04 64bit + CUDA 6.5 配置说明

本步骤能实现用Intel核芯显卡来进行显示， 用NVIDIA GPU进行计算。

1. 安装开发所需的依赖包

安装开发所需要的一些基本包

sudo apt-get install build-essential
sudo apt-get install vim cmake git
sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libboost-all-dev libhdf5-serial-dev

Coderx7

# In the name of GOD the most compassionate the most merciful
# Originally developed by Yasse Souri
# Just added the search for current directory so that users dont have to use command prompts anymore!
# and also shows the top 4 accuracies achieved so far, and displaying the highest in the plot title 
# Coded By: Seyyed Hossein Hasan Pour ([email protected])
# -------How to Use ---------------
# 1.Just place your caffe's traning/test log file (with .log extension) next to this script
# and then run the script.If you have multiple logs placed next to the script, it will plot all of them
# you may also copy this script to your working directory, where you generate/keep your train/test logs
# and easily execute the script and see the curve plotted. 

Coderx7

#!/usr/bin/python
# -*- coding: utf-8 -*-

# Author: Axel Angel, copyright 2015, license GPLv3.
# added mean subtraction so that, the accuracy can be reported accurately just like caffe when doing a mean subtraction
# Seyyed Hossein Hasan Pour
# [email protected]
# 7/3/2016 

import sys

Coderx7

#!/usr/bin/python

# Author: SeyyedHossein Hasanpour copyright 2017, license GPLv3.
# Seyyed Hossein Hasan Pour:
# [email protected]
# Changelog:
# 2015:
# initial code to calculate confusionmatrix by Axel Angel
# 7/3/2016:(adding new features-by-hossein) 
# added mean subtraction so that, the accuracy can be reported accurately just like caffe when doing a mean subtraction

Coderx7

#English: a simple handy snippet which I specifically wrote for calculating mean for a batch of images,
#in semi-vectorized and unvectorized fashion, along with the fully numpy example to test the output!
#
#Farsi: 
#mohasebe mean batchi az tasavir be sorate vectorized, unvectorized and semi vectorized
#age version vectorized error kambod hafeze dad, behtare az semi vectorized estefade beshe
#chon unvectorized ya hamoon loop mamoli sooratesh kheyli kame. 
#[email protected]
#Seyyed Hossein Hasanpour 
#1/12/2017 6:47 pm 

Coderx7

#In the name of God, the most compassionate the most merciful
#a non-vectorized and semi-vectorized implementation for calculating std for a batch of images.
#the semi-vectorized is the one, one should use, since its as fast as the numpy.std  
#Seyyed Hossein Hasan pour 
#[email protected]
#1/12/2017
import math
#unvectorized version --really slow!
def calc_std_classic(a):
    #sum all elements in each channel and divide by the number of elements

Coderx7

#In the name of God, the most compassionate the most merciful
import math
import numpy as np
#English: a simple handy snippet which I specifically wrote for calculating mean for a batch of images,
#in semi-vectorized and unvectorized fashion, along with the fully numpy example to test the output!
#Farsi: 
#mohasebe mean batchi az tasavir be sorate vectorized, unvectorized and semi vectorized
#age version vectorized error kambod hafeze dad, behtare az semi vectorized estefade beshe
#chon unvectorized ya hamoon loop mamoli sooratesh kheyli kame. 
#[email protected]

Coderx7

#in the name of God, the most compassionate the most merciful
#Seyyed Hossein Hasanpour 
#[email protected]
#script for zeropadding and normalizing CIFAR10 dataset (can also be used for CIFAR100)
import math
import caffe
import lmdb
import numpy as np
from caffe.proto import caffe_pb2
import cv2

Coderx7

#in the name of GOD
#pylearn2 cifar10 convertor to lmdb
#by:Seyyed Hossein Hasanpour
#[email protected] 
#2/14/2017
import numpy as np
import cPickle
import lmdb
import caffe
from caffe.proto import caffe_pb2