HaiyongJiang

#include <iostream>
#include <lemon/smart_graph.h>
#include <lemon/lgf_reader.h>
#include <lemon/lgf_writer.h>
#include <lemon/capacity_scaling.h>

using namespace lemon;

int main() {
    SmartDigraph g;

HaiyongJiang

# suppose you have created a ui file called configwin.ui
cmake_minimum_required (VERSION 2.6)

project(tst)

find_package(Qt5Widgets)

set(CMAKE_AUTOMOC ON)
set(CMAKE_INCLUDE_CURRENT_DIR ON)

HaiyongJiang

sudo apt-get remove --purge vim vim-runtime vim-gnome vim-tiny vim-gui-common
 
sudo apt-get install liblua5.1-dev luajit libluajit-5.1 python-dev ruby-dev libperl-dev libncurses5-dev libatk1.0-dev libx11-dev libxpm-dev libxt-dev

sudo rm -rf /usr/local/share/vim

sudo rm /usr/bin/vim
 
sudo mkdir /usr/include/lua5.1/include
sudo cp /usr/include/lua5.1/*.h /usr/include/lua5.1/include/

HaiyongJiang

tmux cheat sheet

(C-x means ctrl+x, M-x means alt+x)

Prefix key

The default prefix is C-b. If you (or your muscle memory) prefer C-a, you need to add this to ~/.tmux.conf:

remap prefix to Control + a

HaiyongJiang

import numpy as np
import re
import sys

'''
Load a PFM file into a Numpy array. Note that it will have
a shape of H x W, not W x H. Returns a tuple containing the
loaded image and the scale factor from the file.
'''
def load_pfm(file):

HaiyongJiang

# [filter size, stride, padding]
#Assume the two dimensions are the same
#Each kernel requires the following parameters:
# - k_i: kernel size
# - s_i: stride
# - p_i: padding (if padding is uneven, right padding will higher than left padding; "SAME" option in tensorflow)
# 
#Each layer i requires the following parameters to be fully represented: 
# - n_i: number of feature (data layer has n_1 = imagesize )
# - j_i: distance (projected to image pixel distance) between center of two adjacent features

HaiyongJiang

tmux cheatsheet

As configured in my dotfiles.

start new:

tmux

start new with session name:

HaiyongJiang

CVPR2017 - 3D Reconstruction関連

• Stereo-Based 3D Reconstruction of Dynamic Fluid Surfaces by Global Optimization

  • ステレオベースでの動的流体表面の三次元復元

• KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences

  • 対応を用いない非剛体の三次元復元
  • ※KillingFusion...Killing Vector Field（キリングベクトル場）の融合

• Using Locally Corresponding CAD Models for Dense 3D Reconstructions From a Single Image

• CADモデルとの局所的な相関関係を用いた単一画像からの三次元復元

HaiyongJiang

import torch
from torch.autograd import Variable, Function

class Linear(Function):

    # Note that both forward and backward are @staticmethods
    @staticmethod
    # bias is an optional argument
    def forward(ctx, input, weight, bias=None):
        ctx.save_for_backward(input, weight, bias)