LimHyungTae

#include <iostream>
#include <tf/tf.h>

int main(){

  /**< Declaration of quaternion */
  tf::Quaternion q;
  q.setW(1);
  q.setX(0);
  q.setY(0);

LimHyungTae

#include <iostream>
#include <tf/tf.h>

void coutQuaternion(tf::Quaternion q){
  std::cout<<q.getX()<<", "<<q.getX()<<", "<<q.getZ()<<", "<<q.getW()<<std::endl;
}

void coutTfMat(const tf::Matrix3x3& mat){
  std::cout<<mat[0][0]<<mat[0][1]<<mat[0][2]<<std::endl;
  std::cout<<mat[1][0]<<mat[1][1]<<mat[1][2]<<std::endl;

LimHyungTae

#include <iostream>
vector<float> ints = {0.01, 0.02, 0.03, 0.04};

void main(){
   // to avoid copying
  for (auto &i: ints){
    std::cout<< i <<std::endl;
  }
  // to prevent to change the value 
  for (auto const i: ints){

LimHyungTae

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.nn.functional as F

num_classes = 5
input = torch.randn(3, num_classes, requires_grad=True)
print(input)
target = torch.randint(num_classes, (3,), dtype=torch.int64)
print(target)

LimHyungTae

#!/bin/sh
gpu='1'
seq='0'
batch=6400
dir="/home/shapelim/RONet/0213fc_"
network_type='fc'
#
count="_1/"
python3.5 train.py --save_dir $dir$count --gpu $gpu --sequence_length $seq --batch_size $batch --network_type $network_type 
python3.5 test.py --load_model_dir $dir$count --gpu $gpu --sequence_length $seq --network_type $network_type

LimHyungTae

import h5py
import os
import numpy as np
import cv2
import matplotlib.pyplot as plt
from scipy import ndimage, misc
from scipy.stats import norm

def draw_histogram(x, n_bins, name):
    n, bins, patches = plt.hist(x, bins=n_bins, color=(0.0, 0.0, 0.5), density=True)

LimHyungTae

[global_config]

focus = system

handle_size = 1

tab_position = bottom

[keybindings]

LimHyungTae

# Normalize for Esential Matrix calaculation
pts_l_norm = cv2.undistortPoints(np.expand_dims(pts_l, axis=1), cameraMatrix=K_l, distCoeffs=None)
pts_r_norm = cv2.undistortPoints(np.expand_dims(pts_r, axis=1), cameraMatrix=K_r, distCoeffs=None)

E, mask = cv2.findEssentialMat(pts_l_norm, pts_r_norm, focal=1.0, pp=(0., 0.), method=cv2.RANSAC, prob=0.999, threshold=3.0)
points, R, t, mask = cv2.recoverPose(E, pts_l_norm, pts_r_norm)

M_r = np.hstack((R, t))
M_l = np.hstack((np.eye(3, 3), np.zeros((3, 1))))

LimHyungTae

#!/usr/bin/env python

import rospy
from std_msgs.msg import String
from sensor_msgs.msg import CompressedImage, Image
from cv_bridge import CvBridge
import cv2

import threading
import time

LimHyungTae

#include <iostream>
#include <pcl/common/transforms.h>
#include <pcl/point_types.h>
#include <pcl/point_cloud.h>


// Input: pcl::PointCloud source, namely cloud_src
//Output: Transformed pcl::PointCloud, namely pc_transformed, via 4x4 transformation matrix
int main(int argc, char **argv){