jeasinema

import torch
import torch.nn as nn
import numpy as np
import torch.nn.functional as F


class STN3d(nn.Module):
    def __init__(self):
        super(STN3d, self).__init__()
        self.conv1 = torch.nn.Conv1d(3, 64, 1)

jeasinema

#!/usr/bin/env python
# -*- coding:UTF-8 -*-
# File Name : xyz2uvd.py
# Creation Date : 26-07-2018
# Created By : Jeasine Ma [jeasinema[at]gmail[dot]com]

from pyquaternion import Quaternion
import numpy as np 

jeasinema

#! /usr/bin/env python
# coding=utf-8

__author__ = 'kingson_jeasinema'

import sys
import alfred
import requests

headers = {

jeasinema

import torch
from torchvision import transforms
import cv2
import numpy as np
import types
from numpy import random


def intersect(box_a, box_b):
    max_xy = np.minimum(box_a[:, 2:], box_b[2:])

jeasinema

import os
import numpy as np
import h5py as h5
from scipy.misc import imread
from struct import pack, unpack
import IPython
import math

# Extract pointcloud from rgb-d, then convert it into obj coordinate system(tsdf/poisson reconstructed object)
# In fact, merged_cloud.ply is exactly composed by pointclouds that transformed into this coordinate system

jeasinema

import numpy as np


def main_mxnet():
    import mxnet as mx 
    from mxnet import gluon, autograd 
    from mxnet.gluon import nn 
    
    net = nn.Sequential()
    with net.name_scope():

jeasinema

#!/usr/bin/env python
# -*- coding:UTF-8 -*-

# File Name : split_draw.py
# Purpose :
# Creation Date : 09-05-2018
# Last Modified : 2018年05月09日 星期三 21时06分55秒
# Created By : Jeasine Ma [jeasinema[at]gmail[dot]com]

import numpy as np

jeasinema

import argparse
import os
import time
import random

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import Dataset

jeasinema

#!/usr/bin/env python
# -*- coding:UTF-8 -*-
# File Name : face_morphing.py
# Creation Date : 04-04-2018
# Created By : Jeasine Ma [jeasinema[at]gmail[dot]com]

import cv2 
import json 
import numpy as np 

jeasinema

import torch
import torch.nn.functional as F
from torch.nn.parameter import Parameter
import numpy as np


class SpatialSoftmax(torch.nn.Module):
    def __init__(self, height, width, channel, temperature=None, data_format='NCHW'):
        super(SpatialSoftmax, self).__init__()
        self.data_format = data_format