Skip to content

Instantly share code, notes, and snippets.

View SeungBack's full-sized avatar

Seunghyeok Back SeungBack

View GitHub Profile
@taegon
taegon / README.md
Created May 9, 2020 05:29
[박사 시작할 때 알았으면 하는 20가지]

박사 시작할 때 알았으면 하는 20가지

— 루시 테일러 박사

박사 학위 시작은 어렵다. 뒤돌아보면 시작할 때 알았으면 하는 것들이 있다. 여기, 새로운 대학원생들을 돕고자 옥스포드 대학교 동물학 현재 박사 과정 학생들과 박사후 연구원들로부터 제안 리스트를 만들었다.

  1. 건강한 워라밸(일-삶 균형)을 유지하라. 과정 동안 집중하여 번아웃 하기 보다는 균형을 잘 개발하여 일을 꾸준히 하는 편이 좋다. 자신을 돌보는 것이 성공의 열쇠다.

  2. 예상하는 바를 지도교수와 의논하라. 누구나 다르게 일한다. 필요한 것을 분명히 알고 지도교수와 일찍 소통해야 함께 생산적으로 협력할 수 있다.

###########################################################################
# Copyright (c) 2020 Qingfeng Xia <qingfeng.xia_ukaea.uk> #
# #
# This file is part of the FreeCAD CAx development system. #
# #
# This library is free software; you can redistribute it and/or #
# modify it under the terms of the GNU Library General Public #
# License as published by the Free Software Foundation; either #
# version 2 of the License, or (at your option) any later version. #
# #
@tejaskhot
tejaskhot / shapenet_synset_list
Created June 24, 2018 00:44
List of category names and their id in the ShapeNet dataset
04379243 table
03593526 jar
04225987 skateboard
02958343 car
02876657 bottle
04460130 tower
03001627 chair
02871439 bookshelf
02942699 camera
02691156 airplane
@jeasinema
jeasinema / weight_init.py
Last active November 22, 2024 07:17
A simple script for parameter initialization for PyTorch
#!/usr/bin/env python
# -*- coding:UTF-8 -*-
import torch
import torch.nn as nn
import torch.nn.init as init
def weight_init(m):
'''
# [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
@brunodoamaral
brunodoamaral / _dice.py
Last active March 16, 2024 18:00 — forked from JDWarner/_dice.py
Dice coefficient between two boolean NumPy arrays or array-like data. This is commonly used as a set similarity measurement (though note it is not a true metric; it does not satisfy the triangle inequality). The dimensionality of the input is completely arbitrary, but `im1.shape` and `im2.shape` much be equal. This Gist is licensed under the mod…
def dice(im1, im2, empty_score=1.0):
"""
Computes the Dice coefficient, a measure of set similarity.
Parameters
----------
im1 : array-like, bool
Any array of arbitrary size. If not boolean, will be converted.
im2 : array-like, bool
Any other array of identical size. If not boolean, will be converted.
Returns
@mattjmorrison
mattjmorrison / crop_and_resize.py
Created April 20, 2011 19:03
Resize and Crop images with Python and PIL
from PIL import Image, ImageChops
def trim(im, border):
bg = Image.new(im.mode, im.size, border)
diff = ImageChops.difference(im, bg)
bbox = diff.getbbox()
if bbox:
return im.crop(bbox)
def create_thumbnail(path, size):