๋ฐ˜์‘ํ˜•

์ „์ฒด ๊ธ€ 177

[PyTorch] make_grid๋กœ ์—ฌ๋Ÿฌ ๊ฐœ์˜ ์ด๋ฏธ์ง€ ํ•œ๋ฒˆ์— plotํ•˜๊ธฐ

Official Docs: https://pytorch.org/vision/main/generated/torchvision.utils.make_grid.html make_grid — Torchvision main documentation Shortcuts pytorch.org ์—ฌ๋Ÿฌ๊ฐœ์˜ ์ด๋ฏธ์ง€๋ฅผ ํ•ฉ์ณ์„œ ํ•˜๋‚˜์˜ grid๋กœ ๋งŒ๋“ค์–ด์ฃผ๋Š” torchvision.utils.make_grid ํ•จ์ˆ˜๋ฅผ ์†Œ๊ฐœํ•ด ๋ณด๊ณ ์ž ํ•œ๋‹ค. tensor (Tensor or list) : grid๋ฅผ ๋งŒ๋“ค ์ด๋ฏธ์ง€๋“ค. 4D mini-batch Tensor (B x C x H x W) ํ˜น์€ ๋™์ผํ•œ ํฌ๊ธฐ์˜ image๋ฅผ ๋‹ด๊ณ  ์žˆ๋Š” list๋ฅผ ์ค„ ์ˆ˜ ์žˆ๋‹ค. nrow (int, optional) : grid์˜ ํ–‰ ๊ฐฏ์ˆ˜๋ฅผ ์ง€์ •ํ•ด์ค„ ์ˆ˜ ์žˆ๋‹ค. ์—ด ๊ฐฏ์ˆ˜๋Š” ์ž..

[HuggingFace] Trainer ์‚ฌ์šฉ๋ฒ•

Official Docs: https://huggingface.co/docs/transformers/v4.19.2/en/main_classes/trainer Trainer When using gradient accumulation, one step is counted as one step with backward pass. Therefore, logging, evaluation, save will be conducted every gradient_accumulation_steps * xxx_step training examples. huggingface.co Trainer class๋Š” ๋ชจ๋ธํ•™์Šต๋ถ€ํ„ฐ ํ‰๊ฐ€๊นŒ์ง€ ํ•œ ๋ฒˆ์— ํ•ด๊ฒฐํ•  ์ˆ˜ ์žˆ๋Š” API๋ฅผ ์ œ๊ณตํ•œ๋‹ค. ๋‹ค์Œ์˜ ์‚ฌ์šฉ์˜ˆ์‹œ๋ฅผ ๋ณด๋ฉด ์ง๊ด€์ ์œผ๋กœ ์ดํ•ดํ•  ์ˆ˜ ์žˆ๋‹ค. f..

์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ์ •๋ฆฌ + Python ๊ตฌํ˜„ (Bubble sort, Selection sort, Insertion sort, Merge sort, Quick sort)

$O(n^2)$ ์‹คํ–‰์‹œ๊ฐ„์„ ๊ฐ–๋Š” ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ์„ธ ๊ฐ€์ง€์™€ $O(n\log n)$ ์‹คํ–‰์‹œ๊ฐ„์„ ๊ฐ–๋Š” ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ๋‘ ๊ฐ€์ง€, ๊ทธ๋ฆฌ๊ณ  ๊ฐ ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜์˜ ํŒŒ์ด์ฌ ์ฝ”๋“œ๋ฅผ ์ •๋ฆฌํ–ˆ๋‹ค. ๋ชฉ์ฐจ $O(n^2)$ ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜ Bubble sort Selection sort Insertion sort $O(n\log n)$ ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜ Merge sort Quick sort ๋‹ค์Œ ์‚ฌ์ดํŠธ์—์„œ ๊ฐ ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜์˜ ์‹œ๊ฐํ™”๋ฅผ ํ•œ๋ˆˆ์— ํ™•์ธํ•  ์ˆ˜ ์žˆ๋‹ค. Comparison Sorting Visualization www.cs.usfca.edu $O(n^2)$ ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ๋‹ค์Œ์˜ ์„ธ ์ •๋ ฌ ์•Œ๊ณ ๋ฆฌ์ฆ˜์€ swap ํ•จ์ˆ˜๋ฅผ ์‚ฌ์šฉํ•œ๋‹ค. def swap(arr, i, j): temp = arr[i] arr[i] = arr[j] arr[j] = ..

[๋”ฅ๋Ÿฌ๋‹ ๋…ผ๋ฌธ๋ฆฌ๋ทฐ + ์ฝ”๋“œ] What uncertainties do we need in Bayesian deep learning for computer vision? (NeurIPS 2017)

๋…ผ๋ฌธ: https://arxiv.org/pdf/1703.04977.pdf Epistemic uncertainty์™€ aleatoric uncertainty๋ฅผ ๋™์‹œ์— ์ธก์ •ํ•  ์ˆ˜ ์žˆ๊ฒŒ ํ•ด์ฃผ๋Š” ๋ฐฉ๋ฒ•์„ ์†Œ๊ฐœํ•œ ๋…ผ๋ฌธ์ด๋‹ค. ๋…ผ๋ฌธ์„ ๊ฐ„๋‹จํžˆ ์ •๋ฆฌํ•˜๊ณ  PyTorch ์ฝ”๋“œ๋ฅผ ํ•จ๊ป˜ ์†Œ๊ฐœํ•˜๊ณ ์ž ํ•œ๋‹ค. Uncertainty์˜ ์ข…๋ฅ˜ 1. Epistemic uncertainty (=Model uncertainty) ๋ชจ๋ธ๊ตฌ์กฐ๋‚˜ ํ•™์Šต๊ณผ์ •์—์„œ ๋ฐœ์ƒํ•˜๋Š” uncertainty์ด๋‹ค. ๋ชจ๋ธ์ด ์ถฉ๋ถ„ํžˆ ํ•™์Šต๋˜์ง€ ์•Š์•˜์„ ์ˆ˜๋„ ์žˆ๊ณ , ์ „์ฒด ๋ฐ์ดํ„ฐ ๋ถ„ํฌ๋ฅผ ๋‹ค ํ•™์Šตํ•˜์ง€ ๋ชปํ–ˆ์„ ์ˆ˜๋„ ์žˆ๊ณ , ๋ชจ๋ธ์˜ ๊ตฌ์กฐ๊ฐ€ ์ง€๋‚˜์น˜๊ฒŒ ๋‹จ์ˆœํ•˜๊ฑฐ๋‚˜ ๋ณต์žกํ•  ์ˆ˜๋„ ์žˆ๋‹ค. Epistemic uncertainty๋Š” ๋ฐ์ดํ„ฐ์…‹ ๋ณด๊ฐ•, ๋ชจ๋ธ ๊ตฌ์กฐ ์ˆ˜์ •, ํ•™์Šต ๋ฐฉ๋ฒ• ๋ณ€๊ฒฝ ๋“ฑ์˜ ๋ฐฉ๋ฒ•์œผ๋กœ ์ค„์ผ ์ˆ˜ ..

๋”ฅ๋Ÿฌ๋‹ ๋…ผ๋ฌธ ์ €์ž๋“ค์˜ paper talk ์•„์นด์ด๋ธŒ ์‚ฌ์ดํŠธ Papertalk

https://papertalk.org/index Papertalk - the platform for scientific paper presentations You have to login to use this feature. papertalk.org ๋”ฅ๋Ÿฌ๋‹ ๋…ผ๋ฌธ ์ €์ž๋“ค์˜ paper talk์„ ๋ชจ์•„ ๋‘” ์‚ฌ์ดํŠธ์ด๋‹ค. ์ตœ์‹  ๋…ผ๋ฌธ, Journal/Conference ๋ณ„, ์ธ๊ธฐ์ˆœ, ํ‚ค์›Œ๋“œ ๋ณ„๋กœ ๋…ผ๋ฌธ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ๊ณ , ๋””์ž์ธ์ด ๋งค์šฐ ๊น”๋”ํ•˜๊ฒŒ ์ •๋ฆฌ๋˜์–ด ์žˆ์–ด์„œ ๋…ผ๋ฌธ์˜ overview๊ฐ€ ํ•„์š”ํ•  ๋•Œ ์œ ์šฉํ•˜๊ฒŒ ์‚ฌ์šฉ๋  ์ˆ˜ ์žˆ์„ ๊ฒƒ ๊ฐ™๋‹ค. ๐Ÿ˜ฎ๐Ÿ‘ ๊ธฐ๋ณธ์ ์œผ๋กœ๋Š” ํ•™ํšŒ์˜ ๋ฐœํ‘œ์˜์ƒ์ด ์˜ฌ๋ผ๊ฐ€์žˆ๊ณ , ์ €์ž๊ฐ€ ์ง์ ‘ ์š”์ฒญํ•˜๋ฉด ๋‹ค๋ฅธ ์˜์ƒ์œผ๋กœ ๋ณ€๊ฒฝํ•  ์ˆ˜ ์žˆ๋‹ค๊ณ  ํ•œ๋‹ค. ๋‹ค๋งŒ 2021๋…„๊นŒ์ง€์˜ paper talk์€ ์•„์นด์ด๋ธŒ๊ฐ€ ๋˜์–ด ์žˆ๋Š”๋ฐ, 2022๋…„..

[๋”ฅ๋Ÿฌ๋‹ ๋…ผ๋ฌธ๋ฆฌ๋ทฐ] Momentum Contrast for Unsupervised Visual Representation Learning (MoCo) (CVPR 2020)

SimCLR์™€ ํ•จ๊ป˜ ๊ฐ€์žฅ ์œ ๋ช…ํ•œ contrastive learning-based self-supervised learning ๋…ผ๋ฌธ์ด๋‹ค. CVPR 2020์—์„œ ๋ฐœํ‘œ๋œ ๋…ผ๋ฌธ์ด๊ณ , Kaiming He๊ฐ€ ์ €์ž๋กœ ์ฐธ์—ฌํ•˜์˜€๋‹ค. Paper, Code GitHub - facebookresearch/moco: PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722 PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722 - GitHub - facebookresearch/moco: PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722 gith..

[๋”ฅ๋Ÿฌ๋‹ ๋…ผ๋ฌธ๋ฆฌ๋ทฐ + ์ฝ”๋“œ] Uncertainty-Driven Loss for Single Image Super-Resolution (NeurIPS 2021)

NeurIPS 2021์—์„œ ๋ฐœํ‘œ๋œ ๋…ผ๋ฌธ์œผ๋กœ, single image super-resolution (SISR)์„ ์œ„ํ•ด uncertainty๋ฅผ ์ด์šฉํ•œ loss๋ฅผ ์ œ์•ˆํ–ˆ๋‹ค. ๋งจ ์•„๋ž˜์— PyTorch๋กœ ๊ตฌํ˜„๋œ ์ฝ”๋“œ๋ฅผ ์ •๋ฆฌํ•ด ๋†“์•˜๋‹ค. ๋…ผ๋ฌธ ๋งํฌ: https://papers.nips.cc/paper/2021/file/88a199611ac2b85bd3f76e8ee7e55650-Paper.pdf Supplementary: https://papers.nips.cc/paper/2021/file/88a199611ac2b85bd3f76e8ee7e55650-Supplemental.pdf Homepage: https://see.xidian.edu.cn/faculty/wsdong/Projects/UDL-SR.htm https:/..

LaTeX figure ๋„ฃ๊ธฐ

LaTex์—์„œ figure์„ ์‚ฌ์šฉํ•˜๊ธฐ ์œ„ํ•ด์„œ๋Š” graphics package๋ฅผ ์„ ์–ธํ•ด์•ผ ํ•œ๋‹ค. \usepackage{graphicx} LaTeX์— ๋“ค์–ด๊ฐ€๋Š” figure์€ ์ผ๋ฐ˜์ ์œผ๋กœ ๋‹ค์Œ๊ณผ ๊ฐ™์ด ๊ตฌ์„ฑ๋œ๋‹ค. \begin{figure}[!t] \centerline{\includegraphics[width=\columnwidth]{figure.png}} \caption{This is the first figure.} \label{figure_1} \end{figure} Figure์˜ ๋‚ด์šฉ์€ \begin{figure} ๊ณผ \end{figure} ์‚ฌ์ด์— ์œ„์น˜ํ•œ๋‹ค. [!t]๋Š” figure์ด ๋†“์ผ ์ˆ˜ ์žˆ๋Š” ์œ„์น˜๋ฅผ ์˜๋ฏธํ•œ๋‹ค. ๋‹ค์Œ ์ค‘ ํ•˜๋‚˜ ์ด์ƒ์˜ option์„ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋‹ค. ๋‹จ, ์ˆœ์„œ๋Œ€๋กœ ์ ์šฉ๋˜๋Š” ๊ฒƒ์€ ์•„๋‹ˆ๋‹ค. ๋Œ€๋ถ€..

[๋ฐฑ์ค€ 16926๋ฒˆ] ๋ฐฐ์—ด ๋Œ๋ฆฌ๊ธฐ 1 (python/ํŒŒ์ด์ฌ)

๋ฌธ์ œ ์„ค๋ช…์„ ๊ทธ๋Œ€๋กœ ๊ตฌํ˜„ํ–ˆ๋”๋‹ˆ ์‹œ๊ฐ„์ดˆ๊ณผ๊ฐ€ ๋– ์„œ, ์ข€๋” ํšจ์œจ์ ์ธ ๋ฐฉ๋ฒ•์„ ๊ณ ์•ˆํ•ด์•ผ ํ–ˆ์Œ. ๐ŸŒผ ๋ฌธ์ œ ๋งํฌ https://www.acmicpc.net/problem/16926 16926๋ฒˆ: ๋ฐฐ์—ด ๋Œ๋ฆฌ๊ธฐ 1 ํฌ๊ธฐ๊ฐ€ N×M์ธ ๋ฐฐ์—ด์ด ์žˆ์„ ๋•Œ, ๋ฐฐ์—ด์„ ๋Œ๋ ค๋ณด๋ ค๊ณ  ํ•œ๋‹ค. ๋ฐฐ์—ด์€ ๋‹ค์Œ๊ณผ ๊ฐ™์ด ๋ฐ˜์‹œ๊ณ„ ๋ฐฉํ–ฅ์œผ๋กœ ๋Œ๋ ค์•ผ ํ•œ๋‹ค. A[1][1] ← A[1][2] ← A[1][3] ← A[1][4] ← A[1][5] ↓ ↑ A[2][1] A[2][2] ← A[2][3] ← A[2][4] A[2][5] www.acmicpc.net ํ‹ฐ์–ด: ์‹ค๋ฒ„ I ๋ถ„๋ฅ˜: ๊ตฌํ˜„ โ— TRIAL 1. ๋”๋ณด๊ธฐ ์ฝ”๋“œ def move(v1, v2, direction, arr, ans): if direction == 'l': x = v1[0] for y in r..

[๋ฐฑ์ค€ 2504๋ฒˆ] ๊ด„ํ˜ธ์˜ ๊ฐ’ (python/ํŒŒ์ด์ฌ)

์กฐ๊ฑด์„ ์—„์ฒญ ์ถ”๊ฐ€ํ•ด์„œ ํ‘ผ ๊ตฌํ˜„ ๋ฌธ์ œ. ์ฝ”๋“œ๊ฐ€ ๋„ˆ๋ฌด ๋”๋Ÿฌ์šด๋ฐ ๋” ์ข‹์€ ํ’€์ด ๋ฐฉ๋ฒ•์ด ์žˆ์„ ๋“ฏ ๐ŸŒผ ๋ฌธ์ œ ๋งํฌ https://www.acmicpc.net/problem/2504 2504๋ฒˆ: ๊ด„ํ˜ธ์˜ ๊ฐ’ 4๊ฐœ์˜ ๊ธฐํ˜ธ ‘(’, ‘)’, ‘[’, ‘]’๋ฅผ ์ด์šฉํ•ด์„œ ๋งŒ๋“ค์–ด์ง€๋Š” ๊ด„ํ˜ธ์—ด ์ค‘์—์„œ ์˜ฌ๋ฐ”๋ฅธ ๊ด„ํ˜ธ์—ด์ด๋ž€ ๋‹ค์Œ๊ณผ ๊ฐ™์ด ์ •์˜๋œ๋‹ค. ํ•œ ์Œ์˜ ๊ด„ํ˜ธ๋กœ๋งŒ ์ด๋ฃจ์–ด์ง„ ‘()’์™€ ‘[]’๋Š” ์˜ฌ๋ฐ”๋ฅธ ๊ด„ํ˜ธ์—ด์ด๋‹ค. ๋งŒ์ผ www.acmicpc.net ํ‹ฐ์–ด: ์‹ค๋ฒ„ I ๋ถ„๋ฅ˜: ๊ตฌํ˜„, ์ž๋ฃŒ๊ตฌ์กฐ, ์Šคํƒ, ์žฌ๊ท€ โ— TRIAL 1. ๋”๋ณด๊ธฐ ์ฝ”๋“œ inputs = list(input()) couple = {'(': ')', '[': ']'} value = {'(': 2, '[': 3} while len(inputs) != 1: ctr = 0 new_in..

๋ฐ˜์‘ํ˜•