๋ณธ๋ฌธ ๋ฐ”๋กœ๊ฐ€๊ธฐ
728x90

๐Ÿ’ป Programming85

[pytorch] COCO Data Format ์ „์šฉ Custom Dataset ์ƒ์„ฑ Object Detection๊ณผ Segmentation ์—์„œ ํ”ํžˆ ์‚ฌ์šฉ๋˜๋Š” COCO dataformat ์ „์šฉ Customdataset์„ ์ƒ์„ฑํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ์†Œ๊ฐœํ•œ๋‹ค. ํ”ํžˆ ์•Œ๊ณ  ์žˆ๋Š” COCO ๋ฐ์ดํ„ฐ์…‹์ด ์žˆ๊ณ , ๋งŽ์€ ๋ฐ์ดํ„ฐ์…‹๋“ค์ด COCO data format ์„ ๋”ฐ๋ฅด๋Š”๋ฐ, ์ด๋Ÿฌํ•œ ๋ฐ์ดํ„ฐ์…‹์„ ์‚ฌ์šฉํ•˜๊ธฐ ์œ„ํ•ด Customdataset์„ ๊ตฌ์„ฑํ•˜๋Š” ๋ฐฉ๋ฒ•๊ณผ COCO API ์ธ Pycocotools ์‚ฌ์šฉ๋ฒ•์„ ์„ค๋ช…ํ•œ๋‹ค. COCO Data Format Detection task์—์„œ๋Š” Bounding box์˜ ์œ„์น˜์™€ class label์ด ํ•„์š”ํ•˜๊ณ  segmentation task ์—์„œ๋Š” segment mask ์ •๋ณด๊ฐ€ ํ•„์š”ํ•˜๋‹ค. ์ด๋Ÿฌํ•œ annotation ์ •๋ณด๋“ค์€ json ํ˜•ํƒœ๋กœ ์ œ๊ณต๋˜๊ณ , JSON ํŒŒ์ผ์—๋Š” Info, Licen.. 2022. 6. 4.
[pytorch] model ์— ์ ‘๊ทผํ•˜๊ธฐ, ํŠน์ • layer ๋ณ€๊ฒฝํ•˜๊ธฐ pytorch ๋ชจ๋ธ์— ์ ‘๊ทผํ•˜๊ณ  ํŠน์ • layer ๋˜๋Š” layer ๋‚ด๋ถ€์˜ ๋ชจ๋“ˆ์„ ๋ณ€๊ฒฝํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ์ •๋ฆฌํ•œ๋‹ค. - ์˜ˆ์‹œ ๋ชจ๋ธ : resnet50 import torch.nn as nn import torchvision.models as models model = models.resnet50(pretrained=True) 1. self.named_parameters() for name, param in model.layer1.named_parameters(): print(name,param.shape,sep=" ") 2. self.named_children() for name,ch in model.layer1.named_children(): print("name :",name) print("child :", ch.. 2022. 1. 5.
[python] ์ฝ”๋”ฉํ…Œ์ŠคํŠธ๋ฅผ ์œ„ํ•œ ํŒŒ์ด์ฌ ๋ฌธ๋ฒ• ์ •๋ฆฌ 1. deque - ์„ ์ž…์„ ์ถœ ํ from collections import deque deq = deque() deq.append(1) deq.appendleft(2) deq.pop() deq.popleft() deque.append(item): item์„ ๋ฐํฌ์˜ ์˜ค๋ฅธ์ชฝ ๋์— ์‚ฝ์ž… deque.appendleft(item): item์„ ๋ฐํฌ์˜ ์™ผ์ชฝ ๋์— ์‚ฝ์ž… deque.pop(): ๋ฐํฌ์˜ ์˜ค๋ฅธ์ชฝ ๋ ์—˜๋ฆฌ๋จผํŠธ๋ฅผ ๊ฐ€์ ธ์˜ค๋Š” ๋™์‹œ์— ๋ฐํฌ์—์„œ ์‚ญ์ œํ•œ๋‹ค. deque.popleft(): ๋ฐํฌ์˜ ์™ผ์ชฝ ๋ ์—˜๋ฆฌ๋จผํŠธ๋ฅผ ๊ฐ€์ ธ์˜ค๋Š” ๋™์‹œ์— ๋ฐํฌ์—์„œ ์‚ญ์ œํ•œ๋‹ค. deque.remove(item): item์„ ๋ฐํฌ์—์„œ ์ฐพ์•„ ์‚ญ์ œํ•œ๋‹ค. deque.rotate(num): ๋ฐํฌ๋ฅผ num๋งŒํผ ํšŒ์ „ํ•œ๋‹ค(์–‘์ˆ˜๋ฉด ์˜ค๋ฅธ์ชฝ, ์Œ์ˆ˜๋ฉด ์™ผ์ชฝ). 2. C.. 2022. 1. 5.
[pytorch] Custom dataset, dataloader ๋งŒ๋“ค๊ธฐ * dataset ํด๋” ๊ตฌ์กฐ minc2500 โ”œโ”€images โ”‚ โ”œโ”€brick โ”‚ โ”‚ โ”œโ”€brick_000000.jpg โ”‚ โ”‚ โ”œโ”€brick_000001.jpg โ”‚ โ”‚ โ”œโ”€... โ”‚ โ”œโ”€carpet โ”‚ โ”‚ โ”œโ”€carpet_000000.jpg โ”‚ โ”‚ โ”œโ”€... โ”‚ โ”œโ”€... โ”‚ โ”‚ โ”œโ”€... โ”‚ โ”‚ โ”œโ”€... ... ... ... โ”œโ”€labels โ”‚ โ”œโ”€train1.txt โ”‚ โ”œโ”€train2.txt โ”‚ โ”œโ”€... โ”‚ โ”œโ”€test1.txt โ”‚ โ”œโ”€test2.txt โ”‚ โ””โ”€... import os import os.path import torch import torch.utils.data as data from PIL import Image from torchvision import transforms imp.. 2022. 1. 2.
[ํ”„๋กœ๊ทธ๋ž˜๋จธ์Šค] 'ํŒŒ์ด์ฌ์„ ํŒŒ์ด์ฌ๋‹ต๊ฒŒ' ๊ฐ•์˜ ์ •๋ฆฌ ํ”„๋กœ๊ทธ๋ž˜๋จธ์Šค 'ํŒŒ์ด์ฌ์„ ํŒŒ์ด์ฌ๋‹ต๊ฒŒ' ๊ฐ•์˜ ์ •๋ฆฌ https://programmers.co.kr/learn/courses/4008 ํŒŒ์ด์ฌ์„ ํŒŒ์ด์ฌ๋‹ต๊ฒŒ ๋ณธ ๊ฐ•์˜๋Š” ํŒŒ์ด์ฌ ๋ฌธ๋ฒ•์„ ์ด๋ฏธ ์•Œ๊ณ  ์žˆ๋Š” ๋ถ„๋“ค์„ ๋Œ€์ƒ์œผ๋กœ ๋งŒ๋“ค์–ด์กŒ์Šต๋‹ˆ๋‹ค. ##### ์ด๋Ÿฐ ๋ถ„๋“ค๊ป˜ ์ถ”์ฒœํ•ฉ๋‹ˆ๋‹ค * ํŒŒ์ด์ฌ ๋ฌธ๋ฒ•์„ ์•Œ๊ณ  ๊ณ„์‹œ๋Š” ๋ถ„ * ์•Œ๊ณ ๋ฆฌ์ฆ˜ ๋ฌธ์ œ๋ฅผ ์กฐ๊ธˆ ๋” ์‰ฝ๊ฒŒ ํ’€๊ณ  ์‹ถ์€ ๋ถ„ * Python ์ฝ” programmers.co.kr 1. ๋ชซ๊ณผ ๋‚˜๋จธ์ง€ : divmod() ํ•จ์ˆ˜ ์‚ฌ์šฉ # ๋‹ค๋ฅธ ์–ธ์–ด a = 7 b = 5 print(a//b, a%b) # ํŒŒ์ด์ฌ a = 7 b = 5 print(*divmod(a,b)) 2. n์ง„๋ฒ•์œผ๋กœ ํ‘œ๊ธฐ๋œ string ์„ 10์ง„๋ฒ• ์ˆซ์ž๋กœ ๋ณ€ํ™˜ํ•˜๊ธฐ # ํŒŒ์ด์ฌ # base(5)์ง„๋ฒ•์œผ๋กœ ํ‘œ๊ธฐ๋œ num(3212)๋ฅผ 10์ง„๋ฒ•์œผ๋กœ ๋ณ€.. 2021. 8. 3.
[pytorch] DataParallel ๋กœ ํ•™์Šตํ•œ ๋ชจ๋ธ load model = custom_LSTM() model = torch.nn.DataParallel(model) with open(os.path.join('C:/Users/' + 'model_1.pt'), 'rb') as f: model.load_state_dict(torch.load(f)) DataParallel ๋กœ ํ•™์Šต์‹œํ‚จ ๋ชจ๋ธ์„ loadํ•ด์„œ ์‚ฌ์šฉํ•  ๋•Œ๋Š” ์œ„์™€ ๊ฐ™์ด torch.nn.DataParallel(model) ์ฝ”๋“œ๋ฅผ ์จ์ค˜์•ผ error ์—†์ด ์‚ฌ์šฉ ๊ฐ€๋Šฅํ•˜๋‹ค. 2021. 2. 17.
728x90