목록분류 전체보기 (71)
잡동사니 블로그
[Python] OpenCV로 Contour 및 Color 검출 하기
import cv2 import numpy as np import matplotlib.pyplot as plt #이미지 불러오기 img = cv2.imread("test.png") #이미지 사이즈 조절 img=cv2.resize(img, dsize=(1000,500)) #이미지의 이진화를 위한 흑백으로 변경 new_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #캐니 에지 검출을 통한 에지 검출 edges = cv2.Canny(new_img, 50, 130) #이미지에서 외곽선(Contours)을 찾음. contours, _ = cv2.findContours(edges, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) #캐니 시각화 plt.ims..
[논문 읽기] Why Should I Trust You?": Explaining the Predictions of Any Classifier
https://arxiv.org/abs/1602.04938 "Why Should I Trust You?": Explaining the Predictions of Any Classifier Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when ch arxiv.org Abstract 대부분의 ML 모델은 Black..
[논문 읽기] Effectivs Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription
https://arxiv.org/abs/2002.05368 Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription There is now significant historical data available on decision making in organizations, consisting of the decision problem, what decisions were made, and how desirable the outcomes were. Using this data, it is possible to learn a surrogate model, and with arxiv.org Before RL(Rei..
[Python] pytorch와 sklearn의 train_test_split 활용하여 데이터 셋 나누기와 간단한 CNN
import torch from torchvision import datasets import torchvision.transforms as transforms import os import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split import torch.nn as nn import torch.optim as optim from torchvision.datasets import STL10 from torch.utils.data import DataLoader #\를 그대로 사용 path2data = r'.\dataset' #폴더 없을 경우 생성 if not os.path.exists(path2data): o..