반응형 데이터 분석/kaggle4 [kaggle] Fashion MNIST 필사 ① 출처 : https://www.kaggle.com/shivamb/how-autoencoders-work-intro-and-usecases https://www.kaggle.com/subinium/how-autoencoders-work-korean-ver https://www.kaggle.com/swhan0329/korver-how-autoencoders-work-intro-and-usecases 1. Autoencoder : 어떤 지도 없이도(즉, 레이블되어 있지 않은 훈련 데이터를 사용해서) 잠재표현(latent representation) 또는 코딩(일반적인 부호화)이라 부르는 입력 데이터의 밀집 표현을 학습할 수 있는 인공 신경망 일반적으로 입력보다 훨씬 낮은 차원을 가지므로 차원축소, 특히 시각화.. 2021. 8. 31. [kaggle] Fruits 360 출처 : https://www.kaggle.com/amadeus1996/fruits-360-transfer-learning-using-keras/data Fruits-360 - Transfer Learning using Keras Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources www.kaggle.com Transfer Learning (원래 코드는 Kaggle Kernels을 사용, 또한 현재 데이터는 업데이트됨) import os from os import listdir, makedirs from os.path import join, exists, expanduser ca.. 2021. 8. 28. [kaggle] image classification 필사 목록 1. Fruits 360 https://www.kaggle.com/amadeus1996/fruits-360-transfer-learning-using-keras Fruits-360 - Transfer Learning using Keras Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources www.kaggle.com 2. Fashion MNIST https://www.kaggle.com/shivamb/how-autoencoders-work-intro-and-usecases How Autoencoders Work: Intro and UseCases Explore and run mac.. 2021. 8. 25. [kaggle] Statoil/C-CORE Iceberg Classifier Challenge(수정중) 1. 데이터 불러오기 import numpy as np import pandas as pd from sklearn.model_selection import train_test_split from os.path import join as opj from matplotlib import pyplot as plt from mpl_toolkits.mplot3d import Axes3D import pylab plt.rcParams['figure.figsize'] = 10, 10 %matplotlib inline from google.colab import drive drive.mount('/content/drive') test = pd.read_json('/content/drive/MyDrive/data/tes.. 2021. 8. 25. 이전 1 다음 반응형
