๋ณธ๋ฌธ ๋ฐ”๋กœ๊ฐ€๊ธฐ


Machine Learning

(15)
MDN https://www.katnoria.com/mdn/ https://www.katnoria.com/mdn/ Mixture Density Networks Supervised machine learning models learn the mapping between the input features (x) and the target values (y). The regression models predict continuous output such as house price or stock price whereas classification models predict www.katnoria.com https://kangbk0120.github.io/articles/2018-05/MDN Mixture Densit..
Hyperparameter Tuning Auto Keras dataset๋งŒ ์žˆ์œผ๋ฉด ๋ชจ๋ธ ์ œ์•ˆ๊นŒ์ง€ ๊ฐ€๋Šฅ Keras Tuner ๋‚ด๊ฐ€ ์ง€์ •ํ•œ ํŒŒ๋ผ๋ฏธํ„ฐ์—์„œ ๋ฒ”์œ„๋‚ด์—์„œ ์ ์ • ์ˆ˜์น˜ ์ œ์•ˆ ๊ฐ€๋Šฅ(Random search, Hyperband) https://github.com/keras-team/keras-tuner keras-team/keras-tuner Hyperparameter tuning for humans. Contribute to keras-team/keras-tuner development by creating an account on GitHub. github.com https://tykimos.github.io/2019/07/04/ISS_2nd_Deep_Learning_Conference_All_Together_tykim/ [2nd DLCAT..
Relu ํ•จ์ˆ˜ import numpy as np import matplotlib.pyplot as plt def relu(x) : return np.maximum(0, x) x = np.arange(-2, 2.4) plt.plot(x, relu(x)) plt.xlim(-2.0, 2) plt.ylim(-0.5, 1.5) plt.grid() plt.show()
Azure ML ์ˆœ์„œ 1. Azure ML ์ž‘์—… ์˜์—ญํ•˜๊ณ  ์—ฐ๊ฒฐ import azureml.core from azureml.core import Workspace # check core SDK version number print("Azure ML SDK Version: ", azureml.core.VERSION) # load workspace configuration from the config.json file in the current folder. ws = Workspace.from_config() print(ws.name, ws.location, ws.resource_group, ws.location, sep = '\t') 2. ์‹คํ—˜ ๋งŒ๋“ฌ - ๋ถˆ๋Ÿฌ์˜จ ์ž‘์—…์˜์—ญ ws์— ์‹คํ—˜ ์ด๋ฆ„ ์ •ํ•˜๊ณ  ๋งŒ๋“ฌ experiment_name ..
AKS ํด๋Ÿฌ์Šคํ„ฐ ๋งŒ๋“ค๊ธฐ Python : SDK ์‚ฌ์šฉํ•˜์—ฌ AKS ์—ฐ๊ฒฐ aks_target = AksCompute(ws,"myaks") deployment_config = AksWebservice.deploy_configuration(cpu_cores = 1, memory_gb = 1) service = Model.deploy(ws, "aksservice", [model], inference_config, deployment_config, aks_target) service.wait_for_deployment(show_output = True) print(service.state) print(service.get_logs()) https://azure.microsoft.com/ko-kr/pricing/ ๊ฐ€๊ฒฉ ์ฑ…์ • ๊ฐœ์š” - Azur..
์ผ€๋ผ์Šค ์ฐฝ์‹œ์ž์—๊ฒŒ ๋ฐฐ์šฐ๋Š” ๋”ฅ๋Ÿฌ๋‹ ๋ชฉ์ฐจ ๋ชฉ์ฐจ 1๋ถ€ ๋”ฅ๋Ÿฌ๋‹์˜ ๊ธฐ์ดˆ 1์žฅ ๋”ฅ๋Ÿฌ๋‹์ด๋ž€ ๋ฌด์—‡์ธ๊ฐ€? 1.1 ์ธ๊ณต ์ง€๋Šฅ๊ณผ ๋จธ์‹  ๋Ÿฌ๋‹, ๋”ฅ๋Ÿฌ๋‹ 1.1.1 ์ธ๊ณต ์ง€๋Šฅ 1.1.2 ๋จธ์‹  ๋Ÿฌ๋‹ 1.1.3 ๋ฐ์ดํ„ฐ์—์„œ ํ‘œํ˜„์„ ํ•™์Šตํ•˜๊ธฐ 1.1.4 ๋”ฅ๋Ÿฌ๋‹์—์„œ ‘๋”ฅ’์ด๋ž€ ๋ฌด์—‡์ผ๊นŒ? 1.1.5 ๊ทธ๋ฆผ 3๊ฐœ๋กœ ๋”ฅ๋Ÿฌ๋‹์˜ ์ž‘๋™ ์›๋ฆฌ ์ดํ•ดํ•˜๊ธฐ 1.1.6 ์ง€๊ธˆ๊นŒ์ง€ ๋”ฅ๋Ÿฌ๋‹์˜ ์„ฑ๊ณผ 1.1.7 ๋‹จ๊ธฐ๊ฐ„์˜ ๊ณผ๋Œ€ ์„ ์ „์„ ๋ฏฟ์ง€ ๋ง์ž 1.1.8 AI์— ๋Œ€ํ•œ ์ „๋ง 1.2 ๋”ฅ๋Ÿฌ๋‹ ์ด์ „: ๋จธ์‹  ๋Ÿฌ๋‹์˜ ๊ฐ„๋žตํ•œ ์—ญ์‚ฌ 1.2.1 ํ™•๋ฅ ์  ๋ชจ๋ธ๋ง 1.2.2 ์ดˆ์ฐฝ๊ธฐ ์‹ ๊ฒฝ๋ง 1.2.3 ์ปค๋„ ๋ฐฉ๋ฒ• 1.2.4 ๊ฒฐ์ • ํŠธ๋ฆฌ, ๋žœ๋ค ํฌ๋ ˆ์ŠคํŠธ, ๊ทธ๋ž˜๋””์–ธํŠธ ๋ถ€์ŠคํŒ… ๋จธ์‹  1.2.5 ๋‹ค์‹œ ์‹ ๊ฒฝ๋ง์œผ๋กœ 1.2.6 ๋”ฅ๋Ÿฌ๋‹์˜ ํŠน์ง• 1.2.7 ๋จธ์‹  ๋Ÿฌ๋‹์˜ ์ตœ๊ทผ ๋™ํ–ฅ 1.3 ์™œ ๋”ฅ๋Ÿฌ๋‹์ผ๊นŒ? ์™œ ์ง€๊ธˆ์ผ๊นŒ? 1.3.1 ํ•˜๋“œ์›จ์–ด 1.3.2 ๋ฐ์ดํ„ฐ..
Azure Machine Learning Azure ์ฒดํ—˜ ๊ณ„์ • ๊ฐ€์ž…ํ•จ : 12๊ฐœ์›” ์ธ๊ธฐ๋ฌด๋ฃŒ + 30์ผ ํฌ๋ ˆ๋”ง \224,930 12๊ฐœ์›” ๋ฌด๋ฃŒ ์ œํ’ˆ ํ•ญ์ƒ ๋ฌด๋ฃŒ? ์ œํ’ˆ Azure Machine Learning ์„œ๋น„์Šค ์„ค๋ช…์„œ https://docs.microsoft.com/ko-kr/azure/machine-learning/service/ Azure Machine Learning ์„œ๋น„์Šค ์„ค๋ช…์„œ - ์ž์Šต์„œ, API ์ฐธ์กฐ Azure Machine Learning Service๋Š” ์‹ ์†ํ•˜๊ฒŒ ๋ฐ์ดํ„ฐ๋ฅผ ์ค€๋น„ํ•˜๊ณ , ๊ธฐ๊ณ„ ํ•™์Šต ๋ชจ๋ธ์„ ํ•™์Šต ๋ฐ ๋ฐฐํฌํ•  ์ˆ˜ ์žˆ๋Š” SDK ๋ฐ ์„œ๋น„์Šค๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ์ž๋™ ํฌ๊ธฐ ์กฐ์ • ์ปดํ“จํŒ… ๋ฐ ํŒŒ์ดํ”„๋ผ์ธ์„ ์‚ฌ์šฉํ•˜์—ฌ ์ƒ์‚ฐ์„ฑ์„ ๊ฐœ์„ ํ•˜๊ณ  ๋น„์šฉ์„ ์ค„์ด์„ธ์š”. PyTorch, TensorFlow ๋ฐ scikit-learn๊ณผ ๊ฐ™์€ ์˜คํ”ˆ ์†Œ์Šค Python ..