주로 사용하는 seed 고정 코드
pytorch lightning framework 사용하는 경우를 예시로 작성
py파일 순차적 수행
모델 학습을 위해 만들어진 여러 py파일 리스트로 지정 후 수행
Docker build & use 다른 서버에서 사용
특정 폴더 루트 예시: /home/tmp/ml
Dockerfile 생성
먼저, 도커 이미지 생성을 원하는 특정 폴더(/home/tmp/ml)에 Dockerfile을 만들어 해당 폴더를 도커 이미지에 포함.
```
Python 3.9을 사용하는 베이스 이미지 설정 (필요한 환경에 맞게 선택)
FROM python:3.9-slim
label Unique RGB 확인 / Image Channel 확인
label Unique RGB 확인
Ubuntu Server admin
우분투 서버 대기모드/절전모드 확인
Folder Split
폴더 나누기(Folder Split)
전체 데이터셋 폴더 -> Train, Validation, Test 폴더로 나누기
DeepLearning.AI TensorFlow Developer Course 2-3
Building….
DeepLearning.AI TensorFlow Developer Course 2-2
[Coursera] DeepLearning.AI TensorFlow Developer ( Tensorflow In Practice ) 강의 정리
Course 1 : Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
Course 2 : Convolutional Neural Networks in TensorFlow
- Week 1 - Exploring a Larger Dataset
- Week 2 - Augmentation: A technique to avoid overfitting
- Week 3 - Transfer Learning
- Week 4 - Multiclass Classifications
DeepLearning.AI TensorFlow Developer Course 2-1
[Coursera] DeepLearning.AI TensorFlow Developer ( Tensorflow In Practice ) 강의 정리
Course 1 : Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
Course 2 : Convolutional Neural Networks in TensorFlow
- Week 1 - Exploring a Larger Dataset
- Week 2 - Augmentation: A technique to avoid overfitting
- Week 3 - Transfer Learning
- Week 4 - Multiclass Classifications
DeepLearning.AI TensorFlow Developer Course 1-4
[Coursera] DeepLearning.AI TensorFlow Developer ( Tensorflow In Practice ) 강의 정리
Course 1 : Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
- Week 1 - A New Programming Paradigm
- Week 2 - Introduction to Computer Vision
- Week 3 - Enhancing Vision with Convolutional Neural Networks
- Week 4 - Using Real-world Images