We introduce low-level TensorFlow and work our way through the necessary concepts and APIs so as to be able to write distributed machine learning models. Given a TensorFlow model, we explain how to scale out the training of that model and offer high-performance predictions using Cloud Machine Learning Engine. Course Objectives: Create machine learning models in TensorFlow Use the TensorFlow libraries to solve numerical problems Troubleshoot and debug common TensorFlow code pitfalls Use tf.estimator to create, train, and evaluate an ML model Train, deploy, and productionalize ML models at scale with Cloud ML Engine
이 강좌는 Machine Learning with TensorFlow on Google Cloud Platform 전문 분야의 일부입니다.
Intro to TensorFlow
제공자:
About this Course
최근 조회 61,064회
귀하가 습득할 기술
Application Programming Interfaces (API)EstimatorMachine LearningTensorflowCloud Computing
강의 계획 - 이 강좌에서 배울 내용
주
1완료하는 데 7분 필요
Introduction
The tool we will use to write machine learning programs is TensorFlow and so in this course, we will introduce you to TensorFlow. In the first course, you learned how to formulate business problems as machine learning problems and in the second course, you learned how machine works in practice and how to create datasets that you can use for machine learning. Now that you have the data in place, you are ready to get started writing machine learning programs.
2개 동영상 (총 7분)
완료하는 데 3시간 필요
Core TensorFlow
We will introduce you to the core components of TensorFlow and you will get hands-on practice building machine learning programs. You will compare and write lazy evaluation and imperative programs, work with graphs, sessions, variables, as finally debug TensorFlow programs.
19개 동영상 (총 72분), 4 quizzes
19개의 동영상
What is TensorFlow2m
Benefits of a Directed Graph5m
TensorFlow API Hierarchy3m
Lazy Evaluation4m
Graph and Session4m
Evaluating a Tensor2m
Visualizing a graph2m
Tensors6m
Variables6m
Lab Intro: Writing low-level TensorFlow programs16
Lab Solution8m
Introduction5m
Shape problems3m
Fixing shape problems2m
Data type problems1m
Debugging full programs4m
Intro: Debugging full programs15
Demo: Debugging Full Programs3m
3개 연습문제
What is TensorFlow?2m
Graphs and Sessions8m
Core TensorFlow20m
주
2완료하는 데 4시간 필요
Estimator API
In this module we will walk you through the Estimator API.
18개 동영상 (총 67분), 4 quizzes
18개의 동영상
Estimator API3m
Pre-made Estimators5m
Demo: Housing Price Model1m
Checkpointing1m
Training on in-memory datasets2m
Lab Intro: Estimator API39
Lab Solution: Estimator API10m
Train on large datasets with Dataset API8m
Lab Intro: Scaling up TensorFlow ingest using batching35
Lab Solution: Scaling up TensorFlow ingest using batching5m
Big jobs, Distributed training6m
Monitoring with TensorBoard3m
Demo: TensorBoard UI28
Serving Input Function5m
Recap: Estimator API1m
Lab Intro: Creating a distributed training TensorFlow model with Estimator API51
Lab Solution: Creating a distributed training TensorFlow model with Estimator API7m
1개 연습문제
Estimator API18m
주
3완료하는 데 2시간 필요
Scaling TensorFlow models
I’m here to talk about how you would go about taking your TensorFlow model and training it on GCP’s managed infrastructure for machine learning model training and deployed.
6개 동영상 (총 29분), 1 reading, 2 quizzes
6개의 동영상
Why Cloud AI Platform?6m
Train a Model2m
Monitoring and Deploying Training Jobs2m
Lab Intro: Scaling TensorFlow with Cloud AI Platform50
Lab Solution: Scaling TensorFlow with Cloud AI Platform16m
1개의 읽기 자료
Cloud ML Engine is now Cloud AI Platform10m
1개 연습문제
Cloud AI Platform10m
완료하는 데 2분 필요
Summary
Here we summarize the TensorFlow topics we covered so far in this course. We'll revisit core TensorFlow code, the Estimator API, and end with scaling your machine learning models with Cloud Machine Learning Engine.
1개 동영상 (총 2분)
1개의 동영상
Summary2m
4.5
176개의 리뷰32%
이 강좌를 수료한 후 새로운 경력 시작하기
35%
이 강좌를 통해 확실한 경력상 이점 얻기
Intro to TensorFlow의 최상위 리뷰
pretty good. some of the code in the last lab could be better explained. also please debug the cloud shell, as it does not always show the "web preview" button ;) otherwise, good job!
Nice introduce, might be more on introduce the model structure, because I still need to read additional notes to locate how to train my deep learning model online.
Google 클라우드 정보
We help millions of organizations empower their employees, serve their customers, and build what’s next for their businesses with innovative technology created in—and for—the cloud. Our products are engineered for security, reliability, and scalability, running the full stack from infrastructure to applications to devices and hardware. Our teams are dedicated to helping customers apply our technologies to create success.
Machine Learning with TensorFlow on Google Cloud Platform 전문 분야 정보
What is machine learning, and what kinds of problems can it solve? What are the five phases of converting a candidate use case to be driven by machine learning, and why is it important that the phases not be skipped? Why are neural networks so popular now? How can you set up a supervised learning problem and find a good, generalizable solution using gradient descent and a thoughtful way of creating datasets? Learn how to write distributed machine learning models that scale in Tensorflow, scale out the training of those models. and offer high-performance predictions. Convert raw data to features in a way that allows ML to learn important characteristics from the data and bring human insight to bear on the problem. Finally, learn how to incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems. You will experiment with end-to-end ML, starting from building an ML-focused strategy and progressing into model training, optimization, and productionalization with hands-on labs using Google Cloud Platform.
> By enrolling in this specialization you agree to the Qwiklabs Terms of Service as set out in the FAQ and located at: https://qwiklabs.com/terms_of_service <
자주 묻는 질문
등록 전에 강좌를 미리 볼 수 있나요?
예. 등록하기 전에 첫 번째 비디오를 미리 보고 강의 계획을 검토할 수 있습니다. 미리 보기에 포함되지 않은 콘텐츠를 이용하려면 강좌를 구매해야 합니다.
강의 및 과제를 언제 이용할 수 있게 되나요?
세션 시작일 전에 강좌에 등록하면 해당 강좌의 모든 강의 비디오 및 읽기 자료에 접근할 수 있습니다. 수업이 시작되면 과제를 제출할 수 있습니다.
등록하면 무엇을 이용할 수 있나요?
등록 후 세션이 시작되면 읽기 자료 항목 및 강좌 토론 포럼을 포함하여 모든 비디오와 기타 리소스를 이용할 수 있습니다. 연습 평가를 보고 제출하며 필요한 성적 평가 과제를 완료하여 성적을 받고 강좌 수료증을 취득할 수 있습니다.
강좌 수료증을 언제 받게 되나요?
강좌를 성공적으로 수료하면 전자 강좌 수료증이 성취도 페이지에 추가됩니다. 해당 페이지에서 강좌 수료증을 인쇄하거나 LinkedIn 프로필에 수료증을 추가할 수 있습니다.
이 강좌를 청강할 수 없는 이유는 무엇인가요?
이 강좌는 현재 Coursera에서 수업료를 결제했거나 재정 지원(해당하는 경우)을 받은 학습자만 이용할 수 있는 강좌입니다.
환불 규정은 어떻게 되나요?
재정 지원을 받을 수 있나요?
궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.