Udemyintermediatees

Deep Learning aplicado: Despliegue de modelos TensorFlow 2.0

Build a production-ready, high-availability deep learning model with TensorFlow 2.0 and REST APIs. Learn to deploy your AI effectively!

4.8(87)
629students
7h 21m
Certificate
Mirko J. Rodríguez Mallma
Mirko J. Rodríguez MallmaTechnology & Data Solution Architect

Course Content

Deep Learning aplicado: Despliegue de modelos TensorFlow 2.0 is an intermediate-level Udemy course taught by Mirko J. Rodríguez Mallma. It runs 7h 21m, is taught in Spanish, and includes a certificate of completion. Learners rate it 4.8 out of 5 from 87 reviews, with 629 students enrolled. It is a paid course, first published October 2020.

Unlock the power of Deep Learning with this comprehensive, hands-on course! Learn to deploy your machine learning models for both development and, crucially, high-performance production environments using TensorFlow 2.0 and REST API creation. This practical course provides an intuitive, step-by-step guide to deploying AI models effectively.

Course Highlights:

  • Deep Dive into Model Deployment: Understand why deploying Deep Learning models is essential and the differences between development and production deployment.
  • Cloud Deployment Expertise: Master deploying models on cloud platforms like Google Cloud Platform (GCP) and CentOS servers.
  • REST API Development: Build Web Services from scratch to expose your models as easily accessible APIs.
  • Containerization with Docker: Learn to use Docker and Docker Swarm for robust production deployments alongside TensorFlow Serving.
  • Seamless Integration: Implement calls to your Web Services and explore model interoperability using ONNX.
  • Custom vs. Platform Deployment: Understand the trade-offs between custom deployment strategies and leveraging established platforms.
  • Practical, Hands-on Learning: This is a 100% practical course prioritizing lab sessions and coding activities. Reproduce every line of code with detailed explanations, building a strong foundation in MLOps and AIOps.
  • Modern Toolset: Utilize the most popular and mature tools in the Python 3.0 ecosystem: TensorFlow 2.0, TensorFlow Serving, Flask, and FastAPI.
  • Simplified Setup: All necessary tools are configured directly within Google Cloud, eliminating the need for local installations.
  • Monitoring & Management: Implement monitoring using Prometheus and Grafana to ensure optimal model performance.

Key Topics Covered:

  • Why Deploy Deep Learning Models? Understanding the business value of model deployment.
  • Development vs. Production Deployment Strategies
  • Cloud Deployment: Google Cloud Platform (GCP) & CentOS
  • Building REST Web Services for AI Models (APIs)
  • Docker for Production Deployments (Docker Swarm, TensorFlow Serving)
  • Integrating Web Services from Zero
  • Technical Considerations for Deep Learning Deployment
  • DevOps & Machine Learning / MLOps / AIOps / XXOps
  • Model Interoperability with ONNX
  • Custom Deployment vs. Platform Solutions
$ whoami — the devs behind tutorialsearch.io

Want AI in your product? Hire the team behind TutorialSearch.io

LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.

5.0(117)
4h 36m
all
5.0(11)
9h 2m
intermediate
5.0(28)
8h 50m
beginner