Overview

Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off

One annual plan covers every course and certificate on Coursera. 40% off for a limited time.

Building Vision and NLP Workflows with TensorFlow and Transformers focuses on developing machine learning pipelines for computer vision and natural language processing tasks. In this course, you will learn how modern AI applications process images and text using deep learning frameworks and transformer architectures. You will begin by building computer vision pipelines that train and evaluate models for image classification and related tasks. Next, you will construct natural language processing workflows using transformer-based architectures to process and analyze text data. The course also explores how tokenization, embeddings, and model evaluation techniques improve NLP model performance. In the final modules, you will use TensorFlow and Keras to build end-to-end machine learning workflows, from data preparation to optimized model deployment. By the end of the course, you will be able to design scalable AI pipelines that handle image and language data, evaluate model performance using appropriate metrics, and optimize machine learning workflows for real-world applications. Tools used in this course include Python, TensorFlow, Keras, and transformer-based NLP frameworks.

Syllabus

Vision Models: Train and Evaluate: Build Your First Transformer Pipeline: Tokenization, Embeddings, and Encoding

You will apply tokenization, embedding, and encoding techniques to construct structured pipelines for processing input data. You will transform raw inputs into model-ready representations and validate intermediate outputs to ensure reliable workflow execution.

Vision Models: Train and Evaluate: Evaluate Model Outputs with Metrics and Human Review

You will evaluate model output quality using automated metrics and structured human review. You will compare quantitative scores with qualitative feedback to identify performance gaps and refine results.

Build & Evaluate NLP Transformer Pipelines: Build Your First Transformer Pipeline: Tokenization, Embeddings, and Encoding

You will apply tokenization, embedding, and encoding techniques to build transformer-based natural language processing pipelines. You will convert raw text into encoded representations suitable for downstream tasks such as classification or summarization.

Build & Evaluate NLP Transformer Pipelines: Evaluate Model Outputs with Metrics and Human Review

You will evaluate model output quality using automated metrics such as ROUGE and structured human evaluation frameworks. You will interpret results to assess reliability, safety, and alignment with task objectives.

Build & Optimize TensorFlow ML Workflows: Build an End-to-End TensorFlow Workflow

You will apply TensorFlow 2.x tools to build an end-to-end machine learning workflow using tf.data pipelines and Keras models. You will structure data ingestion, model definition, training, and checkpointing into a reproducible system.

Build & Optimize TensorFlow ML Workflows: Optimize & Deploy Models with TensorFlow Lite

You will create optimized machine learning model deployments using TensorFlow Lite. You will evaluate inference latency, apply quantization techniques, and improve performance for mobile and edge environments.

Project: Optimizing Vision and Transformer Pipelines for Financial Risk

In this project, you will design and evaluate two production-style machine learning pipelines for a financial services risk intelligence scenario: A computer vision pipeline that converts a multi-class image dataset into a binary risk classification task. A transformer-based NLP pipeline that classifies customer complaint text into low-risk or high-risk categories. You will implement both workflows using TensorFlow and transformer libraries, evaluate performance using appropriate classification metrics, perform structured error analysis, and apply at least one optimization to improve workflow performance. The final deliverable is a portfolio-ready Python script and structured analysis demonstrating your ability to design, evaluate, and refine AI workflows in a professional setting.