Students will apply AI-powered tools to generate captions, descriptions, and summaries from images. By expanding on a simple image caption, they will utilize a text generation model (GPT-2) and a text-to-image model (Stable Diffusion) to create a complete, interactive workflow for text-to-image conversion. They will practice generating descriptive text, summarizing the content, and exploring creative applications.
In this assignment, you will build a complete console-based voice translation application using speech recognition, Google Translate, and text-to-speech. The program takes spoken English input, converts it to text, translates it into a user-selected language, and then speaks the translated result.
In this assignment, you will clean the built-in Penguins dataset available through Seaborn. You will identify missing values, count them column by column, visualize them using a heatmap, remove completely empty records, fill missing categorical values, and estimate missing numerical values using interpolation, backward fill, and forward fill.
In this assignment, you will build a Monthly Savings Progress Chart using Python, NumPy, and Matplotlib. You will plot two savings plans across twelve months, compare their growth, control the visible axis ranges, add a legend, and shade the difference between the plans.
In this assignment, you will build a Fitness Progress Comparison Chart using Seaborn's exercise example dataset. You will filter running records, compare pulse readings after 1 minute and 30 minutes, merge the results, calculate pulse change, sort the participants, build a grouped bar plot, and label each bar.