Skip to content

Utility functions for the practical assignments of the Deep Learning for Visual Signal Processing course (IPCVAI, UAM).

License

Notifications You must be signed in to change notification settings

jcsma/dlvsp-utils

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 

Repository files navigation

dlvsp-utils

Utility functions for the practical assignments of the courses:

Author: Juan Carlos San Miguel (📧 juancarlos [dot] sanmiguel [at] uam [dot] es)

🌐 http://www-vpu.eps.uam.es/jcsanmiguel LinkedIn


Overview

dlvsp-utils is a lightweight utility package used across the course notebooks.
It provides reusable helpers for:

  • dataset manipulation and inspection
  • accuracy computation and per-class reporting
  • simple visualization utilities for model analysis

The goal is to reduce boilerplate code and keep the focus on learning strategies and experimental analysis.


Installation

Install directly from GitHub:

pip install git+https://github.com/jcsma/dlvsp-utils.git

Usage in notebooks:

from torchvision import datasets, transforms
from dlvsp_utils.data import select_classes_dataset, inspect_dataset_classes
from dlvsp_utils.metrics import calculate_accuracy, print_accuracy_report

train_full = datasets.CIFAR10(root="./data", train=True, download=True, transform=none)
train_ds, class_names = select_classes_dataset(train_full, ['cat','dog'])
inspect_dataset_classes(train_ds, class_names=class_names, header="\nTRAIN:")

Package structure

The repository contains the following modules:

  • src/dlvsp_utils/data.py Dataset utilities (class selection, inspection, sampling helpers)
  • src/dlvsp_utils/metrics.py Accuracy computation and per-class performance reporting
  • src/dlvsp_utils/viz.py Visualization helpers for analysis and debugging
  • pyproject.toml Package configuration and dependencies

Related links:

About

Utility functions for the practical assignments of the Deep Learning for Visual Signal Processing course (IPCVAI, UAM).

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages