Useful Machine Learning resources¶
This is a piece of documentation trying to offer some advice on tools to use to answer common problems (non ML expert) users might face.
Here are some basic resources to get you quickly started in the Deep Learning / Machine Learning world.
Deep Learning with Python, F. Chollet
The FastAI book
Deep Learning Book, Ian Goodfellow
Some tools to help you getting started creating your dataset.
CVAT - Image annotation tool (with integration with the Segment Anything Model)
LabelStudio - General annotation (text, images, etc)
LabelImg - Image annotation
refinery - Labeling for NLP
superintendent - ipywidget-based interactive labelling tool for your data.
VGG Image Annotator (VIA) - Image annotation
Biigle - Web based annotation and exploration of images and videos
Roboflow - only free is your dataset is public
Labelbox - paid tool (free with educational license)
Find a dataset¶
If you don’t have any data, try find an open dataset that suits you.
Explore your dataset¶
Less make sure the dataset does not contain errors.
Google’s Know your data - only valid for common Tensorflow Datasets
Sweetviz - explore and compare tabular data
cleanlab - dataset cleaning
FastDup - dataset cleaning. Find anomalies, duplicate and near duplicate images, clusters of similarity, broken images, image statistics, wrong labels.
deepchecks - checks related to various types of issues, such as model performance, data integrity, distribution mismatches, and more.
kangas - exploring, analyzing, and visualizing large-scale multimedia data
Impyute - missing data
Some times less is more. Learn how to select the appropriate features of your dataset.
Do you have too much data from one class and too few from others. Let’s balance things out!
Do you have few data? Make the most out of it!
Is your dataset likely to degrade over time (eg. cam gets dirty). Keep on eye on it!
If you want to develop a model from scratch don’t try to be a hero! Papers with Code gathers top performing models for multiple tasks with their corresponding code. Reuse them for your usecases! Try not to look for the top model but for the one with the cleanest code.
Let’s keep an eye on the training status.
Is your training failing for some reason?
Do you need your model to go faster?
VoltaML - accelerate ML models with a single line of code
AItemplate - transforms deep neural networks into CUDA (NVIDIA GPU) / HIP (AMD GPU) C++ code for lightning-fast inference serving
Hummingbird - transform traditional Ml models (eg. Random Forest) to neural networks, and benefit from hardware acceleration