ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

Last update: Jan 04, 2023

Overview

ManimML

ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library. We want this project to be a compilation of primitive visualizations that can be easily combined to create videos about complex machine learning concepts. Additionally, we want to provide a set of abstractions which allow users to focus on explanations instead of software engineering.

Getting Started
Examples

Getting Started

First you will want to install manim.

Then install the package form source or pip install manim_ml

Then you can run the following to generate the example videos from python scripts.

manim -pqh src/vae.py VAEScene

Examples

Checkout the examples directory for some example videos with source code.

Neural Networks

This is a visualization of a Variational Autoencoder made using ManimML. It has a Pytorch style list of layers that can be composed in arbitrary order. The following video is made with the code from below.

class VariationalAutoencoderScene(Scene):

    def construct(self):
        embedding_layer = EmbeddingLayer(dist_theme="ellipse").scale(2)
        
        image = Image.open('images/image.jpeg')
        numpy_image = np.asarray(image)
        # Make nn
        neural_network = NeuralNetwork([
            ImageLayer(numpy_image, height=1.4),
            FeedForwardLayer(5),
            FeedForwardLayer(3),
            embedding_layer,
            FeedForwardLayer(3),
            FeedForwardLayer(5),
            ImageLayer(numpy_image, height=1.4),
        ], layer_spacing=0.1)

        neural_network.scale(1.3)

        self.play(Create(neural_network))
        self.play(neural_network.make_forward_pass_animation(run_time=15))

Generative Adversarial Network

This is a visualization of a Generative Adversarial Network made using ManimML.

VAE Disentanglement

This is a visualization of disentanglement with a Variational Autoencoder

You might also like...

Create animations for the optimization trajectory of neural nets

Animating the Optimization Trajectory of Neural Nets loss-landscape-anim lets you create animated optimization path in a 2D slice of the loss landscap

81 Dec 25, 2022

Testing the Facial Emotion Recognition (FER) algorithm on animations

PegHeads-Tutorial-3 Testing the Facial Emotion Recognition (FER) algorithm on animations

2 Jan 3, 2022

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

H2O H2O is an in-memory platform for distributed, scalable machine learning. H2O uses familiar interfaces like R, Python, Scala, Java, JSON and the Fl

6.1k Jan 5, 2023

tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series classification, regression and forecasting.

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

2.8k Jan 8, 2023

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

912 Jan 8, 2023

A collection of 100 Deep Learning images and visualizations

A collection of Deep Learning images and visualizations. The project has been developed by the AI Summer team and currently contains almost 100 images.

65 Sep 12, 2022

This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Developed By Google!

Machine Learning Hand Detector This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Dev

3 Feb 25, 2022

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

3k Jan 8, 2023

The LaTeX and Python code for generating the paper, experiments' results and visualizations reported in each paper is available (whenever possible) in the paper's directory

This repository contains the software implementation of most algorithms used or developed in my research. The LaTeX and Python code for generating the

3 Jan 3, 2023

Comments

PyPi out of date

When I pip install manim_ml it doesn't include any of the examples in the README. It also doesn't have many of the modules you'd expect. For example, manim_ml.neural_networks doesn't exist. As a workaround I've manually installed dependencies and added a clone of the latest commit to my python path. However, it would be nice to be able to install it via pip.

opened by ElPiloto 6
[BUG] update some of the examples

I updated most of the examples, in particular: disentanglement cnn vae.

interpolation still doesn't work, and gan has some positioning issues but at least it renders.

Thanks for the cool library btw! l think having working/updated examples would increase it's visibility and usefulness :)

opened by YannDubs 1
NN scaling issue with Convolutional3DLayer
At some point there was code commited changing the behaviour of the net when scaling it. If I use the code in the pip package everything works fine (0.0.11 seems to contain only code prior to the 7th of may). https://user-images.githubusercontent.com/54776552/198372984-f704cceb-8582-4bf9-bc23-c15ebb836b34.mp4

However I'm forking the repo (with the latest commit from august) because I need to change some internal code and noticed this problem.

https://user-images.githubusercontent.com/54776552/198373792-fd672ec7-708e-4ebe-b353-e291c8a591dd.mp4

Maybe someone can pinpoint the exact commit which causes this behaviour?

Code used:

class Test(Scene): def construct(self): # Make the Layer object l1 = Convolutional3DLayer(4, 2, 2) l2 = Convolutional3DLayer(5, 1, 1) l3 = Convolutional3DLayer(2, 3, 3) layers = [l1, l2, l3] nn = NeuralNetwork(layers) nn.scale(2) nn.move_to(ORIGIN) # Make Animation self.add(nn) #self.play(Create(nn)) forward_propagation_animation = nn.make_forward_pass_animation(run_time=5, passing_flash=True) self.play(forward_propagation_animation)
opened by wand555 1

Releases(v0.0.1)

v0.0.1(Mar 28, 2022)

Basic beta version.
Source code(tar.gz)
Source code(zip)

Owner

GitHub Repository

ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

Related tags

Overview

ManimML

Table of Contents

Getting Started

Examples

Neural Networks

Generative Adversarial Network

VAE Disentanglement

You might also like...

Create animations for the optimization trajectory of neural nets

Testing the Facial Emotion Recognition (FER) algorithm on animations

tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series classification, regression and forecasting.

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

A collection of 100 Deep Learning images and visualizations

This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Developed By Google!

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

The LaTeX and Python code for generating the paper, experiments' results and visualizations reported in each paper is available (whenever possible) in the paper's directory

Comments

PyPi out of date

[BUG] update some of the examples

NN scaling issue with Convolutional3DLayer

Releases(v0.0.1)

v0.0.1(Mar 28, 2022)

Owner

Graph WaveNet apdapted for brain connectivity analysis.

The official re-implementation of the Neurips 2021 paper, "Targeted Neural Dynamical Modeling".

The code of paper "Block Modeling-Guided Graph Convolutional Neural Networks".

TiP-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling

Deep Learning Head Pose Estimation using PyTorch.

Research - dataset and code for 2016 paper Learning a Driving Simulator

Code for "Intra-hour Photovoltaic Generation Forecasting based on Multi-source Data and Deep Learning Methods."

A custom DeepStack model for detecting 16 human actions.

Multiwavelets-based operator model

Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

Unsupervised Image to Image Translation with Generative Adversarial Networks

Implementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]

Official PyTorch implemention of our paper "Learning to Rectify for Robust Learning with Noisy Labels".

Multiple-criteria decision-making (MCDM) with Electre, Promethee, Weighted Sum and Pareto

Reimplement of SimSwap training code

An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicity.

3D-printable hand-strapped keyboard

[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

Evolving neural network parameters in JAX.

Implementation of Multistream Transformers in Pytorch