Coding & Development

DeepMoji is a state-of-the-art deep learning model designed for analyzing sentiment, emotion, and sarcasm in textual data. The model was trained on an extensive dataset of 1.2 billion tweets, leveraging emojis to understand how language expresses various emotions. It offers transfer learning capabilities, allowing it to achieve state-of-the-art performance on numerous emotion-related text modeling tasks. Developers can use DeepMoji to extract emoji predictions, convert text into 2304-dimensional emotional feature vectors, or fine-tune the model for new datasets. The project is open-source and based on Keras, supporting either Theano or TensorFlow as a backend. A PyTorch implementation, torchMoji, is also available.

MLAlgorithms provides a comprehensive collection of machine learning algorithm implementations, including deep learning models like MLP, CNN, RNN, and LSTM, as well as classical algorithms such as linear regression, logistic regression, Random Forests, SVM, K-Means, and Naive Bayes. All algorithms are implemented in Python, leveraging libraries like NumPy, SciPy, and Autograd, making the code easy to follow and experiment with. This project is ideal for those who wish to understand the core mechanics of these algorithms without the complexity of highly optimized libraries, offering a simplified approach to learning and building ML models from the ground up.

DeepSeek-V3 is a powerful Mixture-of-Experts (MoE) language model featuring 671B total parameters, with 37B activated for each token, ensuring efficient inference and cost-effective training. Building on the DeepSeek-V2 architecture, it introduces an innovative auxiliary-loss-free strategy for load balancing and a multi-token prediction training objective for enhanced performance. The model was pre-trained on 14.8 trillion diverse tokens and further refined through Supervised Fine-Tuning and Reinforcement Learning. DeepSeek-V3 demonstrates superior performance against other open-source models and rivals top closed-source alternatives, particularly excelling in math and code tasks. It supports local deployment on various hardware and open-source community software, including SGLang, LMDeploy, and TensorRT-LLM, with options for FP8 and BF16 inference.

Comfy Deploy is a platform designed to streamline the deployment and management of ComfyUI workflows for teams. It allows users to share ComfyUI workflows via links, run them instantly in the cloud, or create simplified user interfaces. The platform facilitates one-click deployment of production APIs, ensuring effortless scaling without requiring extensive engineering knowledge. Key features include the ability to install custom nodes and models, share multiple environments, and leverage powerful auto-scaling GPUs like H100s and A100s for parallel cloud generation. Comfy Deploy also offers full version history for workflows, making collaboration and iteration easy, and provides a playground for testing and refining workflows with auto-generated UIs.

micro_diffusion is an open-source repository from Sony Research that provides a minimalistic implementation for training large-scale diffusion models from scratch with an extremely low budget. Utilizing only 37 million publicly available real and synthetic images, it can train a 1.16 billion parameter sparse transformer for approximately $1,890, achieving a strong FID score on the COCO dataset. The repository includes training code, dataset code, and pre-trained model checkpoints for off-the-shelf generation. It supports progressive training from low to high resolution and incorporates patch masking for performance optimization and reduced training time.

DeepExplain offers a comprehensive framework for understanding the behavior of deep neural networks through various attribution methods. It enables researchers and practitioners to interpret existing models and benchmark new attribution techniques. The tool supports both gradient-based methods like Saliency maps, Gradient * Input, Integrated Gradients, DeepLIFT, and epsilon-LRP, as well as perturbation-based methods such as Occlusion and Shapley Value sampling. DeepExplain is compatible with TensorFlow (V1) and Keras with a TensorFlow backend, providing flexibility for different development environments. Its capabilities help in identifying which input features contribute most to a network's output, aiding in debugging and model transparency.

Meshed-Memory Transformer (M²) is an open-source project that provides the reference code for the paper "Meshed-Memory Transformer for Image Captioning" presented at CVPR 2020. This tool is designed for researchers and developers working in computer vision and natural language processing. It allows users to set up a conda environment, download necessary data like COCO annotations and detection features, and then evaluate or train their own image captioning models. The repository includes scripts for both testing and training, with configurable arguments for batch size, number of memory vectors, and learning rate scheduling. It requires Python 3.6 and specific data preparation steps to function correctly.

DeepSeek Coder is a powerful series of code language models, meticulously trained from scratch on 2 trillion tokens, with a composition of 87% code and 13% natural language in both English and Chinese. It offers various model sizes, ranging from 1B to 33B parameters, allowing users to select the most suitable option for their requirements. The tool excels in project-level code completion and infilling, leveraging a 16K window size and a fill-in-the-blank task. DeepSeek Coder achieves state-of-the-art performance among open-source code models across multiple programming languages and benchmarks, making it an invaluable asset for developers seeking advanced code generation capabilities.

mlbookcamp-code is a GitHub repository offering comprehensive code examples and supplementary materials directly from the Machine Learning Bookcamp book. It covers a wide range of machine learning topics, from regression and classification to neural networks, deployment, and serverless deep learning. The repository also provides code for setting up environments, an introduction to Python, NumPy, and Pandas. It serves as a practical companion to the book, allowing users to explore and implement machine learning concepts. Additionally, it links to the Machine Learning Zoomcamp, a free online course based on the book, providing further learning opportunities and community support.

DeepLearningFrameworks is an open-source GitHub repository designed to be a "Rosetta Stone" for deep learning frameworks. Its primary goal is to enable data scientists to easily transfer their expertise from one framework to another by providing common setups and comparisons across different GPUs, CUDA versions, precision levels, and languages (Python, Julia, R). The project includes notebooks demonstrating CNN, DenseNet-121, ResNet-50, and RNN models, along with detailed performance metrics like training times and feature extraction speeds across frameworks such as Caffe2, Chainer, CNTK, MXNet, Keras (with various backends), Tensorflow, Lasagne, PyTorch, and Julia-Knet. It also offers valuable lessons learned regarding API usage, data handling, and performance optimization for various frameworks.

MoneyPrinter is an open-source tool designed to automate the creation of YouTube Shorts by simply providing a video topic. It leverages local Ollama models for script generation and metadata, ensuring that content creation is powered by local AI. The tool features a DB-backed generation queue, utilizing an API, worker, and Postgres in Docker for reliable and restart-safe processing. MoneyPrinter is built with MoviePy for video editing and offers an interactive setup script, quickstart guide, and comprehensive documentation. It supports auto-detection of ImageMagick and provides solutions for common installation issues, making it accessible for users to generate short-form video content efficiently.

DLTK (Deep Learning Toolkit) is an open-source Python library designed for medical image analysis, leveraging the TensorFlow framework. It aims to facilitate rapid prototyping of deep learning models and ensure reproducibility in research applications within the medical imaging field. The toolkit provides state-of-the-art methods and models, accelerating research and development. It includes example applications and tutorial notebooks to help users understand its interface with TensorFlow, write custom read functions, and develop their own model functions. DLTK also features a Model Zoo with implementations of current research methodologies.

DriveDreamer is a pioneering world model entirely derived from real-world driving scenarios, specifically designed for autonomous driving research. Unlike other models that focus on gaming or simulated environments, DriveDreamer addresses the critical limitation of lacking real-world representation. It leverages powerful diffusion models to construct comprehensive representations of complex driving environments and employs a two-stage training pipeline. This allows DriveDreamer to first acquire an understanding of structured traffic constraints and then anticipate future states. The tool empowers precise, controllable video generation that faithfully captures real-world traffic scenarios and enables the generation of realistic and reasonable driving policies, opening avenues for interaction and practical applications in autonomous driving.

NMT-Keras is an open-source library designed for Neural Machine Translation (NMT) using the Keras framework. It provides implementations of both attentional recurrent neural network NMT models and Transformer NMT models. Key features include multi-GPU training for TensorFlow, Tensorboard integration, and online learning capabilities. The library supports various attention mechanisms like Bahdanau and Luong, along with double stochastic attention. Users can leverage beam search decoding, ensemble decoding, and model averaging for improved translation quality. It also offers support for GRU/LSTM networks, label smoothing, N-best list generation, and unknown words replacement. NMT-Keras facilitates the use of pretrained word embeddings and includes a client-server architecture for web demos, making it suitable for researchers and developers in the machine translation domain.

DiffusionDPO is a code repository from SalesforceAIResearch, offering the training code for "Diffusion Model Alignment Using Direct Preference Optimization." This tool is designed for researchers and developers working with diffusion models, providing scripts adapted from the diffusers library. It supports the alignment of models such as StableDiffusion1.5 and StableDiffusion-XL-1.0, with examples for running training on these models. The repository includes utilities for scoring models using various AI feedback mechanisms like PickScore, HPS, Aesthetics, and CLIP, along with notebooks for visualizing results and comparing generations. It's a valuable resource for those looking to fine-tune and evaluate diffusion models for specific preferences.

DiffBIR is an open-source project providing code and pretrained models for blind image restoration, as presented in the ECCV 2024 paper. It leverages generative diffusion prior to handle various restoration tasks, including blind image super-resolution, blind face restoration (aligned and unaligned), and blind image denoising. The tool offers different model versions, including one trained on the Unsplash dataset with LLaVA-generated captions, and supports features like tiled sampling for large images on low-VRAM GPUs. Users can interact with DiffBIR via a Gradio web interface or through command-line inference scripts, making it accessible for both research and practical applications in image enhancement.

DiffEqFlux.jl is a Julia library designed for scientific machine learning (SciML), specifically focusing on neural differential equations. It integrates differential equation solvers into neural networks, enabling the addition of physical information into traditional machine learning models. The library offers pre-built implicit layer architectures with efficient O(1) backpropagation and GPU acceleration. It supports various types of neural differential equations, including Neural ODEs, Neural SDEs, Neural DAEs, and Neural DDEs, as well as Hamiltonian Neural Networks and Continuous Normalizing Flows. DiffEqFlux.jl is built upon DifferentialEquations.jl and Lux.jl, providing a robust framework for researchers and developers to explore advanced scientific machine learning methods.

DL-workshop-series is an open-source GitHub repository maintained by Machine Learning Tokyo (MLT), offering comprehensive materials for deep learning workshops. It features practical implementations and theoretical insights into convolution operations and learning processes within deep neural networks. The repository includes Colab notebooks with examples of kernel applications and functions for constructing Keras models, covering architectures like AlexNet, VGG, Inception, MobileNet, ResNet, and YOLO. It serves as a valuable resource for individuals and groups looking to learn and practice deep learning techniques, providing both code and presentation slides for a structured learning experience.

dl_tutorials is an open-source GitHub repository offering a comprehensive set of deep learning tutorials, structured into weekly modules. It guides users through fundamental concepts such as Python basics, logistic regression, and optimization methods, progressing to advanced topics like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and their applications in image detection, semantic segmentation, and handwriting generation. The tutorials include practical exercises, such as implementing MLPs and CNNs on custom datasets, and cover modern architectures like AlexNet, GoogLeNet, and Residual Networks. It also delves into advanced concepts like deep reinforcement learning, adversarial attacks, and generative adversarial networks, making it a valuable resource for those looking to understand and implement deep learning techniques.

nucleotide-transformer is an open-source repository from InstaDeep AI, dedicated to advancing genomics and transcriptomics through cutting-edge deep learning models. It features a collection of transformer-based genomic language models and innovative downstream applications, including the Nucleotide Transformer (NT), Agro Nucleotide Transformer (AgroNT), SegmentNT, and ChatNT. The platform provides powerful, reproducible, and accessible tools for unlocking new insights from biological sequences, offering pre-trained weights, inference code, and research contributions. It supports various tasks such as functional-track prediction, genome annotation, controllable sequence generation, and single-cell transcriptomics, making it a central hub for AI-driven genomic research.

Erasing is an open-source project designed to remove specific concepts from diffusion models, offering a powerful way to fine-tune AI image generation. The tool provides updated code with diffusers support, significantly reducing GPU memory usage and increasing training speed by 5-8 times compared to older versions. It supports various diffusion models including SDv1.4, SDXL, FLUX, and FLUX.2 Klein, allowing users to erase entire concepts or precise attributes from concepts (e.g., removing hats from cowboys). The project includes installation guides, training instructions, and scripts for generating images and running a local Gradio demo, making it valuable for AI researchers and developers working with generative models.

OctNet is an open-source framework designed for deep learning with sparse 3D data, utilizing efficient space partitioning structures known as octrees. This approach significantly reduces the memory and compute requirements of 3D convolutional neural networks, allowing for the development of deep networks at high resolutions. By hierarchically partitioning space and storing pooled feature representations in leaf nodes, OctNet focuses memory allocation and computation on relevant dense regions. This enables deeper networks without sacrificing resolution, making it suitable for tasks such as 3D object classification, orientation estimation, and point cloud labeling. The framework includes core CPU and GPU code for network operations, data pre-processing tools, and a Torch wrapper for full network integration.

Emotion-recognition-neural-networks is an open-source project developed for emotion recognition using deep neural networks, specifically with TensorFlow. It employs convolutional neural networks (CNNs) for mood recognition, utilizing the FER-2013 Faces Database which contains 28,709 pictures across 7 emotional expressions. The project provides scripts for data transformation from CSV to NumPy, and supports training models using architectures like AlexNet. While the repository notes that the code might not be actively maintained or fully functional, it serves as a foundational academic project for those interested in exploring DNN-based emotion recognition.

e3nn is an open-source, modular framework designed to facilitate the development of neural networks with Euclidean symmetry. It provides fundamental mathematical operations such as tensor products and spherical harmonics, essential for building E(3) equivariant neural networks. The library is under active development, with breaking changes indicated by version number increments. It is recommended to install using pip, and users can contribute to its development or seek help through discussions and bug reports on GitHub. The framework is backed by research papers on Euclidean Neural Networks and e3nn itself, with BibTeX entries available for citation.