deep learning model architectures / neural network architecture implementations
For o bibliotecă pentru construirea modelelor de deep learning, the strongest matches are pjreddie/darknet (Darknet is a C/CUDA framework that provides CNN model), liuzhuang13/densenet (This repository provides a specific implementation of the DenseNet) and ymcui/chinese-bert-wwm (ymcui/chinese-bert-wwm is a pre-trained Chinese BERT transformer model with). huggingface/pytorch-pretrained-bert and graykode/nlp-tutorial round out the shortlist. Each is ranked by relevance to your query, popularity and recent activity.
Selectăm repository-uri open-source de pe GitHub care se potrivesc cu „deep learning framework architectures”. Rezultatele sunt clasificate după relevanța față de căutarea ta — folosește filtrele de mai jos pentru a rafina rezultatele sau utilizează AI-ul.
Rezultate pentru „o bibliotecă pentru construirea modelelor de deep learning”
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- pjreddie/darknet
pjreddie/darknet
26,461Vezi pe GitHubDarknet is a low-level neural network engine and framework written in C. It is designed for training and deploying deep learning models, with a primary focus on convolutional neural networks. The project serves as a CUDA accelerated deep learning library that offloads heavy mathematical operations to NVIDIA graphics hardware. This acceleration is used to increase processing speed and reduce execution time during the training of large networks. The engine supports a range of activities including deep learning research, image recognition development, and the training of convolutional neural ne
Darknet is a C/CUDA framework that provides CNN model implementations (like YOLO) with training pipelines and pretrained checkpoints, fitting the deep learning model architectures category, but it lacks Transformer implementations and multi-framework support.
CConvolutional Neural NetworksLow-Level Neural Network Trainers - liuzhuang13/densenet
liuzhuang13/DenseNet
4,862Vezi pe GitHubDenseNet is a computer vision model and convolutional neural network implementation designed for image recognition and classification tasks. It utilizes a densely connected network architecture where each layer is connected to every other layer to improve feature propagation. The implementation reduces the number of parameters while maintaining accuracy through a dense-connectivity pattern and layer-aggregation concatenation. It supports model construction using both standard and bottleneck-compressed architectures, with configurable network depth and growth rates to balance inference time an
This repository provides a specific implementation of the DenseNet convolutional neural network architecture for image classification, fitting the deep learning model architecture category, but it focuses on a single architecture and framework (Lua/Torch) without covering Transformers, multi-framework support, or the additional features like pre-trained checkpoints or benchmarks.
LuaCNN ArchitecturesConvolutional Neural Network Architectures - ymcui/chinese-bert-wwm
ymcui/Chinese-BERT-wwm
10,212Vezi pe GitHubChinese-BERT-wwm is a pre-trained transformer model and encoder designed for Chinese natural language processing. It converts Chinese text into dense vector representations to be used across various natural language processing applications. The model utilizes a whole word masking strategy during pre-training, masking entire words rather than individual characters. This approach is designed to improve the capture of semantic meaning and language structure within Chinese datasets. The project covers a range of downstream tasks including text classification, sequence labeling, and reading compr
ymcui/chinese-bert-wwm is a pre-trained Chinese BERT transformer model with whole-word masking, providing PyTorch and TensorFlow implementations and pre-trained checkpoints—exactly the kind of neural network architecture implementation the visitor is looking for, though it focuses on a single model family instead of a multi-architecture collection.
PythonTransformer EncodersTransformer ModelsModel Fine-Tuning - huggingface/pytorch-pretrained-bert
huggingface/pytorch-pretrained-BERT
161,658Vezi pe GitHubThis project is a PyTorch transformer model library and pre-trained model framework. It serves as a deep learning model hub and multimodal inference engine, providing a centralized system for loading, executing, and fine-tuning state-of-the-art model checkpoints. The library focuses on multimodal machine learning, enabling predictions across text, vision, and audio data. It provides specialized capabilities for model framework interoperability, allowing the conversion of weights and definitions between different deep learning libraries. The platform covers the full model lifecycle, including
Pytorch-pretrained-bert is a PyTorch library providing transformer model architectures and pre-trained checkpoints, which fits your request for deep learning neural network implementations, though it focuses solely on transformers and does not include CNN models or native multi-framework support.
PythonModel CheckpointsTransformer ModelsModel Fine-Tuning - graykode/nlp-tutorial
graykode/nlp-tutorial
14,855Vezi pe GitHubThis repository serves as an educational resource for learning the foundational architectures of natural language processing through concise code implementations. It provides a structured collection of deep learning models designed to process and understand human language, focusing on the core mechanics of neural network sequence modeling and text analysis. The project distinguishes itself by offering direct, hands-on implementations of complex architectures, including Transformers, attention mechanisms, and word embedding generation. By utilizing tensor-based computational graphs and gradien
This NLP-focused repository implements several key architectures like Transformers and attention mechanisms in both PyTorch and TensorFlow, making it a genuine collection of deep learning model implementations, though it lacks CNN models, pre-trained checkpoints, and benchmarks, so it meets the core intent but is narrower than the full feature set.
Jupyter NotebookTransformer Language ModelsTransformer Models - labmlai/annotated_deep_learning_paper_implementations
labmlai/annotated_deep_learning_paper_implementations
66,981Vezi pe GitHubThis project is a collection of deep learning research papers translated into annotated code. It serves as a resource for reproducing academic research, providing implementations of transformers, diffusion models, and reinforcement learning architectures. The library distinguishes itself by using a side-by-side annotation format that combines executable Python code with descriptive markdown notes. This approach provides a structured way to explain the logic of neural network papers alongside their PyTorch-based implementations. The codebase covers several major capability areas, including ge
This repository provides annotated PyTorch implementations of deep learning architectures from research papers, including transformers and GANs, making it a valuable resource for learning and reproducing models, though it lacks multi-framework support and pre-trained checkpoints.
PythonTransformer ArchitecturesTransformer Models - karpathy/nanogpt
karpathy/nanoGPT
59,730Vezi pe GitHubnanoGPT is a lightweight engine for training and fine-tuning transformer-based language models from scratch. It provides a minimalist codebase designed for educational exploration and rapid experimentation with neural network architectures, utilizing self-attention and feed-forward layers to process sequences and predict subsequent elements. The project distinguishes itself through a focus on high-speed data ingestion and hardware-accelerated performance. It includes a dedicated pipeline for transforming raw text into memory-mapped binary files, which enables efficient streaming during traini
nanoGPT provides a focused, minimalist implementation of the Transformer architecture for language models with training pipelines and performance benchmarks, but it does not offer CNN implementations or multi-framework support, making it a narrower fit for a collection covering diverse architectures and frameworks.
PythonTransformer - aladdinpersson/machine-learning-collection
aladdinpersson/Machine-Learning-Collection
8,465Vezi pe GitHubThis project is a machine learning educational repository providing a collection of implementations and guides for machine learning and deep learning algorithms. It serves as a deep learning model library and a reference for training workflows, covering foundational machine learning, convolutional, recurrent, and transformer architectures. The collection includes a generative adversarial network suite for synthesizing realistic images and performing image-to-image translation. It also functions as a computer vision implementation guide for object detection and semantic segmentation, alongside
This repository is a curated collection of deep learning model implementations covering CNNs, Transformers, GANs, and more across PyTorch and TensorFlow, with training workflow guides—directly matching the request for architecture implementations, though it lacks explicit pre-trained checkpoints and performance benchmarks.
PythonConvolutional Neural NetworksTransformer Architectures - fchollet/deep-learning-models
fchollet/deep-learning-models
7,349Vezi pe GitHubThis project is a collection of deep learning tools for image classification and audio tagging, providing a repository of pre-trained model weights and architectures. It serves as a Keras model zoo that enables the immediate use of established neural networks for inference and transfer learning. The library includes a music tagging framework that classifies audio recordings using convolutional recurrent neural networks and mel-spectrograms. For visual data, it provides implementations of architectures such as ResNet, VGG, and Xception, alongside a repository of weights trained on large datase
This Keras model zoo provides implementations of CNN architectures like ResNet, VGG, and Xception along with pre-trained weights, fitting the search for neural network architecture implementations, though it lacks Transformer models and multi-framework support.
PythonPre-trained Weight LoadingConvolutional Neural Network Architectures - nfmcclure/tensorflow_cookbook
nfmcclure/tensorflow_cookbook
6,239Vezi pe GitHubThe TensorFlow Cookbook is a collection of code examples and recipes for building, training, and deploying machine learning models using TensorFlow. It covers the full model lifecycle, from constructing neural networks and training them with configurable parameters to packaging trained models for production deployment with unit tests and multi-device support. The project also integrates TensorBoard for logging and visualizing computational graphs, scalar summaries, and histograms during training. The cookbook demonstrates a wide range of machine learning techniques, including convolutional ne
This TensorFlow cookbook provides practical code examples for implementing neural network architectures like CNNs and RNNs, fitting the search for deep learning model implementations, but it lacks Transformer coverage, multi-framework support, and pre-trained checkpoints.
Jupyter NotebookConvolutional Neural NetworksConvolutional Neural Network Architectures - pkmital/tensorflow_tutorials
pkmital/tensorflow_tutorials
5,668Vezi pe GitHubThis project is a collection of educational Jupyter Notebooks providing tutorials on neural network construction and tensor operations using the TensorFlow framework. It serves as a machine learning educational repository and implementation guide for deep learning students. The suite focuses on specific advanced architectures, including convolutional networks for image classification, residual networks with skip connections for training stability, and variational autoencoders for generative modeling and data synthesis. It also includes guides for building denoising and deep autoencoders to pe
This repository is a collection of TensorFlow-based Jupyter notebooks that implement CNN, VAE, and residual network architectures, fitting the search for neural network implementations, but it lacks Transformer models, multi-framework support, and pre-trained checkpoints, making it narrower than a comprehensive collection.
Jupyter NotebookConvolutional Neural NetworksConvolutional Neural Networks - keras-team/keras
keras-team/keras
64,094Vezi pe GitHubKeras is a high-level deep learning framework designed for constructing and training neural networks through the composition of modular, functional layers. It serves as a comprehensive modeling toolkit that provides standardized procedures for defining, evaluating, and deploying complex architectures. By utilizing a directed acyclic graph approach, the framework allows users to build intricate models with multiple inputs, outputs, and shared layers, ensuring consistent numerical execution through functional state management. The project distinguishes itself as a multi-backend machine learning
Keras is a high-level deep learning framework that gives you modular building blocks and pre-built implementations (CNNs, Transformers, pre-trained models) across multiple backends (TensorFlow, PyTorch, JAX), complete with training pipelines and benchmarks — exactly the kind of toolkit you need to explore and implement a wide range of neural network architectures.
PythonFrameworksModel DefinitionArchitectures - karpathy/mingpt
karpathy/minGPT
23,639Vezi pe GitHubminGPT is a minimal implementation of the Transformer architecture designed for training and experimenting with language models. It functions as a neural network training framework and a text generation engine, providing the necessary tools to manage data loading, backpropagation, and parameter updates for custom deep learning models. The project is structured as an educational resource for understanding how transformer architectures function by building and training models from scratch. It utilizes a modular block architecture and transformer-based self-attention to process sequences, allowi
A minimal, educational implementation of the Transformer architecture with a training pipeline, but it covers only that one architecture in PyTorch and lacks CNN implementations, multi-framework support, pre-trained checkpoints, and benchmarks.
PythonTransformer Models - huggingface/pytorch-image-models
huggingface/pytorch-image-models
36,893Vezi pe GitHubThis project is a comprehensive library of state-of-the-art neural network architectures designed for image classification and feature extraction. It provides a complete deep learning training framework that supports distributed execution, allowing users to build, train, and fine-tune vision models using optimized schedulers and pre-configured training recipes. The library distinguishes itself through a modular backbone architecture that treats neural networks as decoupled feature extractors, enabling the retrieval of multi-scale outputs for downstream tasks like object detection and segmenta
huggingface/pytorch-image-models is a focused library of state-of-the-art computer vision architectures (CNNs and vision transformers) with pretrained weights and training pipelines, but it covers only PyTorch and the vision domain, so it misses the multi-framework and cross-domain breadth this search asks for.
PythonTraining RecipesModel Fine-Tuning - ageron/handson-ml2
ageron/handson-ml2
29,938Vezi pe GitHubThis project provides a collection of practical machine learning code examples, including implementations for supervised, unsupervised, and reinforcement learning algorithms. It features deep learning model implementations for convolutional, recurrent, and generative architectures, alongside specific examples of reinforcement learning agents that maximize rewards in simulated environments. The repository includes dedicated data preprocessing pipelines for sanitization, feature scaling, and dimensionality reduction. It also provides implementations for a wide range of specific models, such as
This repository provides hands-on Jupyter notebook implementations of various deep learning architectures (CNNs, RNNs, GANs, autoencoders) alongside training pipelines, but it is limited to TensorFlow/Keras and lacks Transformer examples, pre-trained checkpoints, and performance benchmarks, so it covers the category but not the full breadth of features requested.
Jupyter NotebookConvolutional Neural Networks - tensorpack/tensorpack
tensorpack/tensorpack
6,287Vezi pe GitHubTensorpack is a high-level TensorFlow neural network framework and research library designed for building and training deep learning models. It provides a collection of reproducible neural network architectures for computer vision, generative tasks, reinforcement learning, and natural language processing. The project distinguishes itself through a specialized deep learning data pipeline that uses pure Python for parallel data loading and streaming. It includes a multi-GPU training orchestrator for distributing workloads via data-parallel strategies and a dedicated interpretability toolkit for
Tensorpack is a high-level TensorFlow research library that bundles reproducible neural network architectures (including CNNs, GANs, and other vision/generative models) with training pipelines, pre-trained checkpoints, and performance benchmarks, making it a good fit for exploring and implementing deep learning architectures, though it focuses solely on TensorFlow and does not prominently feature Transformer implementations.
PythonPre-trained Weight Loading - tingsongyu/pytorch_tutorial
TingsongYu/PyTorch_Tutorial
8,018Vezi pe GitHubThis project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene
This PyTorch tutorial repository provides implementation examples of CNN and Transformer architectures for vision and language, making it a relevant collection of model architectures, though it is PyTorch-only and lacks pre-trained checkpoints and performance benchmarks.
PythonTransformer ArchitecturesModel Fine-Tuning - pageman/sutskever-30-implementations
pageman/sutskever-30-implementations
3,148Vezi pe GitHubThis project is a collection of deep learning research implementations and a reproduction kit designed to translate theoretical AI papers into working code. It provides a library of neural network architectures and reference implementations for reproducing seminal research concepts through interactive notebooks. The repository distinguishes itself through the implementation of AI theory and scaling laws, covering complexity dynamics, information theory, and the simulation of universal AI agents. It also includes a benchmarking suite for synthetic reasoning, allowing for the evaluation of mode
This repository is a library of deep learning research implementations with training pipelines and performance benchmarks, covering a variety of neural network architectures (including residual and dilated-convolution networks) — it squarely fits the search for architecture implementations, though it is PyTorch-specific and does not explicitly include multi-framework support or pre-trained checkpoints.
Jupyter NotebookConvolutional Neural Network Architectures - tensorflow/models
tensorflow/models
77,663Vezi pe GitHubThis repository serves as a centralized collection of state-of-the-art deep learning architectures and reference implementations designed for research and application development. It provides a comprehensive toolkit for computer vision and natural language processing, offering pre-built models and training pipelines for tasks ranging from image classification and object detection to complex sequence modeling. The project distinguishes itself by providing a flexible execution harness that manages the entire training lifecycle, including data ingestion and backpropagation. It supports scalable
tensorflow/models is a comprehensive collection of deep learning model architectures covering CNNs and Transformers with training pipelines and pretrained checkpoints, though it is limited to the TensorFlow framework rather than spanning multiple frameworks as the search requests.
PythonComputer Vision ModelsDevelopment and Orchestration ToolsDistributed Parameter Synchronisation - fafa-dl/awesome-backbones
Fafa-DL/Awesome-Backbones
1,945Vezi pe GitHubAwesome-Backbones is a modular deep learning framework designed for the end-to-end lifecycle of computer vision models. It provides an integrated platform for training, benchmarking, and deploying convolutional and transformer-based neural network architectures for image classification tasks. The framework distinguishes itself through a configuration-driven approach to model assembly, allowing users to define backbone, neck, and head components externally. It includes a specialized toolkit for model interpretability, utilizing gradient-based visualization techniques to generate class activati
This repository is a modular PyTorch framework that implements CNN and transformer architectures (ResNet, Swin Transformer) with training, benchmarking, and deployment pipelines, fitting the search for neural network architecture implementations, though it only supports one framework and does not clearly offer pre-trained checkpoints.
PythonDeep Learning FrameworksComputer Vision TrainingConfiguration-Driven Pipelines - lucidrains/denoising-diffusion-pytorch
lucidrains/denoising-diffusion-pytorch
10,614Vezi pe GitHubImplementation of Denoising Diffusion Probabilistic Model in Pytorch
This repository provides a clean PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM), a specific deep learning architecture, but it only covers diffusion models in one framework, so it lacks the broader set of architectures (CNNs, Transformers) and multi-framework support you are looking for.
PythonDiffusion ModelsAutomated Folder-Based TrainingDiffusion Model Frameworks - openai/video-pre-training
openai/Video-Pre-Training
1,712Vezi pe GitHubVideo-Pre-Training is a machine learning framework designed for training autonomous agents to perform complex tasks by observing and mimicking human behavior from video recordings. It provides a comprehensive toolkit for imitation learning and reinforcement learning research, enabling the development of agents that can replicate human actions within simulated digital environments. The framework distinguishes itself through its ability to process large-scale, unlabeled video datasets to bootstrap agent capabilities. It utilizes inverse dynamics modeling to infer control inputs from frame trans
This repository implements the Video PreTraining (VPT) neural network architecture for learning to act from unlabeled video — a specific deep learning model, but not a collection of various architectures across multiple frameworks as the search describes.
PythonBehavioral Cloning ToolkitsImitation and Reinforcement Learning ToolkitsImitation Learning Pipelines - facebookresearch/detr
facebookresearch/detr
15,305Vezi pe GitHubThis project provides a transformer-based object detection model that treats the task as a direct set prediction problem. It implements a vision system capable of predicting bounding boxes and class labels for objects within an image, as well as frameworks for instance and panoptic segmentation. The architecture utilizes a transformer encoder and decoder to perform end-to-end set prediction, employing a Hungarian matcher to assign predicted boxes to ground truth objects. It incorporates a convolutional backbone for feature extraction and a system of learnable object queries to probe image loc
DETR is a focused implementation of a transformer-based object detection architecture with pre-trained models and training pipelines, making it a valid example for this search, though it only supports PyTorch rather than multiple frameworks.
PythonObject DetectionTransformer-Based DetectorsAttention Mechanisms - jadore801120/attention-is-all-you-need-pytorch
jadore801120/attention-is-all-you-need-pytorch
9,742Vezi pe GitHubThis project is a Transformer machine translation model and attention-based neural network implemented using the PyTorch deep learning framework. It functions as a text-to-text translation tool designed to convert source sequences into target language text. The implementation focuses on neural machine translation, covering the development of sequence-to-sequence architectures. It includes the full pipeline for translation, from text sequence preprocessing and vocabulary creation to model training and text generation inference. The system incorporates standard transformer components such as a
This repository provides a focused implementation of the Transformer architecture in PyTorch for machine translation, which is a valid deep learning model implementation, but it covers only a single architecture and framework rather than the broad collection of various architectures and frameworks you are seeking.
PythonText Translation ToolsTransformer Architecture ImplementationAttention Mechanisms - huggingface/transformers
huggingface/transformers
161,630Vezi pe GitHubTransformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference. The library features extensive support for model optimization and
Hugging Face Transformers is a library for implementing and fine-tuning transformer-based models, offering pretrained checkpoints, training pipelines, and multi-framework support, but it focuses exclusively on the Transformer family and does not include CNN architectures, so it partially matches the request for varied deep learning architectures.
PythonAPI FrameworksByte Pair EncodingsHybrid
