awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetServeur MCPÀ proposNotre méthodologiePresse
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

31 dépôts

Awesome GitHub RepositoriesPretrained Weight Initializers

Utilities for loading existing model weights to accelerate convergence during training.

Distinct from Weight Initialization: Distinct from Weight Initialization: focuses on loading external pretrained weights rather than random initialization strategies.

Explore 31 awesome GitHub repositories matching artificial intelligence & ml · Pretrained Weight Initializers. Refine with filters or upvote what's useful.

Awesome Pretrained Weight Initializers GitHub Repositories

Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
  • xai-org/grok-1Avatar de xai-org

    xai-org/grok-1

    51,690Voir sur GitHub↗

    Grok-1 is an open-weights large language model implementation featuring a sparse mixture-of-experts architecture. It is designed for high-performance text generation and natural language processing by activating only a subset of specialized expert layers per token. The model utilizes 8-bit weight quantization to reduce memory overhead and accelerate loading. To manage its high parameter count, the implementation supports activation sharding, which distributes the memory load across multiple hardware devices during execution. The project covers large-scale model inference, including text comp

    Initializes the model state by importing pre-trained weight tensors from external checkpoint files.

    Python
    Voir sur GitHub↗51,690
  • tencentarc/gfpganAvatar de TencentARC

    TencentARC/GFPGAN

    37,469Voir sur GitHub↗

    GFPGAN is a generative face restoration model and Python-based image processing tool designed to restore low-resolution facial images. It utilizes generative adversarial networks to recover fine details and increase the clarity of degraded portraits. The system employs a generative facial prior to map degraded images to a high-quality manifold, enabling blind-face restoration without requiring knowledge of the specific degradation process. It utilizes a multi-stage workflow that includes face detection, alignment, and region-specific masking to separate facial areas from the background. Beyo

    Provides utilities for loading pre-trained weights from large-scale datasets to initialize the restoration network.

    Pythondeep-learningface-restorationgan
    Voir sur GitHub↗37,469
  • exacity/deeplearningbook-chineseAvatar de exacity

    exacity/deeplearningbook-chinese

    37,285Voir sur GitHub↗

    This project is a comprehensive Chinese translation of a technical deep learning textbook, providing an educational resource on the theory and implementation of neural networks. It functions as a collaborative technical translation project designed to make complex academic AI literature accessible to non-English speakers. The project utilizes a community-driven translation model that integrates external suggestions and pull requests to refine linguistic accuracy and reduce bias. It employs standardized terminology mapping to ensure a uniform vocabulary throughout the translated content. To i

    Explains extracting weights from generative models to initialize networks for discriminative fine-tuning.

    TeX
    Voir sur GitHub↗37,285
  • rwightman/pytorch-image-modelsAvatar de rwightman

    rwightman/pytorch-image-models

    36,893Voir sur GitHub↗

    This project is a library of pretrained computer vision architectures and backbones for image classification and feature extraction. It serves as a comprehensive model zoo and collection of standardized image encoders, including ResNet, Vision Transformers, and EfficientNet, for use in visual analysis and as backbones for object detection and image segmentation. The library provides a framework for distributed training and evaluation of image models using advanced data augmentation and optimization scripts. It includes a dedicated toolset for converting trained PyTorch vision models into the

    Provides utilities for loading pretrained weights to accelerate convergence and avoid training from scratch.

    Python
    Voir sur GitHub↗36,893
  • matterport/mask_rcnnAvatar de matterport

    matterport/Mask_RCNN

    25,564Voir sur GitHub↗

    This project is a TensorFlow and Keras implementation of the Mask R-CNN architecture. It provides a framework for performing simultaneous object detection and instance segmentation, transforming raw images into segmented masks and bounding boxes for individual object identification. The toolset enables custom computer vision training through fine-tuning pre-trained weights and integrating user-provided datasets. It includes capabilities for distributed GPU training to accelerate the optimization of large vision models. The framework covers model evaluation using standard precision metrics an

    Provides utilities to initialize training using pre-trained weights from large datasets to accelerate convergence.

    Pythoninstance-segmentationkerasmask-rcnn
    Voir sur GitHub↗25,564
  • tensorflow/magentaAvatar de tensorflow

    tensorflow/magenta

    19,797Voir sur GitHub↗

    Magenta is an AI creative suite and TensorFlow generative art framework used to train and deploy models for the production of artistic media. It functions as a generative music library and a deep learning art generator, providing tools to automate the creation of original musical compositions and visual artwork. The project covers AI music composition and generative visual art through neural art generation and machine learning creativity. It enables the training of generative models to produce original songs, images, and drawings based on learned patterns.

    Provides utilities for loading existing model weights to accelerate the creation of new artistic styles.

    Python
    Voir sur GitHub↗19,797
  • paddlepaddle/paddledetectionAvatar de PaddlePaddle

    PaddlePaddle/PaddleDetection

    14,243Voir sur GitHub↗

    PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti

    Supports loading pretrained weights to accelerate model convergence.

    Pythonblazefacedeepsortdetr
    Voir sur GitHub↗14,243
  • rudrabha/wav2lipAvatar de Rudrabha

    Rudrabha/Wav2Lip

    13,045Voir sur GitHub↗

    Wav2Lip is a deep learning lip sync model and neural talking head framework designed to synchronize the lip movements in a video to match a provided audio file. It functions as a computer vision lip synchronizer and speech-to-lip generator that maps speech patterns to visual mouth movements to produce realistic talking head videos. The system utilizes a framework for training and evaluating models that align audio and video frames. This includes the ability to train lip-sync models and visual discriminators using speech-to-lip datasets and evaluating the resulting synchronization accuracy thr

    Supports loading pre-trained model weights to accelerate convergence and improve lip-sync accuracy.

    Python
    Voir sur GitHub↗13,045
  • qubvel-org/segmentation_models.pytorchAvatar de qubvel-org

    qubvel-org/segmentation_models.pytorch

    11,622Voir sur GitHub↗

    This is a PyTorch semantic segmentation library designed for building image masking frameworks. It provides a collection of over 500 pretrained convolutional and transformer-based encoders and various decoder architectures to perform binary and multiclass pixel-level classification. The library features a modular backbone integration that decouples encoder choice from decoder logic. It supports custom input channel configurations and encoder depth tuning, allowing the modification of input layers to accept non-standard channel counts while preserving pretrained weights. Some configurations al

    Allows modifying the first layer of pretrained encoders to accept custom input channel counts while preserving weights.

    Pythoncomputer-visiondeeplab-v3-plusdeeplabv3
    Voir sur GitHub↗11,622
  • cadene/pretrained-models.pytorchAvatar de Cadene

    Cadene/pretrained-models.pytorch

    9,102Voir sur GitHub↗

    This project is a pretrained model library for PyTorch, providing a collection of convolutional neural network architectures and weights. It serves as a computer vision model zoo for image classification and feature extraction, offering a framework for transfer learning where pretrained networks are adapted for custom image recognition tasks. The library focuses on transforming images into high-level numerical representations and calculating class probability scores. It includes utilities for downloading and initializing standard architectures such as ResNet, Inception, and Xception. Capabil

    Loads pre-optimized network weights from external files to enable immediate inference or transfer learning.

    Pythonimagenetinceptionpretrained
    Voir sur GitHub↗9,102
  • jzhang38/tinyllamaAvatar de jzhang38

    jzhang38/TinyLlama

    8,994Voir sur GitHub↗

    TinyLlama is a compact 1.1B parameter language model pretrained on a dataset of 3 trillion tokens. It is an edge AI model designed for high-performance text generation on memory-constrained devices. The project provides a distributed pretraining framework for training small language models across multiple GPUs and nodes. It also includes a finetuning toolkit for full-parameter weight adjustments to adapt the base model for chat and specific tasks. The system supports distributed large language model training and on-device text generation. Its architectural components include rotary positiona

    Employs specific weight initialization distributions to ensure stable convergence during large-scale pretraining.

    Python
    Voir sur GitHub↗8,994
  • rbgirshick/py-faster-rcnnAvatar de rbgirshick

    rbgirshick/py-faster-rcnn

    8,287Voir sur GitHub↗

    This project is a Python implementation of the Faster R-CNN object detection framework. It serves as a convolutional neural network library and tool for locating and classifying multiple objects within images. The framework provides a pre-trained model implementation that allows for object detection inference without manual training. It supports the full lifecycle of object detection, including training detectors on visual datasets to identify and bound specific object classes. The system covers capabilities for computer vision model evaluation, neural network optimization to reduce model si

    Provides utilities for loading pre-trained weights to accelerate the convergence of the training process.

    Python
    Voir sur GitHub↗8,287
  • tingsongyu/pytorch_tutorialAvatar de TingsongYu

    TingsongYu/PyTorch_Tutorial

    8,018Voir sur GitHub↗

    This 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

    Initializes model architectures using weights from pre-trained configuration files.

    Python
    Voir sur GitHub↗8,018
  • fchollet/deep-learning-modelsAvatar de fchollet

    fchollet/deep-learning-models

    7,349Voir sur GitHub↗

    This 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

    Allows initializing models with pre-trained ImageNet weights to improve convergence during transfer learning.

    Python
    Voir sur GitHub↗7,349
  • open-mmlab/mmdetection3dAvatar de open-mmlab

    open-mmlab/mmdetection3d

    6,273Voir sur GitHub↗

    MMDetection3D is an open-source toolbox for 3D perception, providing a unified framework for detecting and segmenting objects in three-dimensional environments. It supports a range of core tasks including monocular 3D object detection from single camera images, LiDAR-based 3D object detection from raw point clouds, and multi-modal fusion that combines camera images with LiDAR data. The toolbox also covers point cloud semantic segmentation, assigning class labels to every point in a scan for scene understanding. The project distinguishes itself through a config-driven pipeline that orchestrate

    Transforms model weights from external frameworks like Detectron and RegNet into the project's format.

    Python3d-object-detectionobject-detectionpoint-cloud
    Voir sur GitHub↗6,273
  • zihangdai/xlnetAvatar de zihangdai

    zihangdai/xlnet

    6,182Voir sur GitHub↗

    Ce projet est un framework de traitement du langage naturel axé sur un pré-entraîneur autorégressif généralisé conçu pour la représentation de langage non supervisée. Il implémente un modèle de langage qui combine un entraînement basé sur la permutation avec une architecture Transformer-XL pour fonctionner comme un processeur de texte à long contexte. Le système se distingue par sa capacité à gérer des séquences de texte dépassant les limites de longueur standard grâce à l'utilisation de la récurrence au niveau du segment et du codage positionnel relatif. Il met à l'échelle le pré-entraînement haute performance sur plusieurs clusters de GPU et TPU en utilisant des implémentations d'entraînement distribué. La base de code couvre l'ensemble du workflow de machine learning, incluant le nettoyage de texte et la tokenisation par sous-mots pour le prétraitement des données, ainsi que le fine-tuning spécifique à une tâche pour la réponse aux questions, la compréhension de lecture et la classification de texte. Il inclut des utilitaires pour l'optimisation des paramètres, la planification du taux d'apprentissage et l'évaluation des probabilités de réponse via des métriques de précision-rappel. Le projet fournit des configurations pour gérer les hyperparamètres du modèle et l'entraînement accéléré par le matériel sur plusieurs hôtes.

    Loads pretrained variables from checkpoint files and maps them to current model variables.

    Python
    Voir sur GitHub↗6,182
  • yahoo/open_nsfwAvatar de yahoo

    yahoo/open_nsfw

    6,011Voir sur GitHub↗

    Open NSFW est un classificateur d'images et un filtre de contenu basé sur le deep learning, conçu pour identifier les contenus visuels explicites ou inappropriés. Il utilise un réseau de neurones pour analyser les images et générer des scores de probabilité déterminant si un média est inapproprié pour le travail (NSFW). Le système s'appuie sur une architecture de modèle basée sur Caffe pour effectuer l'extraction automatique de caractéristiques visuelles et la classification d'images. Il prend en charge l'utilisation de poids pré-entraînés et permet d'affiner le réseau avec des jeux de données personnalisés pour ajuster la précision de la détection. Le projet couvre des workflows complets de modération d'images, incluant l'analyse automatisée du contenu et le filtrage visuel pour signaler ou bloquer les médias inappropriés.

    Supports the use of pre-trained weights to speed up convergence and improve classification accuracy.

    Python
    Voir sur GitHub↗6,011
  • deep-learning-with-pytorch/dlwpt-codeAvatar de deep-learning-with-pytorch

    deep-learning-with-pytorch/dlwpt-code

    5,224Voir sur GitHub↗

    Ce projet est une ressource pédagogique sur le deep learning consistant en des implémentations de modèles PyTorch et des exemples de code. Il fournit des scripts Python fonctionnels et des notebooks pour construire, entraîner et optimiser des réseaux de neurones en utilisant le calcul basé sur les tenseurs. Le dépôt inclut des implémentations pour concevoir des couches de réseau et des fonctions de perte personnalisées, ainsi que des exemples de workflows d'apprentissage par transfert qui chargent des poids de modèles pré-entraînés pour accélérer le développement. La base de code couvre un large éventail de capacités en deep learning, incluant l'entraînement de réseaux de neurones, la conception de composants de modèles personnalisés et l'implémentation d'architectures multicouches pour reconnaître des motifs complexes dans des jeux de données.

    Includes pretrained weight initializers to accelerate model development through transfer learning.

    Jupyter Notebookdeep-learningdeep-neural-networkspython
    Voir sur GitHub↗5,224
  • timesler/facenet-pytorchAvatar de timesler

    timesler/facenet-pytorch

    5,148Voir sur GitHub↗

    facenet-pytorch est une bibliothèque de reconnaissance faciale pour PyTorch qui fournit des réseaux neuronaux pré-entraînés pour détecter les visages et extraire des embeddings faciaux. Elle inclut un détecteur de visage MTCNN pour localiser les visages et les points de repère, aux côtés d'un encodeur de visage InceptionResnet pour convertir les images faciales en vecteurs de haute dimension pour la vérification d'identité. Le projet fournit des outils pour la reconnaissance d'identité en comparant les embeddings faciaux en utilisant la similarité cosinus. Il prend également en charge le suivi vidéo facial pour maintenir la cohérence de l'identité à travers les images consécutives et permet le fine-tuning de modèles pré-entraînés sur des jeux de données personnalisés pour améliorer la précision de reconnaissance pour des individus ou environnements spécifiques. La bibliothèque couvre un large éventail de capacités de vision par ordinateur, incluant la localisation faciale, la vérification d'identité et le traitement de tenseurs d'image via la normalisation par lots.

    Allows loading pretrained weights to enable immediate facial recognition without training from scratch.

    Pythonface-detectionface-identificationface-recognition
    Voir sur GitHub↗5,148
  • ashnkumar/sketch-codeAvatar de ashnkumar

    ashnkumar/sketch-code

    5,143Voir sur GitHub↗

    Sketch-code est un outil de prototypage web par deep learning et un convertisseur image-vers-HTML conçu pour transformer des maquettes de sites web dessinées à la main en code HTML structurel. Il utilise un analyseur de wireframes par réseau de neurones pour reconnaître les éléments visuels dans les croquis et les mapper vers des représentations de mise en page web correspondantes. Le système emploie une architecture basée sur Keras pour entraîner et évaluer des modèles de reconnaissance à l'aide de jeux de données de wireframes dessinés à la main et de HTML de référence. Il découple la mise en page structurelle du design visuel en permettant l'injection de couches CSS personnalisées lors du processus de compilation. Le projet couvre le prototypage frontend automatisé et la génération de mise en page UI, incluant le mapping supervisé image-vers-code et l'évaluation de la précision des prédictions pour mesurer la sortie générée par rapport aux références de vérité terrain.

    Utilizes pretrained weight initialization to accelerate the convergence and improve the accuracy of the recognition model.

    Pythonaugmentationdeep-learningimage-processing
    Voir sur GitHub↗5,143
Préc.12Suivant
  1. Home
  2. Artificial Intelligence & ML
  3. Weight Initialization
  4. Pretrained Weight Initializers

Explorer les sous-tags

  • Adaptive Input LayersLayers that modify input dimensions of pretrained weights to support non-standard channel counts. **Distinct from Pretrained Weight Initializers:** Distinct from general weight initialization; specifically modifies the input layer architecture to preserve pretrained weights for different channel counts.
  • Autoencoder Weight Transfers1 sous-tagTechniques for initializing neural networks by transferring weights learned from a pretrained autoencoder. **Distinct from Pretrained Weight Initializers:** Focuses specifically on utilizing an autoencoder for weight initialization, whereas pretrained weight initializers covers generic weight loading from any model.
  • Model Architecture AdaptationModifying pretrained model layers and output classes to suit specific target datasets. **Distinct from Pretrained Weight Initializers:** Focuses on structural modification of the model after loading weights, not just the initialization process.
  • Vocabulary-Aware Weight InitializationInitializing models by loading pretrained weights alongside specific token vocabularies. **Distinct from Pretrained Weight Initializers:** Integrates vocabulary mapping with weight loading, whereas pretrained initializers are often weight-only.