Simclr

Acest proiect este un framework de învățare contrastivă auto-supervizată conceput pentru a antrena modele de deep learning să învețe reprezentări vizuale din imagini fără a utiliza etichete furnizate de oameni. Oferă un sistem pentru dezvoltarea modelelor de reprezentare vizuală pre-antrenate care pot fi adaptate pentru sarcini de computer vision downstream.

Framework-ul include instrumente pentru clasificarea imaginilor semi-supervizată, care combină seturi mari de date neetichetate cu seturi mici etichetate pentru a îmbunătăți acuratețea. Dispune, de asemenea, de un instrument de evaluare linear probe pentru a evalua calitatea funcționalităților vizuale învățate prin antrenarea unui clasificator linear simplu peste reprezentările înghețate.

Codul sursă acoperă antrenarea distribuită de deep learning și accelerarea hardware pentru a gestiona dimensiuni mari de batch-uri, alături de primitive de optimizare precum programarea ratei de învățare cosine-decay și regularizarea weight-decay. Oferă, de asemenea, utilitare pentru gestionarea modelelor, inclusiv conversia checkpoint-urilor pre-antrenate între diferite formate de framework-uri de deep learning și instrumente pentru implementarea modelelor.

Implementarea este furnizată ca o colecție de Jupyter Notebooks.

Features

Visual Foundation Pre-training - Trains base networks on large image datasets using specialized hardware to create general-purpose visual representations.
Self-Supervised Vision Representation Trainers - Provides a framework for learning visual features from unlabeled image data using self-supervised contrastive techniques.
Contrastive Learning Frameworks - Provides a specialized framework for training models to learn visual representations using contrastive objectives.
Distributed Deep Learning - Implements a training setup that scales deep learning optimization across multiple compute nodes and GPUs.
Distributed GPU Training - Scales the training of contrastive learning models across multiple GPUs to support the required large batch sizes.
Linear Classifiers - Trains simple linear classifiers on top of frozen representations to evaluate the quality of learned image features.
Visual Representation Learning Frameworks - Implements a framework for learning visual representations from unlabeled images using contrastive learning.
Visual Representation Models - Develops pretrained base networks trained on large-scale image data for adaptation to downstream vision tasks.
Representation Evaluation Tools - Ships a tool for assessing the quality of learned image features using frozen weights and linear probing.
Cross-Replica Normalizations - Computes means and variances across multiple hardware cores to ensure consistent normalization during distributed training.
Pre-trained Weight Loading - Provides mechanisms for importing serialized weights of base networks and classification heads into models for immediate use.
Cosine Decay Schedules - Implements a learning rate schedule that reduces the optimization step size following a cosine curve.
Cosine Warmup Schedules - Uses a learning rate schedule that combines a warmup phase with a cosine decay curve.
Model Training Optimizers - Configures optimization algorithms like Momentum or Adam to manage weight updates during the training process.
Hardware Acceleration - Utilizes specialized GPU hardware to accelerate the mathematical computations required for large-scale model training.
Weight Decay Regularization - Applies weight-decay penalties to trainable variables to prevent overfitting during high-capacity model training.
Visual Representation Deployment - Implements functionality to load saved checkpoints for performing visual representation and classification tasks.
Semi-Supervised Classification - Combines large unlabeled datasets with small labeled sets to improve image classification accuracy.
Vision Model Fine-Tuning - Adapts general-purpose pretrained visual representation models to specific downstream tasks using labeled datasets.
Representation Model Adaptation - Adjusts pretrained representation models for specific downstream tasks using supervised learning to improve accuracy.
Advanced Learning - Simple framework for contrastive learning of visual representations.

Istoric stele

Graficul istoricului de stele pentru google-research/simclr

google-researchsimclrArchived

Name: google-research/simclr
Author: google-research

View on GitHub

4,502 stele669 fork-uriJupyter NotebookApache-2.06 vizualizăriarxiv.org/abs/2006.10029

Simclr

Implementarea este furnizată ca o colecție de Jupyter Notebooks.

Features

Visual Foundation Pre-training - Trains base networks on large image datasets using specialized hardware to create general-purpose visual representations.
Self-Supervised Vision Representation Trainers - Provides a framework for learning visual features from unlabeled image data using self-supervised contrastive techniques.
Contrastive Learning Frameworks - Provides a specialized framework for training models to learn visual representations using contrastive objectives.
Distributed Deep Learning - Implements a training setup that scales deep learning optimization across multiple compute nodes and GPUs.
Distributed GPU Training - Scales the training of contrastive learning models across multiple GPUs to support the required large batch sizes.
Linear Classifiers - Trains simple linear classifiers on top of frozen representations to evaluate the quality of learned image features.
Visual Representation Learning Frameworks - Implements a framework for learning visual representations from unlabeled images using contrastive learning.
Visual Representation Models - Develops pretrained base networks trained on large-scale image data for adaptation to downstream vision tasks.
Representation Evaluation Tools - Ships a tool for assessing the quality of learned image features using frozen weights and linear probing.
Cross-Replica Normalizations - Computes means and variances across multiple hardware cores to ensure consistent normalization during distributed training.
Pre-trained Weight Loading - Provides mechanisms for importing serialized weights of base networks and classification heads into models for immediate use.
Cosine Decay Schedules - Implements a learning rate schedule that reduces the optimization step size following a cosine curve.
Cosine Warmup Schedules - Uses a learning rate schedule that combines a warmup phase with a cosine decay curve.
Model Training Optimizers - Configures optimization algorithms like Momentum or Adam to manage weight updates during the training process.
Hardware Acceleration - Utilizes specialized GPU hardware to accelerate the mathematical computations required for large-scale model training.
Weight Decay Regularization - Applies weight-decay penalties to trainable variables to prevent overfitting during high-capacity model training.
Visual Representation Deployment - Implements functionality to load saved checkpoints for performing visual representation and classification tasks.
Semi-Supervised Classification - Combines large unlabeled datasets with small labeled sets to improve image classification accuracy.
Vision Model Fine-Tuning - Adapts general-purpose pretrained visual representation models to specific downstream tasks using labeled datasets.
Representation Model Adaptation - Adjusts pretrained representation models for specific downstream tasks using supervised learning to improve accuracy.
Advanced Learning - Simple framework for contrastive learning of visual representations.

Alternative open-source pentru Simclr

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Simclr.

facebookresearch/moco
facebookresearch/moco
5,136Vezi pe GitHub
moco is a PyTorch implementation of momentum contrast designed for self-supervised visual representation learning. It serves as a research-based framework for extracting high-level image features from unlabeled datasets by maximizing the similarity between different views of the same image. The system utilizes an asymmetric encoder architecture consisting of a fast-learning online encoder and a slow-evolving momentum encoder to stabilize training. It employs a dictionary-based approach that compares query images against a dynamic queue of negative samples to learn distinguishing visual featur
Vezi pe GitHub5,136
facebookresearch/jepa
facebookresearch/jepa
3,986Vezi pe GitHub
This is a PyTorch self-supervised learning framework designed to train models that learn visual representations from video. It implements a joint-embedding predictive architecture that extracts spatio-temporal features by predicting missing regions of a signal within a latent representation space rather than reconstructing raw pixels. The project includes a latent space visualization tool that uses a conditional diffusion model to decode feature-space predictions back into pixels. This allows for the verification of learned representations by transforming abstract predictions into interpretab
Python
Vezi pe GitHub3,986
open-mmlab/mmpretrain
open-mmlab/mmpretrain
3,842Vezi pe GitHub
mmpretrain is a modular PyTorch computer vision framework designed for developing, training, and benchmarking deep learning architectures. It serves as a comprehensive toolkit for vision tasks, providing a specialized platform for multimodal machine learning and self-supervised learning. The project features a computer vision model zoo containing architectural definitions and pre-trained weights for backbones such as ViT, ConvNeXt, and Swin Transformer. It distinguishes itself through a dedicated self-supervised learning toolkit that implements algorithms like MAE and DINO to train models wit
Pythonbeitclipconstrastive-learning
Vezi pe GitHub3,842
facebookresearch/mae
facebookresearch/mae
8,340Vezi pe GitHub
This is a PyTorch library and framework for self-supervised vision learning. It provides an implementation of masked autoencoders and vision transformers designed to learn image representations by reconstructing masked image patches from unlabeled data. The project features a distributed training pipeline that scales workloads across multiple GPU nodes. This infrastructure includes multi-node orchestration and gradient accumulation to manage large batch sizes and coordinate resource requests across clusters. The toolkit covers a complete workflow from self-supervised masked pre-training to d
Python
Vezi pe GitHub8,340

Vezi toate cele 30 alternative pentru Simclr

Întrebări frecvente

Ce face google-research/simclr?

Care sunt principalele funcționalități ale google-research/simclr?

Principalele funcționalități ale google-research/simclr sunt: Visual Foundation Pre-training, Self-Supervised Vision Representation Trainers, Contrastive Learning Frameworks, Distributed Deep Learning, Distributed GPU Training, Linear Classifiers, Visual Representation Learning Frameworks, Visual Representation Models.

Care sunt câteva alternative open-source pentru google-research/simclr?

Alternativele open-source pentru google-research/simclr includ: facebookresearch/moco — moco is a PyTorch implementation of momentum contrast designed for self-supervised visual representation learning. It… open-mmlab/mmpretrain — mmpretrain is a modular PyTorch computer vision framework designed for developing, training, and benchmarking deep… facebookresearch/jepa — This is a PyTorch self-supervised learning framework designed to train models that learn visual representations from… facebookresearch/mae — This is a PyTorch library and framework for self-supervised vision learning. It provides an implementation of masked… facebookresearch/dino — This project is a PyTorch vision transformer framework designed for self-supervised learning. It implements a model… morvanzhou/pytorch-tutorial — This project is a collection of PyTorch learning resources and educational guides designed to teach the construction…