# facebookresearch/convnext

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/facebookresearch-convnext).**

6,388 stars · 743 forks · Python · MIT · archived

## Links

- GitHub: https://github.com/facebookresearch/ConvNeXt
- awesome-repositories: https://awesome-repositories.com/repository/facebookresearch-convnext.md

## Description

Code release for ConvNeXt model

## Tags

### Artificial Intelligence & ML

- [Image Classification Models](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/image-classification-models.md) — Provides a pure convolutional neural network for image classification matching Vision Transformer accuracy.
- [Convolutional Neural Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks.md) — Ships a convolutional neural network backbone transferable to detection and segmentation tasks.
- [Depthwise Separable Convolutions](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-neural-networks/pointwise-convolutions/depthwise-separable-convolutions.md) — Uses 7x7 depthwise separable convolutions for efficient spatial context capture.
- [Hierarchical Stage Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/hierarchical-stage-architectures.md) — Organizes layers into four stages with increasing channel dimensions and decreasing spatial resolution.
- [Overlap Patch Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/image-convolution-operations/image-patch-embedders/patch-embedding-modules/overlap-patch-embeddings.md) — Replaces standard patch embedding with a convolutional layer processing overlapping image patches.
- [Pre-Activation Residual Blocks](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/convolution-layers/convolutional-block-composers/residual-block-composers/pre-activation-residual-blocks.md) — Constructs residual blocks with activation and normalization applied before the convolution.
- [Learnable Scaling Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers/normalization-layers/learnable-scaling-layers.md) — Implements learnable scaling factors on residual block outputs to stabilize deep network training.
- [Global Response Normalizers](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-architectures/u-net-architectures/normalization-enhanced-architectures/global-response-normalizers.md) — Ships a global response normalization layer that normalizes feature maps across spatial dimensions.
- [Stochastic Depth Regularization](https://awesome-repositories.com/f/artificial-intelligence-ml/overfitting-reduction-techniques/stochastic-depth-regularization.md) — Applies stochastic depth regularization by randomly dropping residual blocks during training.
- [PyTorch Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/pytorch-implementations.md) — Implements the ConvNeXt architecture using the PyTorch framework for image recognition.
- [Strided Convolution Downsamplers](https://awesome-repositories.com/f/artificial-intelligence-ml/spatial-downsampling/strided-convolution-downsamplers.md) — Implements strided 2x2 convolutions for spatial downsampling in the ConvNeXt architecture.
- [Pre-trained Model Checkpoints](https://awesome-repositories.com/f/artificial-intelligence-ml/large-scale-model-training/vision-transformer-pre-training/pre-trained-model-checkpoints.md) — Provides pre-trained checkpoints and evaluation scripts for measuring top-1 and top-5 accuracy. ([source](https://cdn.jsdelivr.net/gh/facebookresearch/convnext@main/README.md))
- [Model Fine-Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning.md) — Supports adapting pre-trained ConvNeXt models to custom datasets with training and logging.
- [Task-Specific Fine-Tuning Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning/fine-tuned-model-deployment/classification-fine-tuning/task-specific-fine-tuning-pipelines.md) — Supports transferring the pre-trained ConvNeXt backbone to detection, segmentation, or custom tasks. ([source](https://cdn.jsdelivr.net/gh/facebookresearch/convnext@main/README.md))
- [Pre-trained Model Zoos](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning/pre-trained-model-zoos.md) — Offers pre-trained model checkpoints ready for fine-tuning or direct inference on custom datasets.
- [Training and Evaluation Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/training-and-evaluation-pipelines.md) — Ships a training pipeline for ConvNeXt models on ImageNet-1K and ImageNet-22K datasets.

### Part of an Awesome List

- [ImageNet Classifier Training](https://awesome-repositories.com/f/awesome-lists/ai/model-training-and-fine-tuning/imagenet-classifier-training.md) — Provides training scripts for ConvNeXt models on ImageNet-1K and ImageNet-22K datasets. ([source](https://cdn.jsdelivr.net/gh/facebookresearch/convnext@main/README.md))
- [Vision](https://awesome-repositories.com/f/awesome-lists/ai/model-training-and-fine-tuning/model-fine-tuning/vision.md) — Ships scripts to adapt pre-trained ConvNeXt models to custom datasets with logging support. ([source](https://cdn.jsdelivr.net/gh/facebookresearch/convnext@main/README.md))

### Testing & Quality Assurance

- [Model Evaluation Benchmarks](https://awesome-repositories.com/f/testing-quality-assurance/model-evaluation-benchmarks.md) — Includes scripts to evaluate pre-trained ConvNeXt models on ImageNet validation data. ([source](https://cdn.jsdelivr.net/gh/facebookresearch/convnext@main/README.md))